Post emotion prediction system

Abstract

To provide a post emotion prediction system configured to determine post emotion for each spot with higher reliability.SOLUTION: A post emotion prediction system is configured to: acquire a posted sentence posted on a network together with spot information specifying a spot associated with the posted sentence and poster information related to a poster who has posted the posted sentence; analyze the acquired posted sentence to predict post emotion which is the emotion of the poster who has posted the posted sentence; apply weights to results of predicting post emotion, for each posted sentence, using at least one of the poster information and regional characteristics of a region including the spot associated with the posted sentence; aggregate the predicted post emotion for each spot associated with the posted sentence from which the post emotion is analyzed; and specify post emotion for each spot while referring to the weights.SELECTED DRAWING: Figure 10

Description

Technical Field

[0001] The present invention relates to a posted sentiment prediction system that predicts sentiment from posted texts posted on a network.

Background Art

[0002] In recent years, systems have been provided that enable users to post posted texts on a computer network via a terminal and view posted texts posted by other users. For example, there are blogs, SNS (Social Network Service), X (registered trademark), chats, etc. (hereinafter referred to as SNS, etc.). In addition, many of these posted texts include posted texts that post information about locations such as facilities visited by the poster.

[0003] Here, the above SNS, etc. have the merit of being able to quickly obtain the latest information experienced or felt by users who have actually visited the site, and various systems for providing information based on posted texts posted on the SNS, etc. have been proposed. For example, Japanese Patent Application Laid-Open No. 2019-20784 discloses a technique of collecting posted texts posted on an SNS and information for specifying the posting position, analyzing the posted texts posted at the same location, and determining whether positive sentiment or negative sentiment is dominant among the posters who posted the posted texts for that location, and displaying the determination result as a sentiment mark on a map image.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Here, in Patent Document 1 mentioned above, by collecting and analyzing the posted texts on SNS etc. for each location, it determines whether the sentiment of the posters at that location is positive sentiment or negative sentiment as a whole. However, in that analysis, it did not consider in which region the location to be judged is. However, as an example, in rural areas with a small young population, the number of users of SNS etc. decreases. Therefore, it is expected that the number of posts at stores etc. in such rural areas will be extremely small compared to the number of users in urban areas. If sentiment analysis is performed under the same conditions without considering such regional differences, there is a problem that a highly reliable sentiment determination cannot be made.

[0006] Also, on SNS etc., as long as formal user registration is performed and an account is created, basically anyone can post. Therefore, there are many posted texts with low reliability as information posted using accounts created for business or mischievous purposes among the posted texts. However, in Patent Document 1 mentioned above, it did not consider what kind of posters the posters were. Therefore, whether the posted text has low reliability or high reliability as information, they are treated the same, and there is also a problem that a highly reliable sentiment determination cannot be made.

[0007] The present invention has been made to solve the above-mentioned conventional problems, and by considering the regional characteristics of the location where the posted sentiment is to be specified, or the poster information of the posted text, it aims to provide a posted sentiment prediction system that enables a more reliable determination of the posted sentiment for each location.

Means for Solving the Problem

[0008] To achieve the above object, the post sentiment prediction system according to the present invention includes: a post text information acquisition means for acquiring a post text posted on a network together with location information for specifying a location associated with the post text and post author information regarding the author who posted the post; a sentiment prediction means for predicting a post sentiment, which is the sentiment of the author who posted the post text, by analyzing the post text acquired by the post text information acquisition means; a weighting means for weighting the prediction result by the sentiment prediction means for each post text using at least one of the regional characteristics of the region where the location associated with the post text is located and the post author information; and a location sentiment specifying means for classifying and aggregating the post sentiment predicted by the sentiment prediction means for each location associated with the post text serving as an analysis source, and specifying the post sentiment for each location with reference to the weighting.

Advantages of the Invention

[0009] According to the post sentiment prediction system according to the present invention having the above configuration, when specifying the post sentiment, which is the sentiment of the author who posted the post text for each location, by considering the regional characteristics of the region where the location for which the post sentiment is to be predicted is located, or the post author information of the author who posted the post text, it is possible to more reliably specify the post sentiment.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Mode for Carrying Out the Invention

[0011] Hereinafter, a submission sentiment prediction system according to the present invention will be described in detail with reference to the drawings based on an embodiment in which it is embodied as an information provision system 1. First, the schematic configuration of the information provision system 1 according to the present embodiment will be described with reference to FIG. 1. FIG. 1 is a schematic configuration diagram showing the information provision system 1 according to the present embodiment.

[0012] As shown in FIG. 1, the information provision system 1 according to the present embodiment basically includes an information provision server 3 provided in an information provision center 2 and a communication terminal 5 possessed by a user 4. Further, the information provision server 3 and the communication terminal 5 are configured to be able to transmit and receive electronic data to and from each other via a communication network 6. Note that examples of the communication terminal 5 include a mobile phone, a smartphone, a tablet terminal, a personal computer, and a navigation device which is an in-vehicle device.

[0013] Here, the information providing server 3 is a server device that manages information to be provided to the communication terminal 5 (i.e., the user who holds the communication terminal 5). The information providing server 3 stores information about information providing locations across the country that are targets for providing to the communication terminal 5 in the distribution information DB 7. Note that the information providing locations are not particularly limited in genre or scale, and examples include commercial facilities such as restaurants and retail stores, public facilities such as stations and hospitals, and in addition, accommodation facilities, parking lots, etc. Also, it is not limited to facilities, and for example, tourist spots, etc. may also be included. Further, as will be described later, the information about the information providing locations stored in the distribution information DB 7 includes, in addition to the name, address, position coordinates, telephone number, business hours, etc. of the information providing locations, information regarding "posted sentiment" identified by analyzing posted texts on the network in this embodiment. Details regarding the posted sentiment will be described later. Then, the information providing server 3 provides (distributes) the information about the information providing locations stored in the DB to the communication terminal 5 via the communication network 6.

[0014] In addition, the communication terminal 5 is an information terminal possessed by the user and equipped with communication functions, navigation functions, etc. For example, it corresponds to a mobile phone, a smartphone, a tablet terminal, a personal computer, a navigation device which is an in-vehicle device, etc. In particular, when the communication terminal 5 is a terminal capable of executing applications such as a smartphone, as one of the applications, it displays a map image of an area designated by the user, and can display an icon indicating the posted emotion with respect to the position of the above information providing point included in the displayed map image. An application program is installed. Further, in the above application program, by selecting an icon displayed on the map image, more detailed information regarding the information providing point corresponding to the selected icon can be obtained from the information providing server 3 and guided. Note that the selection of the information providing point to be guided can be made using the above map image, or can also be made from the search results obtained by inputting search conditions. Also, the function of guiding regarding these information providing points may be a part of the navigation function for guiding the movement to the destination, or may be executed by an application program different from the navigation function.

[0015] In addition, the communication network 6 includes a large number of base stations arranged throughout the country and a communication company that manages and controls each base station, and is configured by connecting the base stations and the communication company to each other by wire (optical fiber, ISDN, etc.) or wirelessly. Here, the base station has a transceiver (transmitter / receiver) and an antenna for communicating with the communication terminal 5. Then, while the base station performs wireless communication between communication companies, it becomes the end of the communication network 6 and has the role of relaying the communication of the communication terminal 5 within the range (cell) where the radio wave of the base station reaches between the information providing server 3.

[0016] On the one hand, the information providing server 3 included in the above information providing system 1 can obtain, from an SNS server 8 that provides a social networking service (hereinafter referred to as SNS) existing on the network, a posted text posted on the network, together with location information that identifies the location associated with the posted text and information that identifies the poster (more precisely, the poster's account) who posted the posted text (collectively referred to as posted text information). Furthermore, account information regarding an account registered as a service user of the SNS can also be obtained from the SNS server 8. Note that the method of obtaining the posted text information and the account information may be through the network or through a storage medium such as a flash memory.

[0017] Here, the SNS server 8 is a server device that constructs an SNS on the network. The SNS is a community-type service for constructing connections with others (which may include not only individuals but also corporations). Service users access from clients such as smartphones, tablet terminals, personal computers, etc., and by posting messages, images, etc., the content can be viewed by other service users. Also, other service users who view the messages and images can not only comment on the posts, but also quote and retweet (repost) the content, follow the poster using the follow function, or give a positive reaction (such as 'Like', 'いいね') when they empathize with the post content. Note that in this embodiment, it is an open-type SNS that can be used by anyone who is a registered user without any particular restrictions on the users. Also, the SNS server 8 is equipped with a storage DB 9, and messages, image data, the date and time of posting, hash tags, the location where the post was made (which can be a facility name or location coordinates), the number of positive reactions and the number of retweets received from other service users for each post are stored in the storage DB 9. Furthermore, for each registered service user (account), the number of posts made by the service user, the number of 'Likes' for the posts, the number of retweets of the retweets, the number of followers followed, etc. are stored in the storage DB 9 as account information related to that account.

[0018] And in this embodiment, the information providing server 3 acquires, as post information, from the SNS server 8, among the above data stored in the storage DB 9, a combination of the content of the post text (which may be only the message or may include the image if an image is attached), information identifying the poster who posted the post text (more precisely, the poster's account), and the location where the post text was posted. Furthermore, account information is also acquired as needed.

[0019] Next, the configuration of the information providing server 3 in the information providing system 1 will be described in more detail with reference to FIG. 2. As shown in FIG. 2, the information providing server 3 includes a server control unit 11, a posted text information DB 13 as information recording means connected to the server control unit 11, a distribution information DB 7, a map information DB 14, and a server-side communication device 15.

[0020] The server control unit 11 is a control unit (such as an MCU or MPU) that controls the entire information providing server 3, and includes a CPU 21 as an arithmetic unit and a control unit, a RAM 22 used as a working memory when the CPU 21 performs various arithmetic processes, a control program, and in addition, an internal storage device such as a ROM 23 in which an emotion analysis processing program (FIG. 6) and an information providing processing program (FIG. 11) described later are recorded, and a flash memory 24 that stores the program read from the ROM 23. Note that the server control unit 11 has various means as processing algorithms. For example, the posted text information acquisition means acquires a posted text posted on the network together with location information for specifying a location associated with the posted text and poster information regarding the poster who posted the text. The emotion prediction means predicts the posting emotion, which is the emotion of the poster who posted the posted text, by analyzing the posted text acquired by the posted text information acquisition means. The weighting means performs weighting on the prediction result by the emotion prediction means for each posted text using at least one of the regional characteristics of the region where the location associated with the posted text is located and the poster information. The location emotion specifying means classifies and totals the posting emotions predicted by the emotion prediction means for each location associated with the posted text serving as the analysis source, and specifies the posting emotion for each location with reference to the weighting.

[0021] The post information DB 13 is a storage means for storing the post information acquired from the SNS server 8. Here, the post information includes the post text posted on the network as described above, the location information identifying the location associated with the post text, and the information identifying the poster (more precisely, the poster's account) who posted the post text. Note that the "location associated with the post text" in this embodiment refers to the location where the post text was posted (the location where the poster who posted the post text is located). However, for example, if the post text contains a place name, or if the place name is associated as a hashtag, the place name may be regarded as the location associated with the post text.

[0022] Here, FIG. 3 is a diagram showing an example of the post information stored in the post information DB 13. As shown in FIG. 3, the content of the post text (message text data) in the post information DB 13 is stored in association with the location name indicating the location associated with the post text and the information (e.g., account ID) identifying the poster who posted the post. Note that in the example shown in FIG. 3, it is stored separately for each location name associated with the post text, but how to classify and store it can be changed as appropriate. Also, in the example shown in FIG. 3, the content of the post text is only text information, but if an image is attached, the image may also be included. Also, although the location name is stored as the information indicating the location associated with the post text, it may be position coordinates instead of the location name. Note that when the SNS server 8 receives a post text posted on the network by a service user (poster), the position coordinates of the terminal used by the service user for the post (identified by GPS or the like provided in the terminal) are also acquired as the location where the post text was posted. Therefore, when storing the specific location name where the post text was posted as post information as shown in FIG. 3, it is necessary to refer to the map information and identify the location name of the location where the service user is predicted to be located from the acquired position coordinates. However, this process may be performed by the SNS server 8 or the information providing server 3.

[0023] In addition, as described above, the distribution information DB7 is a storage means for storing various types of information regarding information-providing locations targeted for information provision across the country. Here, FIG. 4 is a diagram showing an example of the information stored in the distribution information DB7.

[0024] As shown in FIG. 4, in the distribution information DB7, for information-providing locations across the country, location ID, location name, location coordinates, detailed information about the location, current congestion status, posted sentiment, regionality level, poster level, etc. are stored. However, it is not necessarily required to store all of these pieces of information in the distribution information DB7. Incidentally, regarding "posted sentiment", specifically, it is to identify which sentiment the sentiment of the poster (accurately, the poster who posted the post at that location) regarding the post about that location as a whole belongs to, and it is identified by the server control unit 11 by analyzing the post information stored in the post information DB13 as described later. Incidentally, there are various human emotions such as joy, trust, fear, surprise, sadness, disgust, anger, expectation, etc. In particular, in this embodiment, the posted sentiment is determined without classifying the types of emotions, using two types, positive sentiment (positive emotion) and negative sentiment (negative emotion), as judgment elements, to identify whether the poster's sentiment is closer to positive sentiment or negative sentiment, or whether it is neutral (neither).

[0025] In addition, the "regionality level" indicates the regional characteristics of the region where the information-providing location is located. For example, it is shown in 10 levels from level 1 (low) to level 10 (high). Incidentally, the regional characteristics are comprehensively judged using, for example, population density, average age group, transportation infrastructure (transportation infra) maintenance status, etc. It indicates that the lower the level, the more sparsely populated the area is where it is predicted that there are fewer SNS users, and the higher the level, the more populated the city is where it is predicted that there are more SNS users.

[0026] Also, the "contributor level" indicates the reliability of the information of the contribution made to the information providing location (the reliability of the contributor making the contribution). For example, it is indicated by 10 levels from level 1 (low) to level 10 (high). As an example, when a contributor who has made a large number of contributions in the past and received empathy from a third party for the contribution makes a contribution, the content of the contribution is considered reliable and thus judged to be at a high level. Note that the calculation methods of the "regional level" and the "contributor level" will be described later.

[0027] For example, in the distribution information DB7 shown in FIG. 4, for the "XX Station" at the position coordinates (x1, y1), facility information, the current congestion status, as well as the contribution sentiment, regional level, and contributor level are stored. Similarly, information regarding other information providing locations is also stored.

[0028] Also, the map information DB14 is a storage means for storing map information. The map information is composed of various information necessary for route search, route guidance, and map display, including a road network. For example, it consists of link data regarding roads (links), node data regarding node points, intersection data regarding each intersection, point data regarding locations such as facilities, map display data for displaying a map, search data for searching for a route, search data for searching for a point, and the like.

[0029] Then, the server control unit 11 uses the map information DB14 to, in response to a request from the communication terminal 5, for example, transmit map display data for displaying a map image on the communication terminal 5, search for a point corresponding to the input search condition, or, when receiving a route search request, perform a route search from the departure point to the destination using the map information stored in the map information DB14.

[0030] However, when the communication terminal 5 has map information, the communication terminal 5 can perform the above processing using the map information it has. In that case, the map information DB14 is not necessarily required in the information providing server 3.

[0031] On one hand, the server-side communication device 15 is a communication device for communicating with the communication terminal 5 which is the target of information transmission and reception via the communication network 6. In addition to the communication terminal 5, it is also possible to receive traffic information composed of various information such as traffic jam information, regulation information, and traffic accident information transmitted from the Internet, traffic information centers, for example, VICS (registered trademark: Vehicle Information and Communication System) centers, etc. Furthermore, in addition to traffic information, by communicating with external servers, it is possible to receive weather information in various regions across the country, event information regarding events held across the country, local news, congestion information at locations, regional characteristics (population density, average age group, traffic infrastructure development status) for each region, etc.

[0032] Next, the schematic configuration of the communication terminal 5 owned by the user will be described with reference to FIG. 5. FIG. 5 is a block diagram schematically showing the control system of the communication terminal 5 according to the present embodiment. Hereinafter, the case where the communication terminal 5 is a smartphone will be described as an example.

[0033] As shown in FIG. 5, the communication terminal 5 is configured by connecting a CPU 31, a memory 32 in which user information (user ID, name, etc.) regarding the user who owns the communication terminal 5 and application programs are stored, an input / output unit 35 which is an interface such as a microphone 33 and a speaker 34, a display 36 composed of a liquid crystal display panel, etc., an input operation unit 37 composed of a touch panel, a keyboard, etc., a GPS 38, and a transmission / reception circuit unit (RF) 39 for transmitting and receiving signals to and from the base station of the communication network 6 to the data bus BUS.

[0034] Here, the CPU 31 built into the communication terminal 5 is a control means for the communication terminal 5 that executes various operations according to the operation program stored in the memory 32, and constitutes the communication terminal control unit 41 together with the memory 32. Also, the various processing contents of the communication terminal control unit 41 are displayed on the display 36 as necessary. Note that the communication terminal control unit 41 constitutes various means as a processing algorithm. For example, the posted emotion display means displays the specified posted emotion for the specified location on the screen.

[0035] In addition to making calls, the communication terminal 5 can communicate via the transmission / reception circuit unit 39 to perform Internet communication, receive information on charging facilities from the information providing server 3, and receive traffic information composed of various information such as traffic jam information, regulation information, and traffic accident information transmitted from a traffic information center, for example, a VICS (registered trademark) center or a probe center.

[0036] In addition, the memory 32 is a storage medium that stores user information (user ID, name, etc.) regarding the user who owns the communication terminal 5, map information, the user's web browsing history, the user's movement history, which is a history of position information detected based on the GPS 38 and other sensors, schedule information, etc. Also, various application programs including the information providing processing program (FIG. 11) described later are stored. Also, the memory 32 may be composed of a hard disk, a memory card, etc.

[0037] In addition to voice output for calls, when the navigation function is executed, the speaker 34 outputs voice guidance for guiding driving along the guided route (the user's planned movement route) based on an instruction from the communication terminal control unit 41.

[0038] In addition, the display 36 is disposed on one surface of the housing, and a liquid crystal display, an organic EL display, or the like is used. Then, the top screen for executing various applications installed in the communication terminal 5, the screen related to the executed application (Internet screen, mail screen, navigation screen, etc.), and various information such as images and videos are displayed. In particular, in this embodiment, a map image of the area designated by the user is displayed, and an icon indicating the posted emotion is displayed at the position of the information providing point included in the displayed map image. Further, when the icon displayed on the map image is selected, more detailed information about the information providing point corresponding to the selected icon is displayed.

[0039] In addition, the input operation unit 37 is composed of a touch panel provided on the front surface of the display 36, hard buttons arranged on the housing, and the like. Then, the communication terminal control unit 41 performs control to execute corresponding various operations based on the electrical signals output by pressing the touch panel or the hard buttons. Incidentally, the input operation unit 37 can also be composed of various keys such as a number / character input key, a cursor key for moving a cursor for selecting the displayed content, and a decision key for confirming the selection.

[0040] In addition, the GPS 38 can detect the current position and current time of the communication terminal 5 (that is, the user) by receiving radio waves generated by artificial satellites. In addition to the GPS 38, it may also be configured to include other devices (for example, a gyro sensor, etc.) for detecting the current position and orientation of the communication terminal 5.

[0041] In addition, the transmission / reception circuit unit 39 is a circuit unit for transmitting and receiving signals to and from the base station of the communication network 6 according to communication standards such as 3G, 4G, and LTE.

[0042] Next, in the information providing system 1 having the above configuration, the sentiment analysis processing program executed by the information providing server 3 will be described with reference to FIG. 6. FIG. 6 is a flowchart of the sentiment analysis processing program according to the present embodiment. Here, the sentiment analysis processing program is executed after a predetermined time (for example, 24 hours) has elapsed since the previous execution, and by analyzing the posted text information stored in the posted text information DB 13, it is a program for specifying "posted sentiment", "regionality level", and "poster level" for each information providing location. Note that the programs shown in the flowcharts in FIGS. 6 and 11 below are stored in the RAM 22, ROM 23, etc. provided in the information providing server 3 and are executed by the CPU 21.

[0043] Here, the sentiment analysis processing program executes processing for information providing locations across the country, and "posted sentiment", "regionality level", and "poster level" are to be specified for each information providing location. However, it is not necessarily required to execute processing for all information providing locations across the country. For example, it is also possible to execute it targeting only specific genres or locations of a predetermined scale or larger. Also, the interval for executing the sentiment analysis processing program for each location may be changed.

[0044] First, in step (hereinafter abbreviated as S) 1, the CPU 21 determines whether there is posted text information associated with the information providing location that is the evaluation target this time in the posted text information DB 13. Note that in order to perform accurate sentiment analysis, it is desirable to exclude old posted texts from the analysis target, and basically, it is determined whether there is posted text information posted within 3 months or within half a year. Also, it may be determined whether there is at least one or more posted text information, but since accurate analysis is difficult when the number of samples is small, it may be determined whether there is a predetermined number (for example, 3) or more of posted text information.

[0045] Here, as shown in FIG. 3, the posted text information DB 13 stores the posted text information obtained in advance from the external SNS server 8. In particular, the content of the posted text (text data of the message) is stored in association with the location name indicating the location (the place where the posted text was posted) linked to the posted text and the poster who posted the posted text (more precisely, the poster's account). Therefore, in step S1, it is determined whether there is posted text information linked to the location name of the information providing location to be evaluated.

[0046] When it is determined that there is posted text information linked to the information providing location to be evaluated this time in the posted text information DB 13 (S1: YES), the process proceeds to S2. On the contrary, when it is determined that there is no posted text information linked to the information providing location to be evaluated this time in the posted text information DB 13 (S1: NO), since no posted text to be analyzed exists for the sentiment of the information providing location to be evaluated, the sentiment analysis processing program is terminated.

[0047] In S2, the CPU 21 extracts and acquires the posted text information linked to the information providing location to be evaluated this time from the posted text information DB 13. Incidentally, in order to perform accurate sentiment analysis, it is desirable to exclude old posted texts from the analysis target, and basically, the posted text information posted within 3 months or within 6 months is acquired as the target.

[0048] Then, the following processes of S3 to S6 are performed for each of the posted text information obtained in S2, and after executing the processes of S3 to S6 for all the obtained posted text information, the process proceeds to S7.

[0049] First, in S3, the CPU 21 performs sentiment analysis on the post information to be processed, and particularly predicts the post sentiment, which is the sentiment of the poster who posted the post, from the text data indicating the post content. Here, there are various methods for sentiment analysis, such as machine learning, rule-based, and combinations thereof. As an example, in sentiment analysis applying machine learning such as deep learning, by inputting the text data of the post, it is possible to output information identifying the "sentiment category" of the post sentiment from the text data (S4). In sentiment analysis applying machine learning, it is possible to analyze the sentiment from the text data based on elements such as the meaning of words appearing in the sentence, the context of the words used, and the expression method, rather than analyzing individual words by natural language processing technology.

[0050] In addition, the "sentiment category" identifies the tendency of sentiment. In this embodiment, for the purpose of particularly identifying which of positive sentiment and negative sentiment is dominant, it is classified into three categories: 'Positive', 'Neutral (a neutral state between positive and negative)', and 'Negative'. However, it may be classified more simply into either 'Positive' or 'Negative', or conversely, it may be classified in more detail down to the types of sentiment such as 'Joy', 'Trust', 'Fear', 'Surprise', 'Sadness', 'Disgust', 'Anger', 'Expectation', etc. Also, in the sentiment analysis of S3, in addition to identifying the "sentiment category", it may be possible to identify the "degree of sentiment", which indicates the magnitude (amount of sentiment) of the sentiment in the identified sentiment category. For example, it may be specified in 10 steps in increments of 0.1 from 0.1 (low) to 1.0 (high). If the level is 0.1 for 'Positive', the post sentiment is positive but a weak sentiment close to neutral, while if the level is 1.0 for 'Positive', it indicates that the post sentiment is positive and a very strong sentiment in the positive direction.

[0051] Here, FIG. 7 is a diagram showing an example of the “emotion category” output as a result of performing emotion analysis on the posted text information of S3. For example, in the example shown in FIG. 7, by performing emotion analysis on a posted text such as “It is sunny today”, “Neutral” is output as the posted emotion. Similarly, by performing emotion analysis on a posted text such as “There is a sale at ○○”, “Positive” is output as the posted emotion. Similarly, by performing emotion analysis on a posted text such as “I was looking forward to it but it rained”, “Negative” is output as the posted emotion. Similarly, by performing emotion analysis on a posted text such as “The event was cancelled”, “Negative” is output as the posted emotion.

[0052] After that, in S5, the CPU 21 acquires the account information of the poster who posted the posted text information to be processed from the SNS server 8. Here, the account information acquired in S5 is information indicating the evaluation of a third party for that account, that is, the reliability for the posted text. More specifically, it includes the number of posts made so far on that account, the number of “likes” for the posts, the number of retweets retweeted, the number of followers followed, and the like.

[0053] Subsequently, in S6, the CPU 21 sets poster parameters for the posted text information to be processed based on the account information (poster information) of the poster acquired in S5. The poster parameters set in S6 are used as weights for the prediction results of the posted emotions predicted in S3. Specifically, the poster parameters are set as follows.

[0054] First, as shown in FIG. 8, the CPU 21 identifies parameter values based on the number of "likes" that can be obtained as the account information of the poster who posted the post information to be processed in S5, the number of retweets, and the number of followers. Specifically, if the number of "likes", the number of retweets, and the number of followers are less than 10, a parameter value of 0.03 is identified. Similarly, if the number of "likes", the number of retweets, and the number of followers are 10 or more and less than 100, a parameter value of 0.08 is identified. If the number of "likes", the number of retweets, and the number of followers are 100 or more and less than 500, a parameter value of 0.12 is identified. If the number of "likes", the number of retweets, and the number of followers are 500 or more and less than 1000, a parameter value of 0.22 is identified. If the number of "likes", the number of retweets, and the number of followers are 1000 or more and less than 5000, a parameter value of 0.25 is identified. If the number of "likes", the number of retweets, and the number of followers are 5000 or more, a parameter value of 0.30 is identified. Then, the sum of the parameter value identified for the number of "likes", the parameter value identified for the number of retweets, and the parameter value identified for the number of followers is calculated, and the calculated total value is used as the poster parameter.

[0055] Here, for the post information with a large numerical value of the poster parameter set in S6, it is expected that the poster who posted the post has made a large number of posts in the past and received empathy from third parties for the post, that is, the reliability of the information for the post is high. On the other hand, for the post information with a small numerical value of the poster parameter set in S6, the poster who posted the post is a new account that has rarely posted in the past or an account that has not transmitted accurate information so far. That is, the reliability of the information for the post is expected to be low.

[0056] In the same way, for each post information obtained in S2, the emotion category is identified and the poster parameter is set (S3 to S6). After the emotion category is identified and the poster parameter is set for all the obtained post information, the process proceeds to S7.

[0057] In S7, the CPU 21 acquires the regional characteristics of the region where the information providing point to be evaluated this time is located. Here, the regional division is based on administrative divisions such as municipalities, but it may be narrower (for example, at the town or cho unit level) or wider (for example, at the prefecture level). Also, as regional characteristics, for example, population density, average age group, and the state of traffic infrastructure (hereinafter referred to as traffic infra) are acquired. On the other hand, the population density may be the population density including all age groups, but in this embodiment, it is the population density targeted at the population expected to use SNS in particular, specifically, the population density of those under 40 years old, and is calculated by, for example, the following formula (1). Population density = Population under 40 years old × 2 / Area of the region ··· (1) However, other than the above may be acquired as regional characteristics. For example, the total population, population density including all age groups, average land price, etc. may be acquired. These regional characteristics may be acquired from the map information DB 14 as part of the map information, for example, or may be acquired from an external server via the Internet or the like.

[0058] Subsequently, in S8, the CPU 21 sets a regionality parameter for the information providing point to be evaluated this time based on the regional characteristics of the region where the information providing point to be evaluated this time is located, which were acquired in S7. The regionality parameter set in S8 is used as a weighting for the prediction result of the posted sentiment predicted in S3. Specifically, the regionality parameter is set as follows.

[0059] First, as shown in FIG. 9, the CPU 21 specifies parameter values based on the population density (in this embodiment, specifically those under 40 years old), average age group, and the state of traffic infra that can be acquired as the regional characteristics of the region where the information providing point to be evaluated this time is located in S5. Specifically, for example, for the population density, if it is 6000 people / km 2 or more, a parameter value of 0.1 is specified. Similarly, for the population density, if it is 800 people / km 2 or more and less than 6000 people / km 2 a parameter value of 0.2 is specified. For the population density, if it is 800 people / km2 If it is less than that, 0.7 is specified as the parameter value. Also, if the average age group is less than 45 years old, 0.1 is specified as the parameter value. Similarly, if the average age group is 45 years old or more and less than 60 years old, 0.2 is specified as the parameter value. If the average age group is 60 years old or more, 0.7 is specified as the parameter value. Also, if the area has an international airport in terms of the transportation infrastructure development status, 0.1 is specified as the parameter value. Similarly, if there is any of a Shinkansen station, an airport, or a ferry port, 0.1 is specified as the parameter value. Even if there is no such airport or Shinkansen station, if there is any of a conventional line station or a bus stop, 0.3 is specified as the parameter value. Furthermore, if there is no such transportation infrastructure at all, 0.5 is specified as the parameter value. Then, the sum of the parameter value specified for the population density, the parameter value specified for the average age group, and the parameter value specified for the transportation infrastructure development status is calculated, and the calculated total value is used as the regionality parameter.

[0060] Here, an information providing point located in an area where the numerical value of the regionality parameter set in S8 is large is in an area where the young population is small and the transportation infrastructure is not developed (that is, the number of people visiting from outside the area is small), and it is expected that there are few users who use SNS and the number of posts is small compared to the number of users. On the other hand, an information providing point located in an area where the numerical value of the regionality parameter set in S8 is small is in an area where the young population is large and the transportation infrastructure is developed (that is, the number of people visiting from outside the area is large), and it is expected that there are many users who use SNS and the number of posts is large compared to the number of users.

[0061] After that, in S9, the CPU 21 calculates the number of points (evaluation points) for each emotion category for the information providing point that is the evaluation target this time. Here, in the present embodiment, the emotion categories are classified into three: 'Positive', 'Neutral (a neutral state in the middle of positive and negative)', and 'Negative' as described in S3. Specifically, the number of points for each emotion category is calculated as follows.

[0062] First, as shown in FIG. 10, for the information-providing location to be evaluated this time (in the example shown in FIG. 10, it is ○○ Restaurant), the CPU 21 calculates a point by multiplying the contributor parameter set in S6 and the regionality parameter set in S8 for each piece of post information obtained in S2. However, the point may be calculated by adding instead of multiplying. Since the regionality parameter is set for each information-providing location, all pieces of post information for the same information-providing location will have the same value. On the other hand, since the contributor parameter varies depending on the contributor who posted the post, even for pieces of post information for the same information-providing location, different values will be obtained for each post. For example, in the example shown in FIG. 10, since the contributor parameter set based on the contributor information of post A is 1.58, the point for post A is 1.1×1.58 = 1.73. Similarly, since the contributor parameter set based on the contributor information of post B is 0.15, the point for post B is 1.1×0.15 = 0.16. Also, since the contributor parameter set based on the contributor information of post C is 0.18, the point for post C is 1.1×0.18 = 0.19. Further, since the contributor parameter set based on the contributor information of post D is 0.15, the point for post D is 1.1×0.15 = 0.16.

[0063] After that, the CPU 21 classifies and totals the points calculated for each posted text information by emotion category, and calculates the number of points (evaluation points) for each emotion category. For example, in the example shown in FIG. 10, as a result of the emotion analysis in S3, the emotion categories predicted to be 'positive' are posted text A and posted text C, and 1.93, which is the total value of the points calculated for posted text A and posted text C, becomes the number of points for 'positive'. Similarly, the emotion category predicted to be 'negative' is posted text B, and 0.16, which is the point calculated for posted text B, becomes the number of points for 'negative'. Also, the emotion category predicted to be 'neutral' is posted text D, and 0.16, which is the point calculated for posted text D, becomes the number of points for 'neutral'. Note that the number of points (evaluation points) for each emotion category calculated in S9 is the result of weighting the prediction results of the posted emotions for each posted text in S3 using regional characteristics and poster information, and aggregating them, and indicates the reliability of the prediction results of the posted emotions for each emotion category. That is, the higher the number of points, the closer that emotion category is to the overall consensus of the posted emotions for the information-providing location.

[0064] Subsequently, in S10, the CPU 21 compares the number of points (evaluation points) for each emotion category calculated in S9 for the information-providing location that is the evaluation target this time, and specifies the emotion category with the highest number of points as the posted emotion of the information-providing location that is the evaluation target this time. For example, in the example shown in FIG. 10, since the number of points for 'positive' is the highest, the posted emotion of ○○ Restaurant is specified as 'positive'. However, it is also possible to set the minimum value of the number of points and make it a condition for specifying the posted emotion that the number of points of the emotion category with the highest number of points is equal to or higher than the minimum value.

[0065] In this embodiment, at an information providing location in a rural area where the regionality parameter is high, that is, where the number of posts is predicted to be small for the user, by performing the above weighting, the degree to which the prediction result of the posting sentiment for each post is affected becomes greater. As a result, regional differences can be compensated for and equal evaluation becomes possible. For example, regarding the number of points (evaluation points) calculated in S10 above, the difference in the number of points for each sentiment category is more likely to be larger than that at an information providing location in an urban area. Therefore, even if the number of posts is small, it becomes easier to identify the posting sentiment. Furthermore, if the number of points (evaluation points) is also guided, even if the number of posts is small, it will become a target of attention, leading to, for example, the discovery of high-quality stores known only to local residents. Also, particularly when a highly reliable poster makes a post, the degree to which the prediction result of the posting sentiment for that post affects the identification of the overall posting sentiment becomes greater. As a result, by respecting highly reliable information more, it becomes possible to more accurately identify the posting sentiment.

[0066] Next, in S11, the CPU 21 calculates the regionality level for the information providing location that is the target of the current evaluation. Note that the "regionality level" indicates a relative evaluation by comparing the regional characteristics of the region where the information providing location is located with other regions. The lower the level, the more sparsely populated the area is where it is predicted that there are fewer SNS users, and the higher the level, the more populated the urban area is where it is predicted that there are more SNS users. Specifically, it is calculated as follows by comparing the regionality parameter (weighting based on regional characteristics) set in S8 for the information providing location that is the target of the current evaluation with other locations.

[0067] First, the minimum value of the regionality parameter that could theoretically be set for locations across the country (0.3 in the example shown in FIG. 9) is set as level 1, and the maximum value of the regionality parameter (1.9 in the example shown in FIG. 9) is set as level 10. By dividing the range between them into 10 equal parts, each reference value of the regionality parameter from level 1 to level 10 is determined. Then, among the reference values from level 1 to level 10, the level corresponding to the reference value closest to the regionality parameter set in S8 for the information providing location that is the target of the current evaluation is set as the regionality level of the information providing location that is the target of the current evaluation.

[0068] Subsequently, in S12, the CPU 21 calculates the contributor level for the information providing location that is the subject of the current evaluation. Note that the "contributor level" is a relative evaluation that compares the contributor information of the region where the information providing location is located with that of other regions. The lower the level, the lower the reliability of the information of the posts made for that information providing location (the reliability of the contributor making the post), and the higher the level, the higher the reliability of the information of the posts made for that information providing location (the reliability of the contributor making the post). Specifically, it is calculated as follows by comparing the contributor parameters (weighting based on contributor information) set in S6 for the information providing location that is the subject of the current evaluation with other locations.

[0069] Specifically, the minimum value of the contributor parameters that could theoretically be set for locations across the country (0.09 in the example shown in FIG. 8) is set as level 1, and the maximum value of the contributor parameters (0.9 in the example shown in FIG. 8) is set as level 10. The reference values of the contributor parameters for levels 1 to 10 are determined by dividing the range between them into 10 equal parts. Then, among the reference values for levels 1 to 10, the level corresponding to the reference value closest to the contributor parameters set in S6 for the information providing location that is the subject of the current evaluation is taken as the contributor level of the information providing location that is the subject of the current evaluation. Note that when a plurality of post text information is associated with the information providing location that is the subject of the current evaluation (a plurality of posts have been made), and a plurality of contributor parameters are set for the same information providing location, the contributor level may be calculated using the highest contributor parameter, or the average value or median value of the contributor parameters may be used to calculate the contributor level.

[0070] After that, in S13, the CPU 21 stores the posting sentiment specified in S10 as the "posting sentiment" for the information providing location that is the target of the current evaluation in the distribution information DB 7. Similarly, the "regionality level" specified in S11 and the "poster level" specified in S12 are also stored in the distribution information DB 7. As described above, the distribution information DB 7 stores various types of information including information regarding "posting sentiment", "regionality level", and "poster level" for information providing locations that are targets of information provision across the country (Fig. 4).

[0071] Subsequently, in the information providing system 1, the information providing processing program executed by the information providing server 3 and the communication terminal 5 will be described with reference to Fig. 11. Fig. 11 is a flowchart of the information providing processing program according to the present embodiment. Here, the information providing processing program is executed after a predetermined application program for obtaining information on the information providing location is launched in the communication terminal 5, and is a program for providing information regarding the information providing location to the user. Note that the program shown as a flowchart in Fig. 11 below is stored in the RAM or ROM provided in the information providing server 3 or the communication terminal 5, and is executed by the CPU 21 or the CPU 31.

[0072] First, the information providing processing program executed by the CPU 31 of the communication terminal 5 will be described with reference to Fig. 11. In S21, the CPU 31 launches a predetermined application program for obtaining information on the information providing location (hereinafter referred to as the information providing app). Note that the information providing app may be a navigation app or a dedicated application program different from the navigation app. It is assumed that the information providing app has been downloaded in advance from a web server or the like and installed in the communication terminal 5.

[0073] Here, when the information providing application is launched on the communication terminal 5, first, a map image around the current location is displayed on the display 36 (S22). Note that the map display data for displaying the map image 51 is acquired from the information providing server 3. The map image 51 displayed on the display 36 can be freely scaled or the display target area can be changed based on the user's operation.

[0074] Next, in S23, the CPU 31 transmits a request signal to the information providing server 3 that requests information regarding the information providing point included in the map image that is the display target on the display 36 at the current time. Note that the request signal includes the terminal ID that identifies the transmitting communication terminal 5 and the point ID that identifies the information providing point included in the map image that is the display target on the display 36 at the current time (the point name or position coordinates may be used instead of the point ID).

[0075] Thereafter, in S24, the CPU 31 receives the information transmitted from the information providing server 3 in response to the request signal transmitted in S23 above. Note that the information received in S24 is information regarding the information providing point included in the map image that is the display target on the display 36 at the current time, particularly information regarding the "posted sentiment" identified by the aforementioned sentiment analysis processing program (Figure 6).

[0076] Subsequently, in S25, the CPU 31 displays an icon indicating the existence of the information providing point at the position where the information providing point exists in the map image around the current location displayed on the display 36. Also, the icon indicates the posted sentiment of the information providing point.

[0077] Here, FIG. 12 is a diagram showing an example of the icon displayed in S25. As shown in FIG. 12, a map image 51 is displayed on the display 36, and an icon 52 is further displayed at the position where the information-providing point exists in the map image 51. The appearance of the icon 52 mimics a face, and there are three types of expressions, and the posted feelings of the information-providing point are indicated by the differences in the expressions. Specifically, if it is 'positive', it is a smiling expression; if it is 'negative', it is an expression of anger; and if it is 'neutral', it is a blank expression. Therefore, if the user visually recognizes the icon 52, the user can easily grasp the posted feelings of the information-providing point. In addition, when the type and magnitude of the posted feelings are specified for the information-providing point in the above-described sentiment analysis processing program (FIG. 6), the magnitude of the feelings may be indicated by the icon 52. For example, it is possible to change the display size or the display color of the icon 52. In addition, for an information-providing point for which the posted feelings cannot be specified, it may be possible not to display the icon 52, or it may be possible to display the 'neutral' icon 52.

[0078] Also, the icon 52 displayed on the map image 51 is a selection target for the user. In S26, the CPU 31 determines whether or not it has received an operation in which the user selects any one of the icons 52 displayed on the map image 51 based on a signal from the input operation unit 37.

[0079] When it is determined that the operation in which the user selects any one of the icons 52 displayed on the map image 51 has been received (S26: YES), the process proceeds to S27. On the other hand, when it is determined that the operation in which the user selects any one of the icons 52 displayed on the map image 51 has not been received (S26: NO), the information-providing processing program is terminated.

[0080] Subsequently, in S27, the CPU 31 transmits a request signal to the information providing server 3 to request more detailed information regarding the information providing point corresponding to the icon 52 selected by the user. Note that the request signal includes a terminal ID for identifying the communication terminal 5 of the transmission source and a point ID for identifying the information providing point corresponding to the icon 52 selected by the user (the point name or position coordinates may be used instead of the point ID).

[0081] Thereafter, in S28, the CPU 31 receives the information transmitted from the information providing server 3 in response to the request signal transmitted in S27. Note that the information received in S28 is more detailed information regarding the information providing point corresponding to the icon 52 selected by the user.

[0082] Next, in S29, the CPU 31 displays, on the display 36, more detailed information regarding the information providing point corresponding to the icon 52 selected by the user based on the information received in S28. Note that the information to be displayed includes, in addition to the "posting sentiment", "regional level", and "poster level" specifically identified by the aforementioned sentiment analysis processing program (Fig. 6), the "posting reaction prediction" obtained by the information providing server 3 in S39 described later. Although the details of the "posting reaction prediction" will be described later, briefly, it is a prediction of the degree of reaction that will be obtained from a third party if the user newly posts on the SNS regarding the information providing point corresponding to the icon 52 selected this time.

[0083] Here, Fig. 13 shows an example of the information providing screen 53 displayed on the display 36 in S29. In the example shown in Fig. 13, the information providing screen 53 displays, for example, the name of the information providing point, an exterior photo, information regarding the details of the point such as business hours and contact information, "posting sentiment", "regional level", "poster level", and "posting reaction prediction".

[0084] Specifically, regarding "posting sentiment", it identifies which sentiment the emotions of the posters who posted posts related to the selected information-providing location as a whole belong to, and one of the emotion categories of "Positive", "Negative", or "Neutral" identified in S10 is displayed. Regarding "regional level (first information)", it shows a relative evaluation by comparing the regional characteristics of the region where the selected information-providing location is located with other regions, and the level is indicated by the position of the pointer 55 relative to the scale 54 in the left-right direction. The level is in 10 grades. The lower the level (the more the position of the pointer 55 is on the right side), the more sparsely populated the area is where it is predicted that there are fewer SNS users. The higher the level (the more the pointer 55 is on the left side), the more populated the urban area is where it is predicted that there are more SNS users. Regarding "poster level (second information)", it shows a relative evaluation by comparing the poster information of the region where the selected information-providing location is located with other regions, and the level is indicated by the position of the pointer 57 relative to the scale 56 in the left-right direction. The level is in 10 grades. The lower the level (the more the position of the pointer 57 is on the right side), the lower the reliability of the information of the posts made for the information-providing location (the reliability of the posters making the posts). The higher the level (the more the pointer 57 is on the left side), the higher the reliability of the information of the posts made for the information-providing location (the reliability of the posters making the posts). Regarding "post reaction prediction", if the user were to newly post on SNS about the information-providing location selected this time, it shows predictions of the degree of reaction from third parties in terms of the number of "likes" and the number of "retweets" respectively. Specifically, it is indicated by the direction of the arrow. If the direction of the arrow is horizontal, it indicates that the number of "likes" and the number of "retweets" of about the reference value are predicted to be obtained. Also, if the direction of the arrow is upward, it indicates that the number of "likes" and the number of "retweets" more than the reference value are predicted to be obtained. Further, if the direction of the arrow is downward, it indicates that the number of "likes" and the number of "retweets" less than the reference value are predicted to be obtained. Note that the reference value may be a fixed value (for example, 10), or the average value of the number of "likes" and the number of "retweets" for the user's previous posts, or the average value of the number of "likes" and the number of "retweets" for the posted texts made for information-providing locations across the country regardless of the user.

[0085] Note that the information-providing screen 53 shown in FIG. 13 is just an example, and any display mode may be used as long as "post sentiment", "region level", "poster level", and "post reaction prediction" are displayed. By the user visually recognizing the information-providing screen 53 shown in FIG. 13, the user can obtain an accurate evaluation based on the posted text for the specified location. In particular, in addition to the regional characteristics of the location and the level (information reliability) of the posters who have made posts for that location, it is also possible to grasp the prediction of the reaction from third parties in the case where the user himself / herself makes a post.

[0086] Next, the information-providing processing program executed by the CPU 21 of the information-providing server 3 will be described. Note that each of the following processes S31 to S40 starts at the timing of receiving the corresponding information from the communication terminal 5. Therefore, the execution order of each step is not necessarily in the order of the smaller step numbers.

[0087] First, in S31, the CPU 21 receives a request signal for information transmitted from the communication terminal 5. Note that the request signal includes a terminal ID for identifying the source communication terminal 5 and a location ID for identifying the information-providing location corresponding to the icon 52 selected by the user (the location name or location coordinates may be used instead of the location ID).

[0088] After that, in S32, the CPU 21 extracts information regarding the requested information-providing location from the distribution information DB 7 based on the request signal received in S31. Note that as described above, the distribution information DB 7 stores various types of information regarding information-providing locations targeted for information provision across the country, including information regarding "posted sentiment", "regional level", and "poster level" (Figure 4), but in S32, only the "posted sentiment" is particularly extracted.

[0089] Subsequently, in S33, the CPU 21 transmits the "posted sentiment" as information regarding the information-providing location extracted in S32 to the communication terminal 5, which is the source of the request signal received in S31. After that, on the communication terminal 5 that has received the information, the posted sentiment of the information-providing location is displayed as an icon 52 on the map image 51 as described above (Figure 12).

[0090] Next, in S34, the CPU 21 receives a request signal for detailed information transmitted from the communication terminal 5. Note that the request signal includes a terminal ID for identifying the source communication terminal 5 and a location ID for identifying the information-providing location corresponding to the icon 52 selected by the user (the location name or location coordinates may be used instead of the location ID).

[0091] After that, in S35, the CPU 21 extracts information regarding the requested information-providing location from the distribution information DB 7 based on the request signal received in S34. Note that as described above, the distribution information DB 7 stores various types of information regarding information-providing locations targeted for information provision across the country, including information regarding "posted sentiment", "regional level", and "poster level" (Figure 4), but in S35, basically all of that information is extracted.

[0092] Subsequently, in S36, the CPU 21 identifies the user who is making an information request based on the terminal ID that identifies the communication terminal 5 of the sender, and acquires the account information of that user from the SNS server 8. Here, the account information acquired in S36 is information indicating the evaluation of a third party with respect to that account, that is, the reliability with respect to the posted text. More specifically, it includes the number of posts made so far with that account, the number of "likes" for the posts, the number of retweets of the retweets, the number of followers who have followed, and the like.

[0093] Subsequently, in S37, the CPU 21 also acquires from the SNS server 8 the account information of the poster who is posting at the information request point where information is being requested, and searches for account information similar to the account information of the user who is making the information request. Regarding whether there is similar account information or not, for example, compare the number of "likes", the number of retweets, and the number of followers, and search for accounts where some or all are close. For example, regarding the number of followers, divide it into less than 10 people, 10 people or more and less than 10,000 people, and 10,000 people or more, and consider accounts that fall into the same category as having similar account information. Also, regarding the number of "likes" and the number of retweets, the total number obtained so far may be compared, the average number obtained per post may be compared, or both may be compared.

[0094] Then, in S38, the CPU 21 determines, based on the result of the search in S37, whether there is account information similar to the account information of the user who is making the information request among the account information of the poster who is posting at the information request point where information is being requested. Note that, without being limited to the account information of the poster who is posting at the information request point where information is being requested, the account information of the poster who is posting at an information providing point with the same scale or the same regional characteristics may also be included in the search target.

[0095] When it is determined that there is account information similar to the account information of the user making the information request (S38: YES), the process proceeds to S39. On the other hand, when it is determined that there is no account information similar to the account information of the user making the information request (S38: NO), the process proceeds to S40. Incidentally, when it is determined that there is no account information similar to the account information of the user making the information request, the above-mentioned "post reaction prediction" is not transmitted and is also excluded from the display targets on the information provision screen 53.

[0096] In S39, the CPU 21 acquires the number of "Likes" and the number of retweets of the retweets that have been made so far for the posts made in the past by the account determined to be similar to the account information of the user making the information request, particularly at the information request point where the information is currently being requested. Incidentally, those pieces of information correspond to the "post reaction prediction" that predicts the degree of reaction that can be obtained from a third party if the user making the information request newly posts to the information provision point on the SNS.

[0097] Subsequently, in S40, the CPU 21 transmits the detailed information regarding the information provision point extracted in S35 and the "post reaction prediction" acquired in S39 to the communication terminal 5 that is the transmission source of the request signal received in S34. Thereafter, as described above, information regarding the information provision point is output on the communication terminal 5 that has received the information (FIG. 13).

[0098] As described in detail above, in the information providing system 1, the information providing server 3, and the communication terminal 5 according to the present embodiment, a posted text posted on a network is acquired together with location information specifying a location associated with the posted text and poster information regarding the poster who posted the posted text (S2). By analyzing the acquired posted text, the posted emotion, which is the emotion of the poster who posted the posted text, is predicted (S3). At the same time, using at least one of the regional characteristics of the region where the location associated with the posted text is located and the poster information, weighting is performed for each posted text on the prediction result of the posted emotion (S6, S8, S9). The predicted posted emotions are classified and aggregated for each location associated with the posted text that is the analysis source, and the posted emotion for each location is specified with reference to the weighting (S9, S10). Therefore, when specifying the posted emotion, which is the emotion of the poster who posted the posted text for each location, by considering the regional characteristics of the region where the location for which the posted emotion is predicted is located, or the poster information of the poster who posted the posted text, it is possible to more reliably specify the posted emotion. Also, the specified posted emotion for the specified location is displayed on the screen (S29). Further, when displaying the posted emotion, at least one of the first information indicating the regional characteristics of the region where the specified location is located and the second information indicating the poster information of the poster who posted the posted text associated with the specified location is also displayed. Therefore, in addition to the posted emotion, it is possible to guide the regional characteristics and poster information that affect the analysis of the posted emotion. In particular, it is possible to guide the user in more detail about what points were considered in the analysis of the posted emotion. Also, regarding the regional characteristics of the region where the specified location is located, the comparison result of the weighting set according to the regional characteristics with other locations is displayed. Regarding the poster information of the poster who posted the posted text associated with the specified location, the comparison result of the weighting set according to the poster information with other locations is displayed. Therefore, the user can visually and easily grasp the regional characteristics and poster information of the location in a guiding manner. In particular, by making a relative evaluation, when comparing a plurality of locations, not only the posted emotions can be compared, but also the regional characteristics and poster information that affect the analysis of the posted emotion can be compared simultaneously. Also, when specifying the posted sentiment for each location, the predicted posted sentiment for each post is classified and aggregated for each location and each type of posted sentiment associated with the post serving as the analysis source, and by referring to the weighting of the post serving as the analysis source of the posted sentiment with respect to the aggregation result for each location and each type of posted sentiment, an evaluation score indicating the reliability of the prediction result by the sentiment prediction means for each location and each type of posted sentiment is calculated (S9), and the type of posted sentiment with the highest evaluation score for each location is specified as the posted sentiment for that location. Therefore, by considering the regional characteristics of the location where the posted sentiment is to be predicted or the information of the poster who posted the post, a more reliable specification of the posted sentiment becomes possible.

[0099] Note that the present invention is not limited to the above-described embodiment, and it goes without saying that various improvements and modifications can be made without departing from the gist of the present invention. For example, in the present embodiment, it is specified whether the posted sentiment at the information-providing location leans more towards positive sentiment (positive emotion) or negative sentiment (negative emotion), or is neutral (neither). However, the emotions can be classified in more detail. For example, it may be specified which of joy, trust, fear, surprise, sadness, disgust, anger, or expectation the posted sentiment is. Also, the types of "emotion categories" specified by the emotion analysis in S3 may not be classified into three types of 'Positive', 'Neutral', and 'Negative', but may be classified into more detailed categories such as joy, trust, fear, surprise, sadness, disgust, anger, expectation, etc.

[0100] Also, in the present embodiment, when specifying the posted sentiment at the information-providing location, weighting is performed on the prediction result of the posted sentiment for each post using both the regional characteristics of the region where the location associated with the post is located and the poster information (S6, S8, S9). However, weighting may be performed using only the regional characteristics or only the poster information. That is, the processes of S5 and S6 in the emotion analysis processing program (Figure 6) may be omitted, or the processes of S7 and S8 may be omitted.

[0101] Also, when performing weighting using only regional characteristics, the calculation of the contributor level in S12 is also omitted, and the display of the contributor level on the information provision screen 53 (Fig. 13) is excluded. Similarly, when performing weighting using only contributor information, the calculation of the regionality level in S11 is also omitted, and the display of the regionality level on the information provision screen 53 (Fig. 13) is excluded.

[0102] In addition, in this embodiment, an example in which the communication terminal 5 is applied to a smartphone has been described. However, it is also possible to apply it to other types of communication terminals as long as they have a function of outputting information regarding the information provision location. For example, it can be applied to a mobile phone, a tablet terminal, a personal computer, a navigation device which is an in-vehicle device, etc. Further, when applying it to devices other than the navigation device, it can also be implemented in situations where the user moves other than by car, for example, in a situation where the user moves on foot.

[0103] In addition, in this embodiment, the information provision server 3 is configured to perform the sentiment analysis processing program (Fig. 6), but a part of the processing may be executed by the communication terminal 5.

Explanation of Reference Numerals

[0104] 1... Information provision system (contribution sentiment prediction system), 2... Information provision center, 3... Information provision server, 4... User, 5... Communication terminal, 6... Communication network, 7... Distribution information DB, 8... SNS server, 9... Storage DB, 11... Server control unit, 13... Contribution text information DB, 36... Display, 41... Communication terminal control unit, 51... Map image, 52... Icon, 53... Information provision screen

Claims

1. A post text information acquisition means for acquiring a post text posted on a network together with location information identifying a location associated with the post text and poster information regarding the poster who posted the post text; An emotion prediction means for predicting a posting emotion, which is the emotion of the poster who posted the post text, by analyzing the post text acquired by the post text information acquisition means; A weighting means for weighting the prediction result by the emotion prediction means for each post text using at least one of the regional characteristics of the region where the location associated with the post text is located and the poster information; A posting emotion prediction system having a location emotion specifying means for classifying and aggregating the posting emotions predicted by the emotion prediction means for each location associated with the post text serving as an analysis source, and specifying the posting emotions for each location with reference to the weighting.

2. A posting emotion display means for displaying, on a screen, the posting emotion specified by the location emotion specifying means for a specified location; The posting emotion display means also displays, together with the posting emotion specified by the location emotion specifying means, at least one of first information indicating the regional characteristics of the region where the specified location is located and second information indicating the poster information of the poster who posted the post text associated with the specified location. The posting emotion prediction system according to claim 1.

3. The posting emotion display means displays, as the first information, a comparison result of the weighting set by the weighting means for the regional characteristics of the region where the specified location is located compared with other locations; displays, as the second information, a comparison result of the weighting set by the weighting means for the poster information of the poster who posted the post text associated with the specified location compared with other locations. The posting emotion prediction system according to claim 2.

4. The emotion prediction means specifies, for each post text, to which of a plurality of types of emotions the posting emotion corresponds; The location emotion specifying means classifies and aggregates the posting emotions predicted by the emotion prediction means for each location associated with the post text serving as an analysis source and for each type of posting emotion; by referring to the weighting of the post text serving as an analysis source of the posting emotion for the result of the aggregation for each location and for each type of posting emotion, an evaluation point indicating the reliability of the prediction result by the emotion prediction means for each location and for each type of posting emotion is calculated. The posting emotion prediction system according to any one of claims 1 to 3, which specifies the type of posting emotion with the highest evaluation score for each location as the posting emotion of that location.

Images