Network rumor recognition system based on artificial intelligence

Abstract

The invention relates to the technical field of network rumor recognition, in particular to a network rumor recognition system based on artificial intelligence, comprising: a data acquisition module for acquiring a news text; the text analysis module is used for analyzing news text features according to preset keywords and the number of wrongly written characters of the news text; the user analysis module is used for analyzing the user behavior characteristics; the propagation analysis module is used for analyzing the propagation characteristics of the news text; the identification module is used for identifying the news text, analyzing the source credibility of the news text according to the source of the news text, and analyzing the time consistency of the news text according to the release time of the news text; and the storage module is used for storing the recognition result of the news text and outputting the recognition result to a user. According to the invention, the accuracy of network rumor recognition is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of network rumor identification, and in particular to a network rumor identification system based on artificial intelligence. Background Art

[0002] With the development of the Internet and social media, all kinds of information are spreading at a very fast speed, but it is mixed with a lot of false information and online rumors. The widespread spread of misleading information not only affects public opinion, but is also likely to have a negative impact on social stability and individual mental health. Therefore, it is particularly important to develop an efficient and accurate online rumor identification system.

[0003] Chinese patent publication number CN112231562A discloses a method or system for identifying online rumors, the method comprising: obtaining a text feature matrix based on multiple texts containing rumor information; constructing a propagation graph structure, the nodes in the graph structure are multiple texts, and the adjacency matrix in the graph structure is the forwarding and comment relationship of rumor information between multiple texts; constructing a graph convolutional neural network model; the input of the graph convolutional neural network model is the text feature matrix and the adjacency matrix, and the output of the graph convolutional neural network model is the rumor feature matrix; training the neural network model according to the rumor feature matrix to obtain a rumor recognition model; identifying online rumors according to the rumor recognition model. The present invention trains the graph convolutional neural network model according to the forwarding and comment relationship between multiple texts of rumors, and trains the neural network model according to the rumor feature matrix, effectively capturing the widespread and dispersed propagation characteristics of rumor information, and can effectively identify rumor information; it can be seen that when identifying online rumors, the scheme does not conduct a comprehensive analysis of text emotional expression, social network user behavior and data sources, and there is a problem of low accuracy in identifying online rumors. Summary of the invention

[0004] The purpose of the present invention is to provide an artificial intelligence-based network rumor identification system to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions: An artificial intelligence-based network rumor identification system, comprising: Data collection module, used to collect news texts; A text analysis module is used to analyze the features of news texts based on preset keywords and the number of typos in the news texts; A user analysis module is used to analyze user behavior characteristics based on the number of comments, likes, shares and replies of the news text publisher in the first monitoring period; A communication analysis module is used to analyze the communication speed of the news text according to the total number of shares of the news text in the second monitoring period, and to analyze the communication characteristics of the news text according to the communication speed of the news text and the number of people who communicated the news text in the second monitoring period; An identification module is used to identify the news text according to the analysis results of the characteristics of the news text, the analysis results of the user behavior characteristics and the analysis results of the dissemination characteristics of the news text, so as to obtain the recognition result of the news text, and is also used to adjust the recognition process of the news text according to the number of rumor texts disseminated by the news text publisher in the history and the release time of the news text; The storage module is used to store the recognition results of the news text and output them to the user.

[0006] Furthermore, the text analysis module includes a text analysis unit, which is used to match the preset keyword with the news text. If the preset keyword matches the news text successfully, the preset keyword is used as the rumor keyword of the news text, and the number of occurrences of the i-th rumor keyword in the news text is counted, which is recorded as fi; The text analysis unit is also used to segment the news text and set the sentiment intensity value of the jth word in the news text to Dj; The text analysis unit is also used to count the number of typos in the news text, which is recorded as B.

[0007] Furthermore, the text analysis module also includes a feature extraction unit, which calculates the text features of the news text based on the number of occurrences fi of each rumor keyword in the news text, the sentiment intensity value Dj of each word in the news text and the number of typos B in the news text to obtain the feature WT of the news text.

[0008] Furthermore, the user analysis module is used to analyze user behavior characteristics according to the number of comments Ct, the number of likes R, the number of shares L and the number of replies S of the news text publisher in the first monitoring period to obtain the user's behavior characteristics HT.

[0009] Furthermore, the propagation analysis module includes a speed analysis unit, which is used to analyze the propagation speed of the news text according to the total number of shares fx of the news text in the second monitoring period to obtain the propagation speed Ve of the news text.

[0010] Furthermore, the communication analysis module also includes a construction unit, which is used to construct a communicator coefficient according to the number of people who spread the news text in the second monitoring period, and the construction results of the communicator coefficient include P1, P2 and P3.

[0011] Furthermore, the communication analysis module also includes a communication analysis unit for analyzing the communication characteristics of the news text according to the communication speed Ve of the news text, the number of people zc who communicate the news text in the second monitoring period, and the construction result of the communicator coefficient to obtain the communication characteristics CT of the news text.

[0012] Furthermore, the recognition module includes a recognition unit, which is used to recognize the news text according to the analysis results of the characteristics of the news text, the analysis results of the user behavior characteristics and the analysis results of the dissemination characteristics of the news text, wherein: If γ1×WT+γ2×HT+γ3×CT≤u0, the recognition unit determines that the news text is a normal news text; If γ1×WT+γ2×HT+γ3×CT>u0, the recognition unit determines that the news text is a rumor risk news text; Among them, γ1 is the text weight, γ2 is the behavior weight, γ3 is the propagation weight, and u0 is the preset anomaly coefficient.

[0013] Furthermore, the identification module also includes a source analysis unit, which constructs a source anomaly coefficient of the news text according to the number ys of rumor texts historically disseminated by the news text publisher, and adjusts the identification process of the news text according to the source anomaly coefficient, and sets the adjusted preset anomaly coefficient to u1.

[0014] Furthermore, the identification also includes a consistency analysis unit, which analyzes the consistency parameter YZ of the news text according to the publication days t0 of the news text and the preset publication days t1, and compares the consistency parameter YZ of the news text with the preset consistency threshold yz0. If the consistency parameter of the news text does not meet the threshold, the preset adjustment ratio is set to η1.

[0015] The beneficial effects of the present invention are as follows: through multi-level feature analysis, including text features, user behavior, propagation features and source credibility, it is possible to accurately identify online rumors and improve the accuracy and efficiency of judgment. The introduction of user analysis and propagation analysis modules helps to better assess the risk of information dissemination and provide strong support for decision-making. Finally, the storage and feedback functions of the system ensure that users can obtain identification results in a timely manner, improving user experience and trust. In summary, the present invention provides an efficient and accurate solution for rumor identification, which helps to maintain a healthy and authentic network environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 Schematic diagram of the structure of the artificial intelligence-based online rumor identification system in this embodiment.

[0018] Figure 2 Schematic diagram of the structure of the text analysis module of this embodiment.

[0019] Figure 3 Schematic diagram of the structure of the propagation analysis module of this embodiment.

[0020] Figure 4 It is a structural diagram of the identification module of this embodiment. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0022] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0023] See also Figure 1 As shown, it is a schematic diagram of the structure of the network rumor identification system based on artificial intelligence in this embodiment, and the system includes: The data collection module is used to collect news texts. It is understandable that the present embodiment does not specifically limit the method for collecting news texts, and those skilled in the art can freely set it as long as the method for collecting news texts is satisfied, wherein the news texts can be collected from news websites and social media through crawler technology or third-party API interfaces.

[0024] Please continue reading Figure 1 As shown, the system also includes: A text analysis module is connected to the data collection module, and is used to analyze the features of the news text according to preset keywords and the number of typos in the news text.

[0025] Specifically, in this embodiment, there is no specific limitation on the setting of preset keywords, and technical personnel in this field can set them freely as long as the setting requirements of the preset keywords are met. Among them, the preset keywords can be set to "sudden, urgent, shocking, revelations, truth, secret, action, cover-up, decision-making insider, danger, alarm, threat, fraud, health warning" and the like.

[0026] See also Figure 2 As shown, the text analysis module includes: A text analysis unit, which is used to match the preset keyword with the news text. If the preset keyword matches the news text successfully, the preset keyword is used as the rumor keyword of the news text. If the preset keyword does not match the news text successfully, the preset keyword is not used as the rumor keyword of the news text, and the number of occurrences of the i-th rumor keyword in the news text is counted, which is recorded as fi; The text analysis unit is also used to segment the news text and set the sentiment intensity value of the jth word in the news text to Dj; The text analysis unit is also used to count the number of typos in the news text, which is recorded as B; by analyzing the preset keywords and the number of typos, the module can quickly identify possible rumor text features and promote preliminary screening. This method can not only capture keywords in a timely manner, but also perform automated evaluation based on the quality of the text, which effectively improves the efficiency of rumor identification.

[0027] Specifically, in this embodiment, no specific limitation is made on the number of occurrences of each rumor keyword in the news text, the way of word segmentation of the news text, the way of assigning sentiment intensity each time in the news text, and the way of obtaining the number of typos. Technical personnel in this field can set them freely, and only need to meet the setting requirements of the number of occurrences of each rumor keyword in the news text, the way of word segmentation of the news text, the way of assigning sentiment intensity each time in the news text, and the way of obtaining the number of typos. Among them, SnowNLP can be used to count word frequencies, the news text can be segmented by the Jieba word segmentation tool, the Harbin Institute of Technology sentiment dictionary can be used to assign sentiment to each word in the news text, and the number of typos in the news text can be identified by Hunspell; in this embodiment, no specific limitation is made on the matching method, and technical personnel in this field can set it freely, and only need to meet the matching requirements, among which matching can be performed based on character strings.

[0028] Please continue reading Figure 2 As shown, the text analysis module also includes: A feature extraction unit is connected to the text analysis unit. The feature extraction unit calculates the text feature WT of the news text according to the number of occurrences of each rumor keyword in the news text, the sentiment intensity value of each word in the news text, and the number of typos in the news text. Set: ; The text feature WT is calculated comprehensively based on multi-dimensional features such as keyword frequency, sentiment intensity and number of typos, which improves the system's judgment ability and accuracy of news texts and thus improves the accuracy of identifying online rumors. Among them, w1 is the keyword weight, w2 is the sentiment weight, w3 is the typo weight, w1+w2+w3=1, I is the number of rumor keywords in the news text, N is the total number of words in the news text, and NZ is the total number of words in the news text.

[0029] It can be understood that the present embodiment does not specifically limit the method for obtaining the total number of words (N) and the total number of characters (NZ) of the news text, and those skilled in the art can freely set it, and it is only necessary to meet the requirements that the total number of words (N) and the total number of characters (NZ) of the news text can usually be obtained by the string processing function in the programming language, wherein it can be obtained by the string processing function in the programming language.

[0030] Please continue reading Figure 1 As shown, the system also includes: A user analysis module is connected to the text analysis module, and is used to analyze user behavior characteristics according to the number of comments Ct, the number of likes R, the number of shares L, and the number of replies S of the news text publisher in the first monitoring period, so as to effectively evaluate the user behavior characteristics, wherein: The user behavior feature analysis module sets the user behavior feature as HT, and sets HT=α×Ct / T1+β×(R+L+S) / T1, where T1 is the duration of the first monitoring cycle, α is the comment weight, β is the interaction weight, and α+β=1; it can be understood that the present embodiment does not specifically limit the setting of the comment weight and the interaction weight, and those skilled in the art can set them freely, as long as the setting requirements of the comment weight and the interaction weight are met, wherein the optimal value of α is 0.4, and the optimal value of β is 0.6; by analyzing the interactive behavior (comments, likes, shares, etc.) of news publishers in the first monitoring cycle, the module can effectively evaluate the user behavior feature HT, reflecting the potential risk of rumor propagation, and the user behavior analysis integrates social interaction into the rumor identification process, thereby improving the practicality of the system.

[0031] It can be understood that in this implementation, there is no specific limitation on the method for obtaining the number of comments Ct, the number of likes R, the number of shares L, and the number of replies S of the news text publisher in the first monitoring period, and those skilled in the art can set it freely, and it is only necessary to meet the requirements for obtaining the number of comments Ct, the number of likes R, the number of shares L, and the number of replies S of the news text publisher in the first monitoring period, wherein the number of comments Ct, the number of likes R, the number of shares L, and the number of replies S of the news text publisher in the first monitoring period can be obtained through the API of social media or news websites; in this embodiment, there is no specific limitation on the setting of the first monitoring period, and those skilled in the art can set it freely, and it is only necessary to meet the setting requirements of the first monitoring period, wherein the 7 days before the news text publisher is published can be used as the first monitoring period.

[0032] Please continue reading Figure 1 As shown, the system also includes: A communication analysis module is connected to the user analysis module, and is used to analyze the communication characteristics of the news text according to the total number of shares and the number of people who communicate the news text in the second monitoring period.

[0033] See also Figure 3 As shown, the propagation analysis module includes: The speed analysis unit is used to analyze the propagation speed Ve of the news text according to the total number of shares fx of the news text in the second monitoring period, so as to timely identify the spread trend of the information. It is set as: Ve=fx / T2, where T2 is the duration of the second monitoring period; the propagation speed Ve is calculated by analyzing the relationship between the total number of shares of the news text in the specified monitoring period and time. A high propagation speed usually means that the content is followed and shared by a large number of users in a short period of time, which may indicate that the content is an emergency or highly concerned information. Through this analysis, the system can timely identify the spread trend of information and provide a basis for rumor identification.

[0034] Please continue reading Figure 3 As shown, the propagation analysis module also includes: A construction unit connected to the speed analysis unit, the construction unit is used to construct a communicator coefficient according to the number of people who spread the news text in the second monitoring period, so as to effectively distinguish the credibility of different communicators and reduce the risk of spreading false information; if cb(k)≤q1, the communication analysis unit sets the communicator coefficient of the kth communicator to P1; if q1<cb(k)≤q2, the communication analysis unit sets the communicator coefficient of the kth communicator to P2; if cb(k)>q2, the communication analysis unit sets the communicator coefficient of the kth communicator to P3; constructing the communicator coefficient based on the historical behavior statistics of the communicator can evaluate the trustworthiness of different communicators in the current communication chain according to their previous communication records, and further enhance the robustness and effectiveness of the system; Among them, cb(k) is the number of rumor texts historically disseminated by the kth disseminator of news text, q1 is the first preset number, q2 is the second preset number, P1 is the first preset coefficient, P2 is the second preset coefficient, P3 is the third preset coefficient, P1<P2<P3; it can be understood that in this embodiment, no specific limitation is made to the preset numbers and preset coefficients, and technical personnel in this field can set them freely as long as the setting requirements of the preset numbers and preset coefficients are met. Among them, the best value of q1 is 3, the best value of q2 is 5, the best value of P1 is 1, the best value of P2 is 1.2, and the best value of P3 is 1.5.

[0035] Specifically, in this embodiment, there is no specific limitation on the method for obtaining the total number of shares of the news text within the second monitoring period, the number of disseminators, and the number of rumor texts disseminated by the disseminator in history. Technical personnel in this field can set it freely, and only need to meet the requirements for obtaining the total number of shares of the news text within the second monitoring period, the number of disseminators, and the number of rumor texts disseminated by the disseminator in history, which can be obtained through the API of social media or news websites; in this embodiment, there is no specific limitation on the setting of the second monitoring period, and technical personnel in this field can set it freely, and only need to meet the setting requirements of the second monitoring period, wherein the second monitoring period can be set to the time period of 5 days after the news text is released.

[0036] Please continue reading Figure 3 As shown, the propagation analysis module also includes: A communication analysis unit is connected to the construction unit, and is used to analyze the communication characteristics CT of the news text according to the communication speed Ve of the news text, the number of people who spread the news text in the second monitoring period, and the construction result of the communicator coefficient, and set: ; Among them, VT is the preset propagation speed, CB is the preset propagation quantity threshold, and P(k) is the communicator coefficient of the kth communicator of the news text. By integrating the results of propagation speed analysis and communicator coefficient, an in-depth analysis of the propagation characteristics of the news text is conducted to help judge the influence of the news content and potential public opinion risks, thereby providing a scientific basis for further rumor identification.

[0037] It can be understood that the present embodiment does not specifically limit the setting of the preset propagation speed and the preset propagation number thresholds, and those skilled in the art can freely set them as long as the setting requirements of the preset propagation speed and the preset propagation number thresholds are met, among which the optimal value of VT is 200 times / day, and the optimal value of CB is 1000.

[0038] Please continue reading Figure 1 As shown, the system also includes: An identification module is connected to the communication analysis module, and is used to identify the news text according to the analysis results of the characteristics of the news text, the analysis results of the user behavior characteristics and the analysis results of the communication characteristics of the news text to obtain the recognition result of the news text, and is also used to adjust the recognition process of the news text according to the number of rumor texts historically disseminated by the news text publisher and the release time of the news text.

[0039] See also Figure 4 As shown, the identification module includes: The recognition unit is used to recognize the news text according to the analysis results of the characteristics of the news text, the analysis results of the user behavior characteristics and the analysis results of the dissemination characteristics of the news text, wherein: If γ1×WT+γ2×HT+γ3×CT≤u0, the recognition unit determines that the news text is a normal news text; If γ1×WT+γ2×HT+γ3×CT>u0, the recognition unit determines that the news text is a rumor risk news text; Among them, γ1 is the text weight, γ2 is the behavior weight, γ3 is the propagation weight, γ1+γ2+γ3=1, and u0 is the preset abnormality coefficient; by comprehensively analyzing the text features, user behavior features and propagation features of the news text, the final judgment of the news text is achieved to improve the accuracy of identifying online rumors.

[0040] It can be understood that, in this embodiment, there is no specific limitation on the setting of each weight and the preset abnormality coefficient, and those skilled in the art can set it freely as long as the setting requirements of each weight and the preset abnormality coefficient are met, among which the optimal value of γ1 is 0.4, the optimal value of γ2 is 0.3, the optimal value of γ3 is 0.3, and the optimal value of u0 is 0.46.

[0041] Please continue reading Figure 4 As shown, the identification module also includes: A source analysis unit is connected to the identification unit. The source analysis unit constructs a source anomaly coefficient of the news text according to the number of rumor texts historically spread by the news text publisher ys, and adjusts the identification process of the news text according to the source anomaly coefficient, wherein: If ys=0, the source analysis unit sets the source anomaly coefficient of the news text to 0; If ys>0, the source analysis unit sets the source anomaly coefficient of the news text to LY, setting LY=η×lg(ys+1), η is a preset adjustment ratio, 0<η<0.4; The source analysis unit sets the adjusted preset anomaly coefficient as u1, and sets u1=u0-LY; by analyzing the number of historical rumor texts spread by the publisher, the source anomaly coefficient is constructed, so that the system can perform risk assessment on the source of the news text to improve the accuracy of identifying online rumors.

[0042] Specifically, this embodiment does not impose any specific limitation on the method for obtaining the number of rumor texts that the news text publisher has historically spread. Technical personnel in this field can set it freely, and it only needs to meet the requirements for obtaining the number of rumor texts that the news text publisher has historically spread, which can be obtained through the API of social media or news websites.

[0043] It can be understood that the present embodiment does not specifically limit the setting of the preset adjustment ratio, and those skilled in the art can freely set it as long as the setting requirements of the preset adjustment ratio are met, wherein the optimal value of η is 0.3.

[0044] Please continue reading Figure 4 As shown, the identification also includes: The consistency analysis unit is connected to the source analysis unit. The consistency analysis unit analyzes the consistency parameter YZ of the news text according to the release date t0 of the news text and the preset release date t1, and sets: YZ=1-1 / (1+e t1-t0 ), e is the natural logarithm; The consistency analysis unit compares the consistency parameter YZ of the news text with the preset consistency threshold yz0, and adjusts the construction process of the source anomaly coefficient according to the comparison result, wherein: If YZ≤yz0, the consistency analysis unit determines that the consistency parameter of the news text meets the threshold value and does not make any adjustment; If YZ>yz0, the consistency analysis unit determines that the consistency parameter of the news text does not meet the threshold, and sets the preset adjustment ratio to η1, setting η1=η×{1+exp[3×(YZ-yz0) / (YZ+yz0)-3]}; evaluating the consistency parameter YZ of the news text based on the release time helps to determine whether the information is an online rumor, thereby providing an important basis for rumor identification, thereby improving the accuracy of online rumor identification.

[0045] Specifically, this embodiment does not specifically limit the method for obtaining the publication days of news texts, and those skilled in the art can freely set it, as long as the requirements for obtaining the publication days of news texts are met, which can be obtained through the API of social media or news websites.

[0046] It can be understood that the present embodiment does not specifically limit the setting of the preset consistency threshold and the preset number of release days, and those skilled in the art can freely set them as long as the setting requirements of the preset consistency threshold and the preset number of release days are met, among which the optimal value of t1 is 5 days, and the optimal value of yz0 is 0.5.

[0047] Please continue reading Figure 1 As shown, the system also includes: A storage module is connected to the recognition module, and is used to store the recognition result of the news text and output it to the user.

[0048] Specifically, the artificial intelligence-based online rumor identification system described in this embodiment is applied to rumor identification on social media and online platforms. By comprehensively analyzing multi-dimensional information such as text features, user behavior, dissemination characteristics, and information sources, it not only improves the accuracy and efficiency of rumor identification, but also helps to build a healthier and safer network environment.

[0049] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. All obvious changes or modifications derived from the technical solution of the present invention are still within the protection scope of the present invention.

Claims

1. An artificial intelligence-based network rumor identification system, characterized in that: include: Data collection module, used to collect news texts; A text analysis module is used to analyze the features of news texts based on preset keywords and the number of typos in the news texts; A user analysis module is used to analyze user behavior characteristics based on the number of comments, likes, shares and replies of the news text publisher in the first monitoring period; A communication analysis module is used to analyze the communication speed of the news text according to the total number of shares of the news text in the second monitoring period, and to analyze the communication characteristics of the news text according to the communication speed of the news text and the number of people who communicated the news text in the second monitoring period; An identification module is used to identify the news text according to the analysis results of the characteristics of the news text, the analysis results of the user behavior characteristics and the analysis results of the dissemination characteristics of the news text, so as to obtain the recognition result of the news text, and is also used to adjust the recognition process of the news text according to the number of rumor texts disseminated by the news text publisher in the history and the release time of the news text; The storage module is used to store the recognition results of the news text and output them to the user.

2. The artificial intelligence-based online rumor identification system according to claim 1 is characterized in that: The text analysis module includes a text analysis unit, which is used to match the preset keyword with the news text. If the preset keyword matches the news text successfully, the preset keyword is used as the rumor keyword of the news text, and the number of occurrences of the i-th rumor keyword in the news text is counted, which is recorded as fi; The text analysis unit is also used to segment the news text and set the sentiment intensity value of the jth word in the news text to Dj; The text analysis unit is also used to count the number of typos in the news text, which is recorded as B.

3. The artificial intelligence-based online rumor identification system according to claim 2 is characterized in that: The text analysis module also includes a feature extraction unit, which calculates the text features of the news text based on the number of occurrences fi of each rumor keyword in the news text, the sentiment intensity value Dj of each word in the news text and the number of typos B in the news text to obtain the feature WT of the news text.

4. The artificial intelligence-based online rumor identification system according to claim 3 is characterized in that: The user analysis module is used to analyze the user behavior characteristics according to the number of comments Ct, the number of likes R, the number of shares L and the number of replies S of the news text publisher in the first monitoring period to obtain the user behavior characteristics HT.

5. The artificial intelligence-based network rumor identification system according to claim 4 is characterized in that: The propagation analysis module includes a speed analysis unit, which is used to analyze the propagation speed of the news text according to the total number of shares fx of the news text in the second monitoring period to obtain the propagation speed Ve of the news text.

6. The artificial intelligence-based online rumor identification system according to claim 5 is characterized in that: The communication analysis module also includes a construction unit, which is used to construct a communicator coefficient according to the number of people who spread the news text in the second monitoring period, and the construction results of the communicator coefficient include P1, P2 and P3.

7. The artificial intelligence-based online rumor identification system according to claim 6 is characterized in that: The communication analysis module also includes a communication analysis unit for analyzing the communication characteristics of the news text according to the communication speed Ve of the news text, the number of people zc who communicate the news text in the second monitoring period, and the construction result of the communicator coefficient to obtain the communication characteristics CT of the news text.

8. The artificial intelligence-based online rumor identification system according to claim 7 is characterized in that: The recognition module includes a recognition unit, which is used to recognize the news text according to the analysis results of the characteristics of the news text, the analysis results of the user behavior characteristics and the analysis results of the dissemination characteristics of the news text, wherein: If γ1×WT+γ2×HT+γ3×CT≤u0, the recognition unit determines that the news text is a normal news text; If γ1×WT+γ2×HT+γ3×CT>u0, the recognition unit determines that the news text is a rumor risk news text; Among them, γ1 is the text weight, γ2 is the behavior weight, γ3 is the propagation weight, and u0 is the preset anomaly coefficient.

9. The artificial intelligence-based network rumor identification system according to claim 8 is characterized in that: The identification module also includes a source analysis unit, which constructs a source anomaly coefficient of the news text according to the number ys of rumor texts historically disseminated by the news text publisher, and adjusts the identification process of the news text according to the source anomaly coefficient, and sets the adjusted preset anomaly coefficient to u1.

10. The artificial intelligence-based network rumor identification system according to claim 9 is characterized in that: The identification also includes a consistency analysis unit, which analyzes the consistency parameter YZ of the news text according to the publication days t0 of the news text and the preset publication days t1, and compares the consistency parameter YZ of the news text with the preset consistency threshold yz0. If the consistency parameter of the news text does not meet the threshold, the preset adjustment ratio is set to η1.

Images