A news hotspot monitoring method and system based on social network analysis

Abstract

The present invention relates to the technical field of news hotspot monitoring, and provides a news hotspot monitoring method and system based on social network analysis, comprising: calculating the correlation between different news events, using the correlation between two news events as the weight of an edge, establishing a relationship network diagram, and calculating a metric for each news event to select hot news events, and obtaining effective hot news events by calculating the synergistic benefit weight results of the selected hot news events; sequentially removing the selected hot news events from the relationship network diagram according to the ranking of the synergistic benefit weight results to obtain a new relationship network diagram, and reselecting hot news events based on the new relationship network diagram to obtain differences from the first selected hot news events, and selecting the hot news event that causes the greatest difference as a key event. This helps to gain a deeper understanding of the connection and influence between hot news events and other news events in news reports.

Description

Technical Field

[0001] The present invention belongs to the technical field of news hotspot monitoring, and in particular relates to a news hotspot monitoring method and system based on social network analysis. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In news reporting, some hot topics become the focus of public discussion due to their significance. These events often possess high news value and social attention, thus attracting widespread attention and discussion. However, because existing methods for monitoring news hot topics primarily rely on manual selection, they are often influenced by the subjective minds of editors and reporters. Furthermore, when selecting hot topics, the media often favors sensational events while overlooking more important but less eye-catching ones, resulting in reports lacking accuracy and authenticity. Furthermore, when selecting hot topics, the media also overlooks long-term and structural issues, resulting in insufficient depth and breadth in reporting. Summary of the Invention

[0004] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a news hotspot monitoring method and system based on social network analysis, which adopts the means of social network analysis to help in-depth understanding of the connection and influence between hot news events and other news events in news reports, thereby better understanding the nature and social significance of news events.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A first aspect of the present invention provides a news hotspot monitoring method based on social network analysis, comprising:

[0007] Get several news texts and get the news event to which each news text belongs;

[0008] Calculate the correlation between different news events, establish a relationship network diagram with news events as nodes and the correlation between two news events as edge weights, and calculate the measurement indicators of each news event based on the relationship network diagram to select hot news events. Then, calculate the synergistic benefit weight results of the selected hot news events to obtain effective hot news events;

[0009] According to the ranking of the synergistic benefit weight results, the selected hot news events are removed in turn in the relationship network diagram to obtain a new relationship network diagram, and based on the new relationship network diagram, the hot news events are reselected to obtain the differences with the hot news events selected for the first time, and the hot news event that causes the greatest difference is taken as the key event.

[0010] Furthermore, it also includes: using measurement indicators as dependent variables and the number of external news events as independent variables to demonstrate the impact of external news events on each news event.

[0011] Furthermore, the Pearson correlation coefficient is used to measure the correlation between different news events.

[0012] Further, the metric includes weighted degree centrality;

[0013] The weighted degree centrality is the sum of the edge weights between a node and other nodes in the relationship network graph.

[0014] Further, the metric includes weighted closeness centrality;

[0015] The weighted closeness centrality is the reciprocal of the sum of weighted distances between a node and other nodes in the relationship network graph.

[0016] Further, the metric includes weighted betweenness centrality;

[0017] The weighted betweenness centrality is the sum of the number of times a node appears on the weighted shortest path between pairs of nodes in the relationship network graph.

[0018] A second aspect of the present invention provides a news hotspot monitoring system based on social network analysis, comprising:

[0019] The data acquisition module is configured to: acquire a number of news texts and obtain the news event to which each news text belongs;

[0020] The first selection module is configured to calculate the correlation between different news events, establish a relationship network diagram with the news events as nodes and the correlation between the two news events as the weight of the edge, and calculate the measurement index of each news event based on the relationship network diagram to select hot news events, and obtain effective hot news events by calculating the synergy benefit weight results of the selected hot news events;

[0021] The second selection module is configured to: remove the selected hot news events in the relationship network diagram in sequence according to the ranking of the synergistic benefit weight results to obtain a new relationship network diagram, and reselect hot news events based on the new relationship network diagram to obtain the difference from the hot news events selected for the first time, and use the hot news event that causes the greatest difference as the key event.

[0022] Furthermore, it also includes a display module, which is configured to: use the measurement index as the dependent variable and the number of external news events as the independent variable to display the impact of external news events on each news event.

[0023] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for monitoring news hot spots based on social network analysis.

[0024] A fourth aspect of the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the news hotspot monitoring method based on social network analysis as described above are implemented.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] The present invention provides a news hotspot monitoring method based on social network analysis, which uses social network analysis to help gain a deeper understanding of the connection and influence between hot events in news reports and other events, thereby better understanding the essence and social significance of the events.

[0027] The present invention provides a news hotspot monitoring method based on social network analysis. By analyzing the impact of other external events on the selection of hot events, the changing trend of the hot event relationship network diagram as external events change is determined, providing the public with more comprehensive and in-depth news reports. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0029] Figure 1 This is a flowchart of a news hotspot monitoring method based on social network analysis according to the first embodiment of the present invention;

[0030] Figure 2 This is a news event relationship network diagram according to the first embodiment of the present invention;

[0031] Figure 3 This is the news event relationship network diagram after removing target 1 in Example 1 of the present invention.

[0032] Figure 4 This is the news event relationship network diagram after removing target 3 in Example 1 of the present invention.

[0033] Figure 5 This is the news event relationship network diagram after removing target 4 in Example 1 of the present invention.

[0034] Figure 6 This is the news event relationship network diagram after removing target 6 in Example 1 of the present invention.

[0035] Figure 7 This is the news event relationship network diagram after removing target 11 in Example 1 of the present invention.

[0036] Figure 8 This is the news event relationship network diagram after removing target 16 in Example 1 of the present invention.

[0037] Figure 9 This is a generalized additive model diagram of the weighted degree centrality of target 13 in Example 1 of the present invention.

[0038] Figure 10 This is a generalized additive model diagram of the weighted closeness centrality of target 13 in Example 1 of the present invention.

[0039] Figure 11 This is a generalized additive model diagram of the weighted betweenness centrality of target 13 in Example 1 of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0041] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0042] Example 1

[0043] This embodiment provides a news hotspot monitoring method based on social network analysis.

[0044] This embodiment provides a news hotspot monitoring method based on social network analysis, which aims to address the problems existing in traditional news hotspot monitoring methods. In terms of news hotspot monitoring, traditional manual selection methods are subjective and lack sufficient objectivity and accuracy. However, methods based on social network analysis can select representative and popular hotspot events by calculating and analyzing the importance of news events. Therefore, the method of the present invention can more objectively and comprehensively select news hotspot events, improve the accuracy and authenticity of news reports, and provide more valuable news information to the public.

[0045] The method for monitoring news hotspots based on social network analysis provided in this embodiment is particularly suitable for selecting hot news events in the field of sustainable development. This is because sustainable development covers a wide range of areas and issues, such as climate change, environmental protection, economic development, and social justice, and the impact of these issues is long-term and global. Therefore, selecting hot news items (topics or goals) with sustainable significance is of great significance for promoting sustainable development and raising public awareness of sustainable development issues.

[0046] This embodiment provides a news hotspot monitoring method based on social network analysis, such as Figure 1 As shown, the following steps are included:

[0047] Step 1: Obtain news texts from multiple sources within several consecutive time periods, classify them, and obtain the news events to which each news text belongs.

[0048] Among them, news texts can be collected from media platforms such as Weibo and Toutiao.

[0049] By preprocessing and classifying the news text, the category of the obtained news text needs to be attributed to the target news event.

[0050] The target news events can be 17 sustainable development goals, such as climate change, environmental protection, economic development, and social justice. It is necessary to determine whether the news text belongs to one or more of the 17 sustainable development goals.

[0051] Step 2: For each source, use the Pearson correlation coefficient to measure the interaction relationship (correlation degree) between news events.

[0052] The formula for calculating the Pearson correlation coefficient between event X and event Y is as follows:

[0053]

[0054] Among them, X i is the number of news texts belonging to event X in the i-th time period, Y i is the number of news texts belonging to news event Y in the i-th time period, is the number of news texts belonging to news event X in several consecutive time periods / number of time periods, It is the number of news texts belonging to news event Y in several consecutive time periods / number of time periods.

[0055] Step 3: Construct a relationship network: By calculating the Pearson correlation coefficient between news events, establish the interaction relationship between news events and construct a relationship network diagram.

[0056] In the relationship network diagram, each node represents a news event, and an edge represents the connectivity between two news events in a source. The weight of the edge is the degree of correlation between the two news events (Pearson correlation coefficient).

[0057] Based on the calculation results of the Pearson correlation coefficient, the present invention establishes a relationship network diagram containing 17 news events, such as Figure 2 shown.

[0058] Step 3: Select Hot Events: Using social network analysis, calculate the weighted degree centrality, weighted closeness centrality, and weighted betweenness centrality of each news event as metrics for selecting hot news events. Specifically, select the news events with the highest sum of weighted degree centrality, weighted closeness centrality, and weighted betweenness centrality as hot news events.

[0059] Given that social network analysis uses numerous metrics to measure network properties, this paper uses three of the most representative metrics as metrics for hotspot events: degree centrality, closeness centrality, and betweenness centrality. These metrics serve as metrics for selecting hotspot events and also as metrics for measuring relationship network graphs. Higher metrics indicate a higher likelihood of selection as a hotspot event. This paper uses social network analysis to calculate weighted degree centrality, weighted closeness centrality, and weighted betweenness centrality among sustainable development goals as metrics for selecting priorities, with higher calculated values ​​given priority.

[0060] (1) Degree centrality refers to the number of links between a node and other nodes in the network. It can measure the importance of a node in the network.

[0061] Weighted degree centrality is a weighted measure of the number of connections a node has in the network. Specifically, for node i, the weighted matrix degree centrality is the sum of the edge weights between it and all other nodes (all directly connected nodes), and the calculation formula is as follows:

[0062]

[0063] Among them, ω ij represents the weight of the edge between node i and node j (without intermediate nodes), and n is the number of news events.

[0064] (2) Weighted closeness centrality is a weighted measure of a node’s ability to be close to other nodes in the network. For node i, the weighted matrix closeness centrality is defined as the inverse of the sum of its weighted distances to all other nodes, and is calculated as follows:

[0065]

[0066] Among them, d ij represents the shortest path length (i.e., distance) between node i and node j, ω ij Represents the weight of the edge between node i and node j. Specifically, the shortest path length between node i and node j is the minimum number of intermediate nodes that need to be passed between the two nodes plus 1, such as Figure 3As shown, there is no direct edge between G2 and G13, and an intermediate node G4 is required. Then the shortest path length between G2 and G13 is 2, and the weight of the edge between G2 and G13 is the weight of the edge from G2 to G4 plus the weight of the edge from G13 to G4.

[0067] (3) Weighted betweenness centrality is a weighted measure of the degree of intermediary between a node and other nodes in the network. For node i, the weighted matrix betweenness centrality is defined as the sum of the number of times it appears on the weighted shortest paths between all pairs of nodes in the network, and is calculated as follows:

[0068]

[0069] Among them, σ st is the number of weighted shortest paths between node s and node t, σ st (i) is the number of times node i appears on the weighted shortest path between node s and node t. Figure 3 As shown, there is no direct edge between G2 and G13, and an intermediate node G4 is required. There are several edges from G2 to G4 and from G13 to G4. An edge from G2 to G4 and an edge from G13 to G4 are regarded as a path, and the path with the smallest sum of edge weights is regarded as the weighted shortest path.

[0070] Step 4. Confirm the importance of the event: Introduce the correlation coefficient to perform weighted calculation on the importance of the hot events to complete the synergistic benefit analysis, verify the importance of the event, and exclude events that do not meet the requirements (hot news events whose synergistic benefit weight results are less than the threshold), obtain valid hot news events, and display them.

[0071] The synergistic benefit analysis method is used to perform weighted calculation on the correlation coefficient (see Formula 1). The calculation formula is as follows:

[0072]

[0073] Among them, W i is the calculated synergistic benefit weight of the i-th hot news event, p i is the ratio of the number of positive / negative benefit news events connected to the news event to the total number of benefit news events, ω jThe correlation coefficient is the weight corresponding to the jth news event and the ith news event. For example, to calculate the synergistic effect weight of news event 1: of the 16 news events other than news event 1, 13 of them have positive effects, accounting for 81.25% of the total news events; 3 of them have negative effects, accounting for 18.75% of the total news events. Based on the positive or negative correlation coefficient of the i-th news event, the synergistic effect weight of the i-th news event with news event 1 is calculated. Finally, the weighted sum of all 16 news events is calculated according to the above calculation.

[0074] As can be seen from the above formula, this method uses 17 sustainable news events as a basis, selects related hot events from the news events, and ranks the calculated weighted results through synergy analysis. During the weight ranking process, the weighted results are used to quantitatively evaluate the contribution of each news event to the hot events, thereby verifying the importance and effectiveness of the hot events selected in step 3.

[0075] Taking 17 news events as an example, the present invention calculates the degree centrality, closeness centrality and betweenness centrality of each news event through step 3, and then compares them with the synergistic benefit analysis results of step 4. It is found that the three centrality calculation results of news events 1, 3, 4, 6, 11, and 16 are ranked high and their effectiveness is proved after synergistic benefit analysis. Therefore, the present invention selects news events 1, 3, 4, 6, 11, and 16 as hot events.

[0076] Step 5. Explore the dynamic changes of events: According to the ranking of the synergistic benefit weight results, remove the hot events selected in step 4 one by one, calculate the measurement indicators of the remaining news events again, and generate a new relationship network diagram. Based on the new relationship network diagram, reselect the hot news events to obtain the differences with the hot news events selected for the first time. The hot news event that causes the greatest difference (causing the largest number of difference set elements between the set of reselected hot news events and the set of hot news events selected for the first time) is selected as the key event and displayed.

[0077] Remove the hot events selected in step 4 (for example, remove target 1) in sequence, recalculate the metrics of the remaining news events based on the social network analysis method, and select news events with higher metrics as hot events.

[0078] Based on new news events, reconstruct the relationship network diagram of news events; analyze the new relationship network diagram (such as Figure 3 、 Figure 4 、 Figure 5 、 Figure 6 、 Figure 7 、 Figure 8 (as shown), compare the differences between new hot events and previous hot events, and explore their dynamic changes.

[0079] Step 6: Explore the impact of external news events on the relationship network: Construct a generalized additive model of external events and 17 news events to explore the impact of external news events on the relationship network.

[0080] The present invention constructs 17 generalized additive models to explore the impact of external news events on the relationship network. Among them, external news events include global technological progress news events, global health news events, climate change news events, global peace news events, and world governance news events. In order to explore the impact of external news events on the event relationship network, the present invention takes the generalized additive model constructed by event 13 as an example, and uses the three centralities (see formulas (2), (3), and (4)) that measure the relationship network structure as dependent variables, and the number of external news events as the independent variable to obtain the impact of external news events on the relationship network. As the number of external news events increases, the target centrality also changes (such as Figure 9 、 Figure 10 、 Figure 11 This will help observe the impact of external events on network structure and provide data for formulating more meaningful news release strategies.

[0081] This embodiment provides a news hotspot monitoring method based on social network analysis. This method utilizes social network analysis to provide a deeper understanding of the connections and impacts between hot events (topics) and other events in news reports, thereby better understanding the nature and social significance of the events. Furthermore, by analyzing the impact of other external news events on the selection of hot events, the present invention can determine the changing trends of the hot event relationship network diagram as external news events change, thereby providing the public with more comprehensive and in-depth news reports.

[0082] The present embodiment provides a news hotspot monitoring method based on social network analysis, which has the advantages of objectivity, accuracy, and comprehensiveness, and is also of great significance in the field of sustainable development.

[0083] This embodiment provides a news hotspot monitoring method based on social network analysis, which takes sustainable development news events as research objects and aims to explore how to select hot news items with sustainable significance.

[0084] This embodiment provides a news hotspot monitoring method based on social network analysis, which deeply analyzes the role played by each news hotspot event in the natural development of other events. At the same time, with the help of social network analysis, hotspot events are selected from the news, in order to provide valuable reference for the public to accept news information. This method can avoid the influence of subjective consciousness, reduce bias and misleading in media reports, and ensure the accuracy and authenticity of reports. In addition, this method can also pay attention to the impact of other news events on the event relationship network, so that the report has sufficient comprehensiveness. Therefore, the method of the present invention is a news hotspot event selection method with wide application value.

[0085] Example 2

[0086] This embodiment provides a news hotspot monitoring system based on social network analysis, which specifically includes:

[0087] The data acquisition module is configured to: acquire a number of news texts and obtain the news event to which each news text belongs;

[0088] The first selection module is configured to calculate the correlation between different news events, establish a relationship network diagram with the news events as nodes and the correlation between the two news events as the weight of the edge, and calculate the measurement index of each news event based on the relationship network diagram to select hot news events, and obtain effective hot news events by calculating the synergy benefit weight results of the selected hot news events;

[0089] The second selection module is configured to: remove the selected hot news events in the relationship network diagram in sequence according to the ranking of the synergistic benefit weight results to obtain a new relationship network diagram, and reselect hot news events based on the new relationship network diagram to obtain the difference from the hot news events selected for the first time, and use the hot news event that causes the greatest difference as the key event.

[0090] The display module is configured to: use the measurement indicator as the dependent variable and the number of external news events as the independent variable to display the impact of external news events on each news event.

[0091] It should be noted here that the various modules in this embodiment correspond one-to-one to the various steps in Example 1, and the specific implementation processes are the same, which will not be repeated here.

[0092] Example 3

[0093] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the news hotspot monitoring method based on social network analysis as described in the first embodiment above are implemented.

[0094] Example 4

[0095] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the method for monitoring news hot spots based on social network analysis as described in the first embodiment above are implemented.

[0096] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0097] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0100] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0101] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A news hotspot monitoring method based on social network analysis, characterized in that: include: Get several news texts and get the news event to which each news text belongs; Calculate the correlation between different news events, establish a relationship network diagram with news events as nodes and the correlation between two news events as edge weights, and calculate the measurement indicators of each news event based on the relationship network diagram to select hot news events. Then, calculate the synergistic benefit weight results of the selected hot news events to obtain effective hot news events; According to the ranking of the synergistic benefit weight results, the selected hot news events are sequentially removed from the relationship network diagram to obtain a new relationship network diagram, and based on the new relationship network diagram, the hot news events are reselected to obtain the difference from the hot news events selected for the first time, and the hot news event that causes the greatest difference is selected as the key event; The measurement indicators include weighted degree centrality, weighted closeness centrality and weighted betweenness centrality; the weighted degree centrality is the sum of the edge weights between a node and other nodes in the relational network graph; the weighted closeness centrality is the inverse of the sum of the weighted distances between a node and other nodes in the relational network graph; the weighted betweenness centrality is the sum of the number of times a node appears on the weighted shortest path between pairs of nodes in the relational network graph.

2. The method for monitoring news hot spots based on social network analysis according to claim 1, wherein: Also includes: The measurement index is used as the dependent variable, and the number of external news events is used as the independent variable to show the impact of external news events on each news event.

3. The method for monitoring news hot spots based on social network analysis according to claim 1, wherein: The Pearson correlation coefficient is used to measure the correlation between different news events.

4. A news hotspot monitoring system based on social network analysis, characterized in that: include: The data acquisition module is configured to: acquire a number of news texts and obtain the news event to which each news text belongs; The first selection module is configured to calculate the correlation between different news events, establish a relationship network diagram with the news events as nodes and the correlation between the two news events as the weight of the edge, and calculate the measurement index of each news event based on the relationship network diagram to select hot news events, and obtain effective hot news events by calculating the synergy benefit weight results of the selected hot news events; The second selection module is configured to: sequentially remove the selected hot news events from the relationship network diagram according to the ranking of the synergistic benefit weight results to obtain a new relationship network diagram; and reselect hot news events based on the new relationship network diagram to obtain differences from the hot news events selected for the first time, and select the hot news event that causes the greatest difference as the key event; The measurement indicators include weighted degree centrality, weighted closeness centrality and weighted betweenness centrality; the weighted degree centrality is the sum of the edge weights between a node and other nodes in the relational network graph; the weighted closeness centrality is the inverse of the sum of the weighted distances between a node and other nodes in the relational network graph; the weighted betweenness centrality is the sum of the number of times a node appears on the weighted shortest path between pairs of nodes in the relational network graph.

5. A news hotspot monitoring system based on social network analysis as claimed in claim 4, characterized in that: It also includes a display module, which is configured to: use the measurement indicator as the dependent variable and the number of external news events as the independent variable to display the impact of external news events on each news event.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the news hotspot monitoring method based on social network analysis as described in any one of claims 1 to 3 are implemented.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the news hotspot monitoring method based on social network analysis as described in any one of claims 1 to 3 are implemented.

Images