Social network emotion evolution model fusing user influence and activeness

Abstract

The invention discloses a social network emotion evolution model fusing user influence and activeness, and relates to the technical field of social network analysis. In order to solve the technical defects of inaccurate simulation and inflexible prediction in the existing network sentiment analysis and sentiment evolution analysis process in the prior art, the invention provides a social network sentiment evolution model fusing user influence and activeness. The model analysis method comprises the steps of collecting a text emotion of a target user; collecting the user influence of each user; collecting the activeness of the target social network at the t moment; the forgetting probability of each user at the t moment is collected as the emotional evolution ability; an emotional evolution dynamics model of the social network; optimizing the evolution probability of the information spreading model according to the text emotion; and analyzing the evolution process of the emotional evolution dynamics model of the social network according to the optimized information propagation model. The method is suitable for social network analysis work.

Description

Technical Field

[0001] The present invention relates to the technical field of social network analysis, and in particular to a social network sentiment evolution model integrating user influence and activity. Background Art

[0002] In the field of social network analysis technology, research on sentiment analysis and sentiment evolution in social networks has become a hot topic in recent years. Social platforms such as Facebook, Twitter, and Sina Weibo and WeChat in China have become an indispensable part of the daily lives of hundreds of millions of users. Users post various emotional content on social platforms, and the evolution of these contents has an increasingly significant impact on social opinion and public sentiment. Existing research mainly focuses on sentiment analysis based on sentiment dictionaries, the application of information dissemination models, and the evaluation of the influence of user behavior.

[0003] Current sentiment analysis research generally uses text-based sentiment dictionary methods to classify the sentiment of texts posted by users. Such methods can help determine the sentiment polarity of texts, such as using sentiment dictionaries such as BosonNLP and SentiWordNet. On the other hand, sentiment propagation and evolution models are mostly based on the SIR (Susceptible-Infectious-Recovered) model, which is used to simulate the spread of sentiment in social networks. However, existing technologies usually simply equate the spread of user sentiment with the spread of epidemics, ignoring the differences between individual users in social networks.

[0004] For example, in some studies based on the SIR model, the user status is only divided into susceptible, infected, and immune, without taking into account the different influences between individuals. Influence is a key factor in social networks, and the influence of different users can significantly affect the breadth and speed of emotional transmission. At the same time, changes in social network activity also have an important impact on the emotional evolution process, but many existing studies have failed to fully quantify and utilize activity. In addition, the phenomenon of forgetting and gradual attenuation of individual emotions during the emotional transmission process, that is, the process of nodes gradually changing from positive or negative states to immune states, has not been fully reflected in existing models.

[0005] Therefore, there are mainly the following problems in the prior art:

[0006] 1. The emotion propagation model fails to effectively integrate the differences in user influence, resulting in the model's inaccurate simulation of the real emotion evolution.

[0007] 2. The impact of social network activity on emotional communication is not fully considered, making the model not flexible enough in predicting emotional evolution in dynamic social environments.

[0008] 3. The lack of modeling of the emotional forgetting process fails to reflect the natural attenuation mechanism in the evolution of emotions, which reduces the authenticity of the simulation results. Summary of the invention

[0009] In order to solve the technical defects existing in the prior art, that is, in the existing network sentiment analysis and sentiment evolution analysis process, the simulation of real sentiment evolution is not accurate enough, the prediction of sentiment evolution in a dynamic social environment is not flexible enough, and the authenticity of the simulation results cannot be guaranteed, the technical solution provided by the present invention is:

[0010] A social network sentiment evolution model that integrates user influence and activity. The model analysis method is:

[0011] Steps to collect text sentiment of target users;

[0012] Steps for collecting the user influence of each user in the target social network;

[0013] The step of collecting the activity of the target social network at time t;

[0014] Collect the forgetting probability of each user at time t in the target social network as a step for the emotional evolution ability;

[0015] Steps of the dynamics model of sentiment evolution in social networks;

[0016] The steps of collecting the preset information dissemination model;

[0017] A step of optimizing the evolution probability of the information propagation model according to the text sentiment;

[0018] The step of analyzing the evolution process of the sentiment evolution dynamics model of the social network according to the optimized information propagation model.

[0019] Further, a preferred implementation is provided, wherein the text emotion of the target user is specifically the text emotion of the target microblog user, and the acquisition method is:

[0020] The step of performing sentence and word segmentation processing on the microblog text to obtain a word segmentation set;

[0021] Traverse the sentences in the word segmentation set and detect sentiment words, degree adverbs and negative words;

[0022] Compare the dictionary to obtain the weight of each sentiment word, degree adverb and negation word;

[0023] The step of judging the sentiment tendency according to the weight.

[0024] Furthermore, a preferred implementation is provided, in which the user influence of each user is obtained according to the number of followers and fans of each user.

[0025] Furthermore, a preferred implementation is provided, in which the activity of the target social network at time t is obtained according to the number of active nodes, passive nodes and immune nodes in the target social network at time t.

[0026] Furthermore, a preferred implementation is provided, in which the forgetting probability of each user at time t is obtained according to the forgetting mechanism and the user influence mechanism.

[0027] Furthermore, a preferred implementation is provided, in which the information propagation model is obtained according to the user influence of each user, the activity of the target social network at time t, and the emotional evolution ability.

[0028] Based on the same inventive concept, the present invention also provides an analysis device for a social network sentiment evolution model integrating user influence and activity, comprising:

[0029] A module for collecting text sentiments of target users;

[0030] A module that collects the user influence of each user in the target social network;

[0031] A module for collecting the activity of the target social network at time t;

[0032] Collect the forgetting probability of each user at time t in the target social network as a module for emotion evolution ability;

[0033] Module for the dynamics model of sentiment evolution in social networks;

[0034] A module for collecting preset information propagation models;

[0035] A module for optimizing the evolution probability of the information propagation model according to the text sentiment;

[0036] A module for analyzing the evolution process of the sentiment evolution dynamics model of the social network according to the optimized information propagation model.

[0037] Based on the same inventive concept, the present invention also provides a computer storage medium for storing a computer program, and when the computer reads the computer program, the computer executes the described method.

[0038] Based on the same inventive concept, the present invention also provides a computer, including a processor and a storage medium. When the processor reads a computer program stored in the storage medium, the computer executes the method described.

[0039] Based on the same inventive concept, the present invention also provides a computer program product, which is a computer program. When the computer program is executed, the method described above is implemented.

[0040] Compared with the prior art, the technical solution provided by the present invention is beneficial in that:

[0041] By introducing a method to calculate user influence, the model can more accurately simulate the effect of individuals on the spread of emotions in social networks. Compared with existing models that only consider user status, this solution quantifies the influence of users based on the number of their fans and followers, thereby improving the accuracy of the path and scope of emotional spread, making the spread effect more consistent with the influence distribution in real social networks.

[0042] Combined with the calculation of social network activity, this scheme can simulate the dynamic process of emotion propagation more flexibly. In existing studies, activity is usually not fully considered, and this scheme improves the dynamic response ability to the emotion propagation rate and influence range by introducing the activity changes of different nodes in the social network. This approach enables the model to show higher adaptability and prediction accuracy when dealing with complex social network environments.

[0043] By introducing the node forgetting probability, this scheme successfully simulates the natural attenuation mechanism in the evolution of emotions, making the transition of node states closer to the emotional propagation process in real social networks. Compared with the single state transition in the traditional SIR model, this scheme simulates the gradual weakening of emotions in nodes through the forgetting probability, making the transformation process of positive and negative emotions smoother and more realistic, thereby effectively improving the rationality of the emotional evolution results.

[0044] Compared with the traditional SIR model, the SIR-IASF emotion evolution model of this solution adds comprehensive consideration of user influence, activity and forgetting mechanism, making the process of emotion propagation more complex and diverse. This improvement enables the model to more accurately reflect the law of emotion propagation in social networks, especially in complex situations where multiple emotions coexist and node states are constantly changing, and can better describe the evolution path and final state of emotions.

[0045] Suitable for use in social network analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a flow chart of a social network sentiment evolution model that integrates user influence and activity;

[0047] Figure 2 This is the probability change diagram of an infected node becoming an immune node. DETAILED DESCRIPTION

[0048] In order to make the advantages and benefits of the technical solution provided by the present invention more clearly reflected, the technical solution provided by the present invention is now further described in detail with reference to the accompanying drawings, specifically:

[0049] Implementation method 1: This implementation method provides a social network sentiment evolution model that integrates user influence and activity. The model analysis method is:

[0050] Steps to collect text sentiment of target users;

[0051] Steps for collecting the user influence of each user in the target social network;

[0052] The step of collecting the activity of the target social network at time t;

[0053] Collect the forgetting probability of each user at time t in the target social network as a step for the emotional evolution ability;

[0054] Steps of the dynamics model of sentiment evolution in social networks;

[0055] The steps of collecting the preset information dissemination model;

[0056] A step of optimizing the evolution probability of the information propagation model according to the text sentiment;

[0057] The step of analyzing the evolution process of the sentiment evolution dynamics model of the social network according to the optimized information propagation model.

[0058] Specifically, they include:

[0059] Step 1: Weibo text segmentation and sentiment extraction

[0060] First, the jieba Chinese word segmentation component is used to segment the microblog texts of social network users. By sentence segmentation, the text is split into a vocabulary set. Then, the text sentiment of microblog users is extracted using a text-based sentiment evolution analysis method, specifically detecting sentiment words, degree adverbs, and negative words, and calculating the sentiment polarity score and sentiment tendency of each microblog text based on the sentiment dictionary. The output of this step is the sentiment polarity score and sentiment tendency of each user's microblog text.

[0061] Step 2: Calculate user influence

[0062] Next, the influence of each user in the social network is calculated based on the influence model. When creating a social network, each social network user is first assigned an initial influence value, and then the user's actual influence is calculated based on the number of fans and followers of the user. In order to prevent the user's influence from being too large and affecting the experimental results, the influence is adjusted using a standardization method. The output of this step is the standardized influence value of each user.

[0063] Step 3: Calculation of social network activity

[0064] In this step, the activity of the social network at a certain moment is calculated based on the number of active nodes, passive nodes, and immune nodes in the social network at that moment. The activity of the social network reflects the activity of users in the network and is an important dynamic parameter for sentiment propagation. The output of this step is the social network activity value at a specific moment.

[0065] Step 4: Calculate the node forgetting probability

[0066] Based on the forgetting mechanism and the user influence mechanism, the forgetting probability of social network users at a specific moment is calculated. The forgetting probability reflects the natural decay process of the user's emotional evolution and is calculated based on the Ebbinghaus forgetting curve. The more influential the user, the slower the change rate of the forgetting probability, that is, the longer the user influences the surrounding nodes. The output of this step is the forgetting probability of each node at a specific moment.

[0067] Step 5: Emotional evolution probability calculation and dynamic model construction

[0068] Using user influence, social network activity and node forgetting probability, the probability of emotion evolution of social network users is calculated, and an emotion evolution dynamics model is constructed. The status of user nodes is divided into susceptible nodes, active nodes, passive nodes and immune nodes. The SIR-IASF emotion evolution analysis model is used to simulate the emotion propagation process until all user nodes become immune nodes. The output of this step is the change in the emotion status of the user nodes.

[0069] Step 6: Emotional Evolution Analysis

[0070] Finally, we traverse all nodes in the social network and calculate the emotional evolution of each node based on the sentiment analysis of the text and the aforementioned dynamic model. We update the emotional state of each node to determine whether its emotion has evolved. We repeat the above calculation process until all node states become immune nodes, and obtain the final results of the emotional evolution of social network users.

[0071] Implementation method 2: This implementation method further limits the social network sentiment evolution model that integrates user influence and activity provided in implementation method 1. The text sentiment of the target user is specifically the text sentiment of the target microblog user, and the acquisition method is:

[0072] The step of performing sentence and word segmentation processing on the microblog text to obtain a word segmentation set;

[0073] Traverse the sentences in the word segmentation set and detect sentiment words, degree adverbs and negative words;

[0074] Compare the dictionary to obtain the weight of each sentiment word, degree adverb and negation word;

[0075] The step of judging the sentiment tendency according to the weight.

[0076] Implementation method three: This implementation method further limits the social network sentiment evolution model that integrates user influence and activity provided in implementation method one, and obtains the user influence of each user according to the number of followers and fans of each user.

[0077] Implementation method 4: This implementation method is a further limitation of the social network sentiment evolution model that integrates user influence and activity provided in implementation method 1. The activity of the target social network at time t is obtained according to the number of active nodes, negative nodes and immune nodes in the target social network at time t.

[0078] Implementation method five: This implementation method further limits the social network sentiment evolution model that integrates user influence and activity provided in implementation method one. According to the forgetting mechanism and the user influence mechanism, the forgetting probability of each user at time t is obtained.

[0079] Implementation method six: This implementation method is a further limitation of the social network sentiment evolution model that integrates user influence and activity provided in implementation method one. The information propagation model is obtained based on the user influence of each user, the activity of the target social network at time t, and the sentiment evolution ability.

[0080] Embodiment 7: This embodiment provides an analysis device for a social network sentiment evolution model integrating user influence and activity, including:

[0081] A module for collecting text sentiments of target users;

[0082] A module that collects the user influence of each user in the target social network;

[0083] A module for collecting the activity of the target social network at time t;

[0084] Collect the forgetting probability of each user at time t in the target social network as a module for emotion evolution ability;

[0085] Module for the dynamics model of sentiment evolution in social networks;

[0086] A module for collecting preset information propagation models;

[0087] A module for optimizing the evolution probability of the information propagation model according to the text sentiment;

[0088] A module for analyzing the evolution process of the sentiment evolution dynamics model of the social network according to the optimized information propagation model.

[0089] Embodiment 8: This embodiment provides a computer storage medium for storing a computer program. When the computer reads the computer program, the computer executes the method provided in embodiment 1.

[0090] Embodiment 9: This embodiment provides a computer, including a processor and a storage medium. When the processor reads a computer program stored in the storage medium, the computer executes the method provided in embodiment 1.

[0091] Embodiment 10: This embodiment provides a computer program product, which is a computer program. When the computer program is executed, the method provided in embodiment 1 is implemented.

[0092] Implementation Method XI: Combination Figure 1-2 This embodiment is described in detail by using specific examples to further describe the technical solution provided above. Specifically:

[0093] Reference Figure 1 As shown, this embodiment proposes an embodiment of a social network sentiment evolution model that integrates user influence and activity, and the construction method includes the following steps:

[0094] Step 1: Use the Jieba Chinese word segmentation component to segment the microblog texts of social network users, and then use the text-based sentiment evolution analysis method to extract the text sentiment of microblog users;

[0095] Step 2: Based on the influence model, each user has different influence on the surrounding nodes. The user influence of each user in the same social network is calculated based on the number of followers and fans of the user's surrounding nodes;

[0096] Step 3: Using the number of active nodes, passive nodes, and immune nodes in the social network at a certain time t, calculate the social network activity popular(t) at time t;

[0097] Step 4: Based on the forgetting mechanism and user influence mechanism, calculate the forgetting probability of social network users at time t, that is, the ability to respond to emotional evolution;

[0098] Step 5: Use user influence, social network activity and node forgetting probability to obtain the emotion evolution probability of social network users, and obtain the emotion evolution dynamics model of social network.

[0099] Step 6: Use the SIR-IASF sentiment evolution analysis model to analyze the sentiment evolution process of users in the social network until all user nodes become immune nodes, and return the evolved social network user sentiment.

[0100] In step 1, the text-based sentiment evolution analysis method is used to extract the text sentiment of microblog users, specifically:

[0101] Step 1: Segment and segment the microblog text to obtain the collection Item i =[[Word 11 , Word 12 , …, Word 1n1 ],…,[Word k1 , Word k2 , …, Word knk ]], where i is the i-th Weibo user, n k is the number of word segments in each sentence, and k is the number of sentences in this microblog;

[0102] Step 1 and 2: traverse the sentence after word segmentation and detect sentiment words, degree adverbs, negative words, etc.;

[0103] Step 13: Compare the sentiment dictionary, degree adverb dictionary and negation dictionary to obtain the weight set {w1, w2, ..., w n}. If the negative word is before the sentiment word, its sentiment value should be multiplied by the sentiment coefficient -1 to get the new sentiment value;

[0104] Step 14: Compare the sentiment dictionary to get the score of each sentiment word {e1, e2, ..., e n}, based on the calculated sentiment score of each microblog text, the specific calculation method is:

[0105]

[0106] Step 15: If the sentiment score Ei is greater than 0, the sentiment tendency is positive; if the sentiment score Ei is less than 0, the sentiment score is negative. The sentiment tendency and sentiment score are returned.

[0107] In step 2, the influence of each user in the social network is calculated. When creating a social network, each social network user is first given an initial value of influence (i) of 1, and then the real influence of each user is calculated. The specific calculation method is:

[0108]

[0109] Where d is a damping coefficient, and through experiments, it is found that the best effect is achieved when d is 0.8. Influence(i) is the influence of user i, Follower(i) is the number of fans of user i, and Followee(i) is the number of followers of user i. In order to avoid the calculated user influence from being too large and affecting the experimental results, it needs to be standardized. The standardized calculation method is:

[0110]

[0111] In a social network, the number of fans of a node is the in-degree of the node, and the number of followers is the out-degree of the node.

[0112] In step 3, the specific calculation method of social network activity at time t is:

[0113] people(t)=P(t)+N(t)+R(t)

[0114]

[0115] Among them, popular(t) represents the activity of the social network at time t, and people(t) represents the number of people who have been infected by a certain emotion at a certain moment.

[0116] In step 4, after being infected by a certain emotion, users in the social network gain the ability to evolve and spread this emotion, becoming positive nodes P or negative nodes N. However, as time goes by, their emotional evolution ability gradually weakens, that is, their ability to become immune nodes gradually increases. In order to make the model more close to the emotional evolution in the real world, the forgetting probability of the node is introduced. Referring to the Ebbinghaus forgetting curve, its calculation method is:

[0117]

[0118] Among them, γ i (t) is the positive node P or the negative node N, represented by node i, the probability of forgetting at time t, that is, the probability of becoming an immune node R and losing the ability to influence surrounding nodes, δ i Represents the rate of change of the probability of forgetting. The more fans a user has in a social network, the greater the user's influence, the longer it will take for him to affect the emotions of the surrounding nodes, and the rate of change of the probability of forgetting should be relatively slower, so δ i The calculation method is:

[0119]

[0120] Taking a node in a social network as an example, after it evolves from a susceptible node S to an active node P or a passive node N, its forgetting probability changes to the probability of becoming an immune node R as follows: Figure 2 shown.

[0121] Depend on Figure 2 It can be seen that when the susceptible node S just becomes an active node P or a passive node N, its ability to influence the emotions of the surrounding susceptible nodes S is 0, and as time goes by, it loses the ability to influence the surrounding nodes, that is, the probability of becoming an immune node R gradually increases, and after a certain period of time, it will definitely lose its influence ability, which is more consistent with the emotional evolution process in real life.

[0122] In step 5, the social network sentiment evolution analysis model SIR-IASF is constructed using methods based on the information propagation model SIR, user influence, social network activity, and node forgetting probability. Specifically:

[0123] Step 5.1: Divide the user node status into susceptible nodes S, active nodes P, passive nodes N, and immune nodes R. Susceptible nodes S are nodes that have not been infected by a certain emotion, but may be infected by the surrounding infected nodes at any time and evolve into positive or negative nodes. They also have certain emotional tendencies obtained through sentiment analysis of their microblog texts; active nodes P are usually infected, and they have the ability to infect the surrounding susceptible nodes S to the positive nodes P, so that they can become immune nodes R through forgetting probability; negative nodes N are infected, and they have the ability to infect the surrounding susceptible nodes S to the negative nodes N, and become immune nodes S through forgetting probability; immune nodes S are new nodes after the positive nodes P or negative nodes N lose their immunity, and no longer have the ability to infect the surrounding susceptible nodes; their evolutionary dynamics formula is:

[0124]

[0125] Among them, α1 is the probability that the susceptible node S is infected by the surrounding infected nodes P or N and evolves into an active node P, α2 is the probability that the susceptible node S is infected by the surrounding active nodes P or negative nodes N and evolves into a negative node N, β1 is the probability that the active node P loses the ability to evolve emotions and evolves into an immune node R, β2 is the probability that the negative node N loses the ability to evolve emotions and evolves into an immune node R, and the number of nodes in the social network is unchanged, that is, S(t)+P(t)+N(t)+R(t)=K.

[0126] Step 52: Calculate the probability of user sentiment evolution based on user influence, social network activity, and sentiment polarity score.

[0127]

[0128] Where Spreader(i) is the number of users who are positive nodes P and negative nodes N among the followers of microblog user i, Emotion(i) is the sentiment polarity of the microblog posted by user i after sentiment analysis, 1 represents positive polarity, and -1 represents negative polarity. Popular(t) represents the activity of the social network at time t, and α represents the parameter for tuning the result.

[0129] Step 5.3. Then calculate ω1 and ω2 according to the sentiment polarity score. If the user's sentiment polarity is greater, the impact of his user influence on the evolution of sentiment will be greater, that is, the larger ω1 is. On the contrary, the impact of social network activity on the evolution of sentiment will be smaller, and ω2 will be smaller. The method of processing ω1 and ω2 using the sentiment polarity score is:

[0130]

[0131] score(i) is the sentiment polarity score of social network user i, |score| max is the maximum value of sentiment polarity score among social network users, |score| min It is the value with the smallest sentiment polarity score in the social network.

[0132] Step 54: According to the forgetting probability, calculate the probability β1 and β2 that the node evolves from a positive node P and a negative node N to an immune node R and loses the ability to evolve emotions. The calculation method is:

[0133]

[0134] Among them, γ is used to adjust the rate of change of the forgetting probability, which is related to the user's influence. The greater the user's influence, the slower the growth of the forgetting probability should be, so it is inversely proportional to the user's influence, that is,

[0135] From its dynamic model, we can know that the change of its nodes is that the susceptible node S gradually becomes the positive node P and the negative node N due to being infected by the surrounding positive nodes P and negative nodes N, thus gradually decreasing and finally decreasing to 0. Since the susceptible node S keeps changing into the positive node P, and then gradually becomes the immune node R as the forgetting probability increases, the change of its nodes should be gradually increasing first, then gradually decreasing, and finally all become immune nodes S.

[0136] In step 6, the SIR-based information propagation model is used to analyze the sentiment evolution of social networks, specifically:

[0137] Step 61: traverse all nodes in the social network and perform text-based sentiment analysis on them to obtain their sentiment labels and sentiment polarity scores;

[0138] Step 62: Calculate the node influence and current social network activity of each node, and then calculate the probability of its sentiment evolution to determine whether its sentiment has evolved;

[0139] Step 63: Calculate the forgetting probability of each node, and determine whether the node state has changed based on the forgetting probability.

[0140] Step 64: Repeat step 62 to step 63 until all nodes are changed to immune nodes, and obtain the final social network user sentiment.

[0141] The technical solution provided by the present invention is further described in detail above through several specific implementation modes in order to highlight the advantages and benefits of the technical solution provided by the present invention. However, the several specific implementation modes described above are not intended to be used as limitations on the present invention. Any reasonable modification and improvement of the present invention, combination of implementation modes and equivalent substitution within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A social network sentiment evolution model integrating user influence and activity, characterized in that: The model analysis method is: Steps to collect text sentiment of target users; Steps for collecting the user influence of each user in the target social network; The step of collecting the activity of the target social network at time t; Collect the forgetting probability of each user at time t in the target social network as a step for the emotional evolution ability; Steps of the dynamics model of sentiment evolution in social networks; The steps of collecting the preset information dissemination model; A step of optimizing the evolution probability of the information propagation model according to the text sentiment; The step of analyzing the evolution process of the sentiment evolution dynamics model of the social network according to the optimized information propagation model.

2. According to claim 1, a social network sentiment evolution model integrating user influence and activity is characterized in that: The target user's text emotion is specifically the target microblog user's text emotion, which is obtained by: The step of performing sentence and word segmentation processing on the microblog text to obtain a word segmentation set; Traverse the sentences in the word segmentation set and detect sentiment words, degree adverbs and negative words; Compare the dictionary to obtain the weight of each sentiment word, degree adverb and negation word; The step of judging the sentiment tendency according to the weight.

3. The social network sentiment evolution model integrating user influence and activity according to claim 1 is characterized in that: The user influence of each user is obtained according to the number of followers and fans of each user.

4. The social network sentiment evolution model integrating user influence and activity according to claim 1 is characterized in that: According to the number of active nodes, passive nodes and immune nodes in the target social network at the time t, the activity of the target social network at the time t is obtained.

5. The social network sentiment evolution model integrating user influence and activity according to claim 1 is characterized in that: According to the forgetting mechanism and the user influence mechanism, the forgetting probability of each user at time t is obtained.

6. The social network sentiment evolution model integrating user influence and activity according to claim 1 is characterized in that: The information propagation model is obtained according to the user influence of each user, the activity of the target social network at time t, and the sentiment evolution ability.

7. An analysis device for a social network sentiment evolution model integrating user influence and activity, characterized in that: include: A module for collecting text sentiments of target users; A module that collects the user influence of each user in the target social network; A module for collecting the activity of the target social network at time t; Collect the forgetting probability of each user at time t in the target social network as a module for emotion evolution ability; Module for the dynamics model of sentiment evolution in social networks; A module for collecting preset information dissemination models; A module for optimizing the evolution probability of the information propagation model according to the text sentiment; A module for analyzing the evolution process of the sentiment evolution dynamics model of the social network according to the optimized information propagation model.

8. A computer storage medium for storing a computing program, characterized in that: When the computer reads the computer program, the computer executes the method of claim 1.

9. A computer, comprising a processor and a storage medium, characterized in that: When the processor reads the computer program stored in the storage medium, the computer executes the method of claim 1 .

10. A computer program product, being a computer program, characterized in that When the computer program is executed, the method of claim 1 is implemented.

Images