Public opinion event propagation analysis method, public opinion event propagation analysis system and computer program product

Abstract

The invention belongs to an event analysis method, and provides a public opinion event propagation analysis method, a public opinion event propagation analysis system and a computer program product in order to solve the technical problem that a mathematical model is not fully used for exploring causes and a propagation mechanism in a network space in current research about moods of netizens. In different stages of the public opinion event, different models are adopted to analyze the propagation condition of the public opinion event, the progress of the public opinion event is divided according to whether bifurcation occurs, the network public opinion event is described in a mode of combining a chaos dynamics model and an infectious disease model, and the public opinion propagation process is analyzed in each stage. Therefore, reasons and essential reasons for changing network public opinion events into network violence events can be known fundamentally, and a strategy for controlling the trend of public opinions can be formulated based on the reasons. According to the method, the comprehensive model is improved, the public opinion process in which the network storm possibly occurs can be completely described, and in practical application, disposal suggestions can be given in combination with data analysis.

Description

Technical Field

[0001] The present application relates to an event analysis method, and specifically to a public opinion event propagation analysis method, system, and computer program product. Background Art

[0002] The rapid development of platforms such as social media has made it easy and quick for people to express their opinions on the platforms. It has also led to a large number of opinions with positive and negative emotions spreading rapidly on the Internet. As a result, many ordinary public opinions may evolve into incidents of cyber violence.

[0003] At present, the research on netizens' emotions mainly focuses on psychology, sociology and behaviorism. Most of these studies focus on netizens' internal psychological orientation, psychological dynamics and the resulting external behavioral problems, or the behavioral interactions of netizens based on different cultural backgrounds and personality traits. However, these studies often only stay at the level of qualitative description and analysis, lacking in-depth quantitative research and support from mathematical models, and not making full use of mathematical models to explore the causes of these emotions and their propagation mechanisms in cyberspace. Summary of the invention

[0004] This application aims to address the technical problem that current research on netizens' emotions has not fully used mathematical models to explore the causes and propagation mechanisms in cyberspace, and provides a method, system, and computer program product for analyzing the propagation of public opinion events.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions: In the first aspect, the present application proposes a method for analyzing the spread of public opinion events, including: The stage of the current public opinion event is determined based on whether it evolves into a cyber violence incident. The stage before it evolves into a cyber violence incident is recorded as the first stage, and the stage after it evolves into a cyber violence incident is recorded as the second stage. In the first stage, the SEPNR model is used to describe the development of public opinion events; the SEPNR model divides the crowd into five categories: unknowns, lurkers, positive emotion communicators, negative emotion communicators and immune people; the communication process between different categories of people includes: unknowns are transformed into lurkers after obtaining information on the Internet; lurkers become immune people, positive emotion communicators or negative emotion communicators according to the characteristics of the information and their judgment of the information; positive emotion communicators and negative emotion communicators can transform into each other, and both have the possibility of transforming into immune people; immune people do not spread; In the second stage, the chaotic mechanics model is used to describe the development of public opinion events, which is used to obtain the complexity and nonlinear characteristics of network public opinion based on the bifurcation characteristics.

[0006] Furthermore, the propagation dynamics equation of the SEPNR model is:

[0007] in, For the unknown, is the propagation time, The probability that an unknown person will become a lurker after obtaining information on the Internet. For lurkers, is the probability of a lurker turning into a positive emotion communicator, is the probability of a lurker turning into a negative emotion spreader, is the latent immunity rate, To be a positive emotion spreader, is the probability of a positive emotion communicator turning into a negative emotion communicator, is the probability of a negative emotion communicator transforming into a positive emotion communicator, Spreaders of negative emotions is the probability of positive emotion communicators turning into immune people, is the probability of a negative emotion spreader becoming an immune person, For the immune ones.

[0008] Furthermore, the discrete chaos mapping expression in the chaotic mechanics model is:

[0009] in, For the The state at the iteration, is the control parameter used to determine the system dynamics, For the The state at the iteration, is the number of iterations.

[0010] Furthermore, it also includes formulating corresponding processing strategies according to the description results of the first stage and / or the second stage.

[0011] Furthermore, formulating a corresponding processing strategy according to the description results of the first stage and / or the second stage includes: The parameters of the propagation dynamics equation of the SEPNR model are set according to the strength of external supervision, and different schemes are formed accordingly; Through simulation analysis, the optimal supervision intensity is determined by analyzing the changes in the five categories of people in each plan over time.

[0012] Furthermore, the formulating of corresponding processing strategies according to the description results of the first stage and / or the second stage also includes: , determine the direction of public opinion events and formulate corresponding handling strategies.

[0013] In the second aspect, the present application proposes a public opinion event propagation analysis system, comprising: The stage demarcation module is used to determine the stage of the current public opinion time based on whether it evolves into a cyber violence incident. The period before the evolution into a cyber violence incident is recorded as the first stage, and the period after the evolution into a cyber violence incident is recorded as the second stage. The first description module is used to describe the development of public opinion events using the SEPNR model in the first stage; wherein the SEPNR model divides the crowd into five categories: unknowns, lurkers, positive emotion communicators, negative emotion communicators and immune people; the communication process between different categories of people includes: unknowns are transformed into lurkers after obtaining information on the Internet; lurkers become immune people, positive emotion communicators or negative emotion communicators according to the characteristics of the information and their judgment of the information; positive emotion communicators and negative emotion communicators can transform into each other, and both have the possibility of transforming into immune people; immune people do not spread; The second description module is used to describe the development of public opinion events using a chaotic mechanics model in the second stage, and is used to obtain the complexity and nonlinear characteristics of network public opinion based on bifurcation characteristics.

[0014] On the third aspect, the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for analyzing the propagation of public opinion events.

[0015] Compared with the prior art, this application has the following beneficial effects: This application proposes a method for analyzing the spread of public opinion events. Different models are used at different stages of public opinion events to analyze the spread of public opinion events, and the progress of public opinion events is divided according to whether bifurcation occurs. The chaotic dynamics model and the infectious disease model are combined to describe online public opinion events. The public opinion propagation process is analyzed separately at each stage, so that the reasons and essential reasons for the transformation of online public opinion events into online violence events can be fundamentally understood, and strategies on how to control the direction of public opinion can be formulated based on this. The comprehensive model proposed in this application can fully describe the public opinion process in which online violence may occur. In practical applications, it can be combined with data analysis to give disposal suggestions, and thus provide a certain reference for the measures that can be taken in online violence events.

[0016] This application also proposes a public opinion event propagation analysis system and a computer program product, which have all the advantages of the above-mentioned public opinion event propagation analysis method. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the technical solutions of the embodiments of the present application, the accompanying drawings required for the embodiments will be briefly introduced below. It should be understood that the following accompanying drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related accompanying drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is the first flow schematic diagram of the public opinion event propagation analysis method of the present application; Figure 2 It is the propagation schematic diagram of the SEPNR model in the embodiments of the present application; Figure 3 It is the bifurcation diagram of the IMP Logistic (1 < p < 2) mapping in the embodiments of the present application; Figure 4(a) is the model change diagram of the first government-level solution of the SEPNR model in the embodiments of the present application; Figure 4(b) is the model change diagram of the second government-level solution of the SEPNR model in the embodiments of the present application; Figure 4(c) is the model change diagram of the third government-level solution of the SEPNR model in the embodiments of the present application; Figure 5(a) is in the embodiments of the present application β The schematic diagram of the model change when the media reports on the event when = 0.3; Figure 5(b) is in the embodiments of the present application β The schematic diagram of the model change when the media reports on the event when = 0.5; Figure 5(c) is in the embodiments of the present application β The schematic diagram of the model change when the media reports on the event when = 0.7; Figure 5(d) is in the embodiments of the present application β The schematic diagram of the model change when the media reports on the event when = 0.9; Figure 6(a) is in the embodiments of the present application = 0.02, The schematic diagram of the model change when the media mainly promotes positive emotions when = 0.02; Figure 6(b) is in the embodiments of the present application = 0.06, The schematic diagram of the model change when the media mainly promotes positive emotions when = 0.06; Figure 6(c) is in the embodiments of the present application = 0.1, The schematic diagram of the model change when the media mainly promotes positive emotions when = 0.1; Figure 7(a) is in the embodiments of the present application = 0.02, =0.02, the model changes when the media mainly promotes negative emotions; FIG. 7 (b) is an example of the present application. =0.06, =0.06, the model changes when the media mainly promotes negative emotions; FIG. 7 (c) is an example of the present application. =0.1, =0.1, the model changes when the media mainly promotes negative emotions; Figure 8 A schematic diagram of the public opinion event propagation analysis system of this application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0022] In the description of the embodiments of the present application, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, or the orientation or position relationship in which the invented product is usually placed when used. It is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0023] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0024] In the description of the embodiments of the present application, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0025] The existence of social media platforms allows information to be seen and forwarded by a large number of users in a very short period of time, thus quickly forming public opinion events. When facing an event, netizens often express their opinions based on their own positions, experiences and emotions. The emotions contained in these opinions, whether positive or negative, can have an infectious effect on others, thereby affecting the direction of the entire public opinion. When a public opinion event triggers negative emotions among a large number of netizens, such emotions can easily be amplified online, forming cyber violence. Cyber ​​violence may not only cause serious psychological harm to the parties involved in the event, but may also destroy the network ecology and affect social stability.

[0026] Current research often only focuses on the positive or negative emotions of netizens, ignoring the interaction and transformation between these two emotions. In fact, the development of public opinion events is often driven by the interweaving of multiple emotions. Although there are a large number of empirical studies exploring the impact of netizens' emotions on public opinion, most of these studies remain at the level of qualitative analysis and lack quantitative analysis through mathematical models, making it difficult to accurately predict and explain the development of public opinion events.

[0027] Therefore, in response to the problem of online violence-related public opinion incidents that exist in the current society, this application proposes a method, system, and computer program product for analyzing the spread of public opinion events, which combines the chaotic dynamics model and the infectious disease model to study the development process of the entire public opinion event. Depending on whether the chaotic dynamics model bifurcates and enters a chaotic state, the online public opinion event is divided into two stages for study.

[0028] like Figure 1 As shown, it is a first flow chart of the public opinion event propagation analysis method of the present application, which may include: S101, based on whether it evolves into a cyber violence incident, determine the stage of the current public opinion incident, and record the period before it evolves into a cyber violence incident as the first stage, and the period after it evolves into a cyber violence incident as the second stage.

[0029] S102, in the first stage, the SEPNR model is used to describe the development of public opinion events.

[0030] Among them, the SEPNR model divides the population into five categories: unknowns, lurkers, positive emotion communicators, negative emotion communicators and immune people; the communication process between different categories of people includes: unknowns are transformed into lurkers after obtaining information on the Internet; lurkers become immune people, positive emotion communicators or negative emotion communicators according to the characteristics of the information and their judgment of the information; positive emotion communicators and negative emotion communicators can transform into each other, and both have the possibility of transforming into immune people; immune people do not spread.

[0031] It should be noted that the SEPNR model is a model that divides people into different categories and describes the information dissemination process between them. Specifically, unknowns refer to people who have not yet been exposed to relevant information about public opinion events. Lurkers are people who have been exposed to information but have not yet shown obvious emotional tendencies or dissemination behaviors. Positive emotional communicators are people who have a positive attitude towards public opinion events and tend to spread positive information. Negative emotional communicators are people who have a negative attitude towards public opinion events and tend to spread negative information. Immune people are people who are not interested in public opinion events or have formed fixed views and no longer spread them. The SEPNR model describes the dissemination process between these groups, including how unknowns are transformed into lurkers, how lurkers become people of other categories based on information characteristics, and the mutual transformation between positive emotional communicators and negative emotional communicators.

[0032] S103, in the second stage, a chaotic mechanics model is used to describe the development of public opinion events, which is used to obtain the complexity and nonlinear characteristics of network public opinion based on bifurcation characteristics.

[0033] At this stage, the development of public opinion events becomes more complex and nonlinear, so the chaotic mechanics model can be used to describe it. The chaotic mechanics model can capture the bifurcation characteristics of the development of public opinion events, that is, the direction of public opinion events may suddenly change at a certain moment. This bifurcation characteristic reflects the complexity and nonlinear characteristics of online public opinion, allowing us to have a deeper understanding of the development laws and possible trends of public opinion events.

[0034] Through the method of this application, a comprehensive and in-depth analysis of the development of public opinion events can be conducted, so as to better predict and respond to possible online violence events. At the same time, this method also provides a scientific basis for formulating effective public opinion management strategies.

[0035] The present application is further described in detail below with reference to examples: For infectious disease models: Compared with the traditional SEIR (Susceptible-Exposed-Infectious-Recovered) model, in the process of the development of public opinion events, various positive and negative emotions will spread in social media, and the positive or negative emotional spread will stimulate netizens, affect their judgment of public opinion events, and even affect the spread of public opinion events. Especially in cyber violence events, the emotional bias of netizens in social media has an extremely important impact on the spread of events. Therefore, based on the traditional SEIR model, it is improved and optimized to form the emotion-based SEPNR (Susceptible-Exposed-Positive Spreaders-Negative Spreaders-Resistant) model.

[0036] In the SEPNR model, all people are divided into five categories, namely, unknown people S, latent people E, positive emotion communicators P, negative emotion communicators N, and immune people R. Figure 2 As shown in Figure 1, it is a propagation diagram of the SEPNR model. is the infection rate, Figure 2 middle, is the probability of a lurker turning into a positive emotion communicator, is the probability of a lurker turning into a negative emotion spreader, is the immunity rate of latent is the probability of a positive emotion communicator turning into a negative emotion communicator, is the probability of a negative emotion communicator transforming into a positive emotion communicator, is the immunity rate of positive emotion communicators, The immunity rate for those who spread negative emotions.

[0037] The kinetic equation of propagation of the SEPNR model in this application is as follows:

[0038] The specific propagation process is: 1. Unknown (S) The probability of obtaining certain information on the Internet through various channels and becoming a lurker.

[0039] 2. Lurkers (E) may not be interested in the information based on its characteristics and their own judgment of it. The probability of becoming immune or having a positive attitude towards information is The probability of becoming a positive emotional communicator, or having a negative attitude towards the information, The probability of becoming a negative emotion spreader.

[0040] 3. Positive emotion communicators (P) may be incited by the speech of negative emotion communicators. The probability of becoming a negative emotion spreader or gradually losing interest in it. The probability of becoming immune.

[0041] 4. Negative emotion communicators (N) may be moved by the words of positive emotion communicators. The probability of becoming a negative emotion spreader or gradually losing interest in it. The probability of becoming immune.

[0042] 5. Immune people (R) receive but do not transmit.

[0043] The infectious disease model and chaotic dynamics model are used to describe the first and second stages of the event and conduct analysis.

[0044] Here is an example: In the first stage of the entire incident, that is, before it evolved into a cyber violence incident, the emotion-based SEPNR model was used to describe the development of the public opinion event. The initial value of the model was set according to the data of the first stage of public opinion dissemination. The focus was on discussing the changes in the dissemination process under the intervention of the government and the media.

[0045] 1. Government level At the government level, the time and means of government intervention are collectively referred to as regulatory intensity. In order to supervise public opinion events, the government's regulatory intensity is divided into three levels: Level 0 means no regulation: the government does not take any measures.

[0046] Level 1 is general supervision: that is, the government takes general supervision measures, some self-media follow up on the incident and report the truth of the incident, call for a rational view of the incident, etc., and relevant parties declare their intervention in the handling, announce the results of the handling, and optimize the public management system. In the above case, some self-media on major platforms report on the incident and track the truth of the incident.

[0047] Level 2 is enhanced supervision: the government takes enhanced supervision measures, the official media follows up on the truth of the incident, calls for a rational view of the incident, etc.; the government announces the truth of the incident, publicizes the handling plan, and promises the handling results, etc.; the network platform operator takes technical intervention measures. In the above case, the government takes relevant measures to investigate the incident and publish the investigation results.

[0048] According to the above classification of regulatory levels, set the corresponding parameter plan (implementation plan). Table 1 is the corresponding table of implementation plans Table 1 Supervision intensity plan

[0049] Assume that in the absence of any regulation, the infection rate ( ) is 0.7. As the incident is gradually exposed, the infection rate gradually increases. Assuming that there is no supervision, the parameters are set as shown in Scheme 1. As the incident continues to be exposed, relevant measures are taken. (The rate of lurkers turning into positive emotion communicators) increases, (The rate at which lurkers turn into negative emotion spreaders) decreases, (The rate of positive emotion communicators turning into negative emotion communicators) increases, (The rate of negative emotion communicators turning into positive emotion communicators) decreases, (latent immunity rate) increases. The program parameter settings are shown in Table 2.

[0050] Table 2 Scheme parameter table

[0051] The three schemes were analyzed using Matlab9.4.0.813654 (R2018a) simulation software. The model changes of each scheme are shown in Figure 4, where (a) is the model change diagram of scheme 1 at the government level, (b) is the model change diagram of scheme 2 at the government level, and (c) is the model change diagram of scheme 3 at the government level.

[0052] Through the analysis of model changes, it can be obtained that in scheme three, the curve reaches equilibrium the fastest, that is, the proportion of immune people reaches 1, and the proportions of the rest of the population are all 0, and under this parameter condition, the proportion of those who spread negative emotions is the smallest, which shows that the government's adoption of level 2 regulatory measures is more conducive to public opinion reaching a balance point faster and making public opinion tend to stabilize.

[0053] 2. Media level At the media regulatory level, the discussion focuses on parameter changes in three aspects.

[0054] (1) Media reports on the incident Media coverage of the incident will attract more public attention. The value increases. The model change of media reporting on events is shown in Figure 5, where (a) is =0.3, (b) is the model change diagram of media reporting on events. = 0.5, (c) is the model change diagram of media reporting on events. =0.7, (d) is the model change diagram of media reporting on events. =0.9.

[0055] Through the analysis of model changes, it can be found that as the media reports on the incident, the infection rate It continues to rise, which means that more unknown people will learn about the incident and turn into lurkers, thus promoting the spread of public opinion events. The larger it is, the faster the entire event spreads, the faster P, N, S, and E drop to 0, and the faster R rises to 1. This shows that due to the increasing infection rate, more unknown people are transformed into latent ones and eventually into immune ones.

[0056] If media reports mainly promote positive emotions: Media reports mainly promote positive emotions, which leads to more negative emotion spreaders being transformed into positive emotion spreaders. Increase, The model change of the media mainly promoting positive emotions is shown in Figure 6, where (a) is =0.02, = 0.02, the media mainly promotes positive emotions, (b) =0.06, = 0.06, the model change diagram of the media mainly promoting positive emotions, (c) =0.1, =0.1, the model changes when the media mainly promotes positive emotions.

[0057] Through the analysis of model changes, it can be found that the media focuses on spreading positive emotions during the dissemination of public opinion events, which makes the overall emotions of netizens tend to be positive. (the probability of a lurker turning into a positive emotion communicator), (The probability of negative emotion communicators turning into positive emotion communicators) increases, resulting in an increase in the proportion of positive emotion communicators in the entire communication process, which is more conducive to the governance of online violence incidents.

[0058] If media reports mainly promote negative sentiment: Media reports promote negative emotions, causing more positive emotion spreaders to become negative emotion spreaders. Increase, The model change of the media mainly promoting negative emotions is shown in Figure 7, where (a) is =0.02, = 0.02, the media mainly promotes positive emotions, (b) =0.06, = 0.06, the model change diagram of the media mainly promoting positive emotions, (c) =0.1, =0.1, the model changes when the media mainly promotes positive emotions.

[0059] Through the analysis of model changes, it can be found that the media focuses on promoting negative emotions during the dissemination of public opinion events, which makes the overall emotions of netizens tend to be negative. (the probability of a lurker turning into a negative emotion spreader), (The probability of positive emotion communicators turning into negative emotion communicators) increases, resulting in an increase in the proportion of negative emotion communicators in the entire communication process, which is more unfavorable for the governance of online violence incidents.

[0060] For chaotic dynamics models: Chaotic dynamics models can be used to describe and analyze the complexity and nonlinear characteristics of online public opinion, which helps to better understand and predict the evolution of online public opinion, and provides a new perspective and method for understanding and predicting the evolution of online public opinion. "Chaos" is an irregular macroscopic spatiotemporal behavior generated by an inherent nonlinear dynamics itself, and is a steady state of a nonlinear dynamic equation described by a deterministic equation. Chaos is the seemingly random irregular motion of a nonlinear system, and chaotic behavior is characterized by uncertainty, non-repeatability, and unpredictability.

[0061] Chaotic behavior can be characterized by an iterative mapping. A nonlinear mapping , is an equation, that is, for any , there is only Correspondingly, for any current state of the iterative mapping , the next state can be determined by the following mapping relationship :

[0062] in, represents a real or complex number, represents the number of iterations, Represents the iteration trajectory.

[0063] The common discrete chaotic map is the improved Logistic (IMP Logistic, improved Logistic) chaotic map, and the specific expression is:

[0064] in, , . p is the control parameter that determines the dynamic behavior of the system. Parameter p controls the growth rate of the system. If parameter p is too small, the system may converge to a fixed point. If parameter p is large, more complex dynamic behaviors may occur, including periodic and chaotic behaviors. Changes in parameter p not only affect the stability of the system, but also the type and nature of the attractor.

[0065] In a chaotic dynamics model, the bifurcation phenomenon of chaos refers to the qualitative mutation of the stable and unstable states of a system at some nodes (called bifurcation points) during the evolution of a dynamic system. Bifurcation often occurs when the nonlinearity of the system is strong enough. The bifurcation diagram of a chaotic map takes a certain parameter of the chaotic map as the abscissa and the stable steady state as the ordinate. The bifurcation diagram reflects the state of whether the map is constant, periodic, or chaotic as certain parameters change. As Figure 3 shown, it is the bifurcation diagram of the IMP Logistic (1 < p < 2) map. As the parameter p changes from small to large, the state changes from period-doubling bifurcation to chaos, and there is a self-similar structure of repeated period-doubling bifurcation within the chaos.

[0066] In the above two cases, great changes have occurred in the process of public opinion dissemination. For example, in the case of "the incident of a primary school student being hit on campus in Wuhan", due to the accusations from netizens about the dressing and appearance of the mother of the hit student and the assumption that it was for money, the dissemination process began to bifurcate and enter a chaotic state, that is, it did not develop in the direction of targeting the driver and the hit primary school student, but instead turned to discussions and accusations against his mother and his family, forming online violence, and making the development of the whole incident move towards an uncontrollable and unpredictable direction. Similarly, in the case of "the pink-haired girl died due to online violence", due to the change in the attention of netizens, which shifted to the pink hair of the girl and her personal life, a large number of accusations and online violence against the girl occurred, also making the matter develop in an unpredictable and uncontrollable direction.

[0067] This process of deviating from the预想 and developing in a completely different direction from before can be described by the bifurcation characteristics in the chaotic dynamics model. In the chaotic dynamics model, its chaotic parameters determine the final change situation of the entire public opinion event, and will determine whether the whole process bifurcates and enters a chaotic state. In the above cases, it is precisely because the opinions and attention of netizens towards the event have changed, resulting in a bifurcation change in the chaotic parameters, which has caused the entire public opinion process to bifurcate, form online violence, and start to develop in an unpredictable and uncontrollable direction similar to chaos. Therefore, in order to manage online violence, it is also necessary to pay extra attention to the changes in the chaotic parameters, and its changes will affect the final direction of the whole process.

[0068] The above experimental results show that in the first stage of public opinion development when the chaotic dynamics model does not bifurcate, the infectious disease model is used to describe the evolution of public opinion. Through parameter analysis, it is suggested that the government needs to intervene in the incident as soon as possible, the media should guide netizens' views to develop in a positive direction, and strengthen the supervision of accounts that publish bad opinions on social media platforms. In the second stage when the chaotic dynamics model bifurcates and enters a chaotic state, and cyber violence occurs, it is suggested that special attention should be paid to the changes in the opinions of big Vs in social networks and the changes in netizens' opinions and attention during the development of public opinion events, which will directly affect the changes in chaotic parameters and thus affect the direction of the development of public opinion events.

[0069] The method proposed in this application involves a new public opinion event model that combines a chaotic dynamics model with an infectious disease model. It can describe the transformation process from a type of ordinary public opinion event to a cyber violence event. The model can be divided into two stages according to whether the model bifurcates. In the first stage, that is, before the model bifurcates and enters the chaotic state, the emotion-based SEPNR model is used to describe it. As the event develops, due to the incitement of some remarks on social networks, some netizens' attention and opinions on the event begin to change, causing the entire public opinion process to bifurcate and enter a chaotic state. The model enters the second stage and evolves into a cyber violence event.

[0070] like Figure 8 As shown, it is a schematic diagram of a public opinion event propagation analysis system, which may include: The stage demarcation module is used to determine the stage of the current public opinion time based on whether it evolves into a cyber violence incident. The period before the evolution into a cyber violence incident is recorded as the first stage, and the period after the evolution into a cyber violence incident is recorded as the second stage. The first description module is used to describe the development of public opinion events using the SEPNR model in the first stage; wherein the SEPNR model divides the crowd into five categories: unknowns, lurkers, positive emotion communicators, negative emotion communicators and immune people; the communication process between different categories of people includes: unknowns are transformed into lurkers after obtaining information on the Internet; lurkers become immune people, positive emotion communicators or negative emotion communicators according to the characteristics of the information and their judgment of the information; positive emotion communicators and negative emotion communicators can transform into each other, and both have the possibility of transforming into immune people; immune people do not spread; The second description module is used to describe the development of public opinion events using a chaotic mechanics model in the second stage, and is used to obtain the complexity and nonlinear characteristics of network public opinion based on bifurcation characteristics.

[0071] It should be noted that in the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the system embodiments described above are merely schematic. For example, the division of each module is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules can be combined or integrated into another device, or some features can be ignored or not executed. The module described as a separate component may or may not be physically separated. The component displayed as a module may be a physical unit or multiple physical units, that is, it may be located in one place, or it may be distributed in multiple different places. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0072] In addition, each module in each embodiment of the present invention may be integrated into a processing unit, each module may exist physically separately, or two or more modules may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0073] The present application also proposes a computer program product, which includes instructions, and when the instructions are executed by a processor, the steps in the above-mentioned public opinion event propagation analysis method embodiment are implemented.

[0074] The computer program may be divided into one or more modules / units, and the one or more modules / units are stored in a memory and executed by the processor to accomplish the present invention.

[0075] The carrier for implementing the above-mentioned computer program product may be a computer device, or the computer program product may be stored in a computer storage medium.

[0076] The computer device may be a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The computer device may include, but is not limited to, a processor and a memory.

[0077] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0078] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0079] If the module / unit integrated in the computer device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0080] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for analyzing the spread of public opinion events, characterized in that: include: The stage of the current public opinion event is determined based on whether it evolves into a cyber violence incident. The stage before it evolves into a cyber violence incident is recorded as the first stage, and the stage after it evolves into a cyber violence incident is recorded as the second stage. In the first stage, the SEPNR model is used to describe the development of public opinion events; the SEPNR model divides the crowd into five categories: unknowns, lurkers, positive emotion communicators, negative emotion communicators and immune people; the communication process between different categories of people includes: unknowns are transformed into lurkers after obtaining information on the Internet; lurkers become immune people, positive emotion communicators or negative emotion communicators according to the characteristics of the information and their judgment of the information; positive emotion communicators and negative emotion communicators can transform into each other, and both have the possibility of transforming into immune people; immune people do not spread; In the second stage, the chaotic mechanics model is used to describe the development of public opinion events, which is used to obtain the complexity and nonlinear characteristics of network public opinion based on the bifurcation characteristics.

2. The method for analyzing the spread of public opinion events according to claim 1 is characterized in that: The propagation dynamics equation of the SEPNR model is: in, For the unknown, is the propagation time, The probability that an unknown person will become a lurker after obtaining information on the Internet. For lurkers, is the probability of a lurker turning into a positive emotion communicator, is the probability of a lurker turning into a negative emotion spreader, is the latent immunity rate, To be a positive emotion spreader, is the probability of a positive emotion communicator turning into a negative emotion communicator, is the probability of a negative emotion communicator transforming into a positive emotion communicator, Spreaders of negative emotions. is the probability of positive emotion communicators turning into immune people, is the probability of a negative emotion spreader becoming an immune person, For the immune ones.

3. The method for analyzing the spread of public opinion events according to claim 2 is characterized in that: The discrete chaos mapping expression in the chaotic mechanics model is: in, For the The state at the iteration, is the control parameter used to determine the system dynamics, For the The state at the iteration, is the number of iterations.

4. The method for analyzing the spread of public opinion events according to any one of claim 3, characterized in that: It also includes formulating corresponding treatment strategies based on the descriptive results of the first stage and / or the second stage.

5. The method for analyzing the spread of public opinion events according to claim 4 is characterized in that: According to the description results of the first stage and / or the second stage, a corresponding processing strategy is formulated, including: The parameters of the propagation dynamics equation of the SEPNR model are set according to the strength of external supervision, and different schemes are formed accordingly; Through simulation analysis, the optimal supervision intensity is determined by analyzing the changes in the five categories of people in each plan over time.

6. The method for analyzing the spread of public opinion events according to claim 4 is characterized in that: The method of formulating a corresponding processing strategy according to the description results of the first stage and / or the second stage also includes: , determine the direction of public opinion events and formulate corresponding handling strategies.

7. A public opinion event dissemination analysis system, characterized in that: include: The stage demarcation module is used to determine the stage of the current public opinion time based on whether it evolves into a cyber violence incident. The period before the evolution into a cyber violence incident is recorded as the first stage, and the period after the evolution into a cyber violence incident is recorded as the second stage. The first description module is used to describe the development of public opinion events using the SEPNR model in the first stage; wherein the SEPNR model divides the crowd into five categories: unknowns, lurkers, positive emotion communicators, negative emotion communicators and immune people; the communication process between different categories of people includes: unknowns are transformed into lurkers after obtaining information on the Internet; lurkers become immune people, positive emotion communicators or negative emotion communicators according to the characteristics of the information and their judgment of the information; positive emotion communicators and negative emotion communicators can transform into each other, and both have the possibility of transforming into immune people; immune people do not spread; The second description module is used to describe the development of public opinion events using a chaotic mechanics model in the second stage, and is used to obtain the complexity and nonlinear characteristics of network public opinion based on bifurcation characteristics.

8. The public opinion event propagation analysis system according to claim 7 is characterized in that: In the first description module, the propagation dynamics equation of the SEPNR model is: in, For the unknown, is the propagation time, The probability that an unknown person will become a lurker after obtaining information on the Internet. For lurkers, is the probability of a lurker turning into a positive emotion communicator, is the probability of a lurker turning into a negative emotion spreader, is the latent immunity rate, To be a positive emotion spreader, is the probability of a positive emotion communicator turning into a negative emotion communicator, is the probability of a negative emotion communicator transforming into a positive emotion communicator, Spreaders of negative emotions. is the probability of positive emotion communicators turning into immune people, is the probability of a negative emotion spreader becoming an immune person, For the immune ones.

9. The public opinion event propagation analysis system according to claim 7 is characterized in that: In the second description module, the discrete chaos mapping expression in the chaotic mechanics model is: in, For the The state at the iteration, is the control parameter used to determine the system dynamics, For the The state at the iteration, is the number of iterations.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for analyzing the propagation of public opinion events as described in any one of claims 1 to 6 is implemented.

Images