CN112396150B - Rumor event analysis method, rumor event analysis device, rumor event analysis equipment and computer readable storage medium - Google Patents
Rumor event analysis method, rumor event analysis device, rumor event analysis equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN112396150B CN112396150B CN202011241201.2A CN202011241201A CN112396150B CN 112396150 B CN112396150 B CN 112396150B CN 202011241201 A CN202011241201 A CN 202011241201A CN 112396150 B CN112396150 B CN 112396150B
- Authority
- CN
- China
- Prior art keywords
- rumor
- user
- user node
- target
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Abstract
The application provides a rumor event analysis method, a rumor event analysis device, rumor event analysis equipment and a computer readable storage medium, which are used for effectively analyzing rumor events. The method comprises the following steps: determining that a target social platform with a target rumor event in a propagation state exists in a platform network; acquiring user nodes in a target social platform, and initial fitness of the user nodes to the rumor formation information and social relations of the user nodes; dividing the user node into a plurality of user sets, and selecting a target user node meeting the optimal adaptability requirement from each user set; the continuous daylighting simulation processing is carried out on a plurality of user sets through the frog-leaping algorithm and the particle swarm optimization algorithm, and each iteration process of the continuous daylighting simulation processing comprises the following steps: pushing the balling information to target user nodes, updating the fitness of each user node to the balling information in combination with the social relationship, detecting whether each user node is updated to meet the optimal fitness requirement, and if so, meeting the convergence standard; and obtaining simulation results of continuous rumor simulation processing.
Description
Technical Field
The present application relates to the field of communications, and in particular, to a method, apparatus, device, and computer readable storage medium for analyzing rumor events.
Background
With the rapid growth of the internet and the advent of various forms of networks, social platforms have become a popular big channel for communicating and collecting first hand information between users on online social networks. The social platform propagates information in a fixed manner, so that users can timely publish the information and share the information with other users online, the information comprises hand information, and the information can be widely propagated through the social platform in various ways such as words, images, videos, audios, hyperlinks and the like.
However, some people do not satisfy the curiosity of the public or have individuals who are low, and in the social platform, unrealistic messages or cataloging messages are released, which can come from any user and can be propagated throughout the social platform, and whether they are true or false, cannot be verified for the first time, and social harmony may be affected once false or fraudulent rumor information appears and takes public opinion on the social platform.
In the research process of the prior related art, the inventor finds that the prior balling mechanism is the balling information published on the social platform through some authorities or authoritative accounts, but in practical application, the authorities or authoritative accounts may be misled and further issue false balling information, which further spreads the rumen, and secondly, the distribution channels of the authorities or authoritative accounts are limited by the manual operation of staff, so that the problem of reaction lag exists, and secondly, the situation of limited audience is also involved, and from the content, the prior balling mechanism obviously has the problem of low balling efficiency, such as early propagation stage of novel coronavirus pneumonia (covd-19), and various rumors are enriched on each large social platform, so that the panic of the masses is caused, and meanwhile, the progress of epidemic management and control work is easily influenced, which is very unfavorable for social harmony.
Disclosure of Invention
The application provides a rumor event analysis method, a rumor event analysis device, rumor event analysis equipment and a computer readable storage medium, which are used for effectively analyzing rumor events and obtaining simulation results of continuous rumor-forming simulation processing of the rumor events, so that relevant coping operations can be arranged in a first time according to the simulation results, and continuous rumor-forming can be performed efficiently.
In a first aspect, the present application provides a method for analysing a rumor event, the method comprising:
determining that a target social platform with a target rumor event in a propagation state exists in a platform network;
acquiring user nodes in a target social platform, initial fitness of the user nodes to the rumor-forming information and social relations of the user nodes, wherein the user nodes comprise infection nodes of target rumor events;
dividing the user nodes into a plurality of user sets as different frog populations formed by different frog individuals, and selecting target user nodes meeting the optimal adaptability requirement from each user set;
the continuous daylighting simulation processing is carried out on the plurality of user sets through a frog-leaping algorithm (Shuffled Frog Leading Algorithm, SFLA) and a particle swarm optimization algorithm (Particle swarm optimization, PSO), and each iteration process of the continuous daylighting simulation processing comprises the following steps: pushing the rumor information to target user nodes, updating the fitness of each user node to the rumor information by combining with social relations, detecting whether each user node is updated to meet the optimal fitness requirement, and if so, meeting convergence criteria to complete continuous rumor simulation processing;
And obtaining simulation results of continuous rumor simulation processing.
With reference to the first aspect of the present application, in a first possible implementation manner of the first aspect of the present application, the social relationship includes different affinities, self-reliability and credibility, the affinities are used for indicating the affinities between the user nodes, the self-reliability is used for indicating the credibility of the user nodes for self rumors distinguishing ability, the credibility is used for indicating the credibility between the user nodes, and the fitness is calculated according to the affinities, the self-reliability and the credibility.
With reference to the first possible implementation manner of the first aspect of the present application, in a second possible implementation manner of the first aspect of the present application, the affinity includes family membership, friend relationship, colleague/neighbor relationship, and stranger relationship, and when the affinity between the user node to be updated and the target user node that propagates the rumor information to the user node to be updated is the family relationship, the user node to be updated updates the fitness through the target user node; or alternatively, the process may be performed,
when the affinity between the user node to be updated and the target user node is a friend relationship, the user node to be updated updates the fitness through the release center node of the ballad information or the target user node; or alternatively, the process may be performed,
When the intimacy between the user node to be updated and the target user node is a colleague/neighbor relationship, the user node to be updated updates the fitness through the target user node based on the information propagation relationship established by the random user between the user node to be updated and the target user node; or alternatively, the process may be performed,
when the intimacy between the user node to be updated and the target user node is a stranger relationship, the user node to be updated updates the fitness through the release center node of the rumor-building information.
In a third possible implementation manner of the first aspect of the present application in combination with the first aspect of the present application, the optimal fitness requirement is a preset fitness of a central node for the distribution of the ballad information.
With reference to the first aspect of the present application, in a fourth possible implementation manner of the first aspect of the present application, the target rumor event is a rumor event having a long-time repeated continuous rumor requirement and issuing rumor information, or the target rumor event is a rumor event having a dispute or a different rumor conclusion, and issuing rumor information.
With reference to the first aspect of the present application, in a fifth possible implementation manner of the first aspect of the present application, obtaining an initial fitness of a user node to the ballad information and a social relationship of the user node includes:
Acquiring account information disclosed by a user node in a target social platform;
and determining initial fitness and social relation according to the account information.
With reference to the first aspect of the present application, in a sixth possible implementation manner of the first aspect of the present application, after obtaining a simulation result of the continuous rumor-building simulation result, the method further includes:
pushing the rumor-forming information to the target user node according to the simulation result so as to perform rumor-forming processing on the target rumor event in the target social platform according to the simulation result.
In a second aspect, the present application provides an analysis device for rumor events, the device comprising:
the determining unit is used for determining that a target social platform with a target rumor event in a propagation state exists in the platform network;
the acquisition unit is used for acquiring user nodes in the target social platform, initial fitness of the user nodes to the ballad information and social relations of the user nodes, wherein the user nodes comprise infection nodes of target ballad events;
the dividing unit is used for dividing the user nodes into a plurality of user sets as different frog populations formed by different frog individuals;
the selecting unit is used for selecting the target user node meeting the optimal adaptability requirement from each user set;
The simulation unit is used for performing continuous rumor-creating simulation processing on a plurality of user sets through the SFLA algorithm and the PSO algorithm, and each iteration process of the continuous rumor-creating simulation processing comprises the following steps: pushing the rumor information to target user nodes, updating the fitness of each user node to the rumor information by combining with social relations, detecting whether each user node is updated to meet the optimal fitness requirement, and if so, meeting convergence criteria to complete continuous rumor simulation processing;
the acquisition unit is also used for acquiring a simulation result of continuous rumor-forming simulation processing.
With reference to the second aspect of the present application, in a first possible implementation manner of the second aspect of the present application, the social relationship includes different affinities, self-reliability and credibility, the affinities are used for indicating the affinities between the user nodes, the self-reliability is used for indicating the credibility of the user nodes for self rumor distinguishing capability, the credibility is used for indicating the credibility between the user nodes, and the fitness is calculated according to the affinities, the self-reliability and the credibility.
With reference to the first possible implementation manner of the second aspect of the present application, in a second possible implementation manner of the second aspect of the present application, the affinity includes family membership, friendship, colleague/neighbor relationship, and stranger relationship, and when the affinity between the user node to be updated and the target user node that propagates the rumor information to the user node to be updated is the family relationship, the user node to be updated updates the fitness through the target user node; or alternatively, the process may be performed,
When the affinity between the user node to be updated and the target user node is a friend relationship, the user node to be updated updates the fitness through the release center node of the ballad information or the target user node; or alternatively, the process may be performed,
when the intimacy between the user node to be updated and the target user node is a colleague/neighbor relationship, the user node to be updated updates the fitness through the target user node based on the information propagation relationship established by the random user between the user node to be updated and the target user node; or alternatively, the process may be performed,
when the intimacy between the user node to be updated and the target user node is a stranger relationship, the user node to be updated updates the fitness through the release center node of the rumor-building information.
With reference to the second aspect of the present application, in a third possible implementation manner of the second aspect of the present application, the optimal fitness requirement is a preset fitness of a central node for distributing the ballad information.
In a fourth possible implementation manner of the second aspect of the present application in combination with the second aspect of the present application, the target rumor event is a rumor event having a long-time repeated continuous rumor requirement and issuing rumor information, or the target rumor event is a rumor event having a dispute or a different rumor conclusion, and issuing rumor information.
With reference to the second aspect of the present application, in a fifth possible implementation manner of the second aspect of the present application, the obtaining unit is specifically configured to:
acquiring account information disclosed by a user node in a target social platform;
and determining initial fitness and social relation according to the account information.
With reference to the second aspect of the present application, in a sixth possible implementation manner of the second aspect of the present application, the apparatus further includes a pushing unit, configured to:
pushing the rumor-forming information to the target user node according to the simulation result so as to perform rumor-forming processing on the target rumor event in the target social platform according to the simulation result.
In a third aspect, the application provides an analysis device for rumor events, comprising a processor for carrying out the steps of the first aspect or any implementation of the first aspect of the application described above when executing a computer program stored in a memory.
In a fourth aspect, the present application provides a readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the first aspect or any implementation of the first aspect of the present application described above.
From the above technical scheme, the application has the following advantages:
Before the target rumor event in a propagation state appears on the target social platform, the rumor creating process can be simulated through the SFLA algorithm and the PSO algorithm to analyze the rumor creating result of the target rumor event, social relation factors are introduced into the target social platform based on the clustering collaborative local searching capability of the SFLA algorithm and the rapid convergence of the PSO algorithm, the adaptability of each user individual to the rumor information is iteratively updated through the social relation factors in the rumor creating process for each user in the target social platform, and user nodes which are considered to exist fixedly and meet the optimal adaptability requirement are used as nodes for pushing the rumor information in each iteration process, so that iteration is ended when each user reaches the optimal adaptability, and continuous rumor creating simulation processing with smaller granularity and higher precision is completed. Therefore, related coping operations can be arranged for the target rumor event in the first time according to the simulation result, rumors can be effectively formed, and the problem of low efficiency obviously existing in the existing rumors forming mechanism is avoided.
Drawings
FIG. 1 is a flow chart of a method for analyzing rumor events according to the present application;
FIG. 2 shows a schematic view of a scenario of the present application;
FIG. 3 is a schematic diagram of a rumor event analyzer according to the present application;
fig. 4 is a schematic structural diagram of an analysis device for rumor events according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
In the description that follows, specific embodiments of the application will be described with reference to steps and symbols performed by one or more computers, unless otherwise indicated. Thus, these steps and operations will be referred to in several instances as being performed by a computer, which as referred to herein performs operations that include processing units by the computer that represent electronic signals that represent data in a structured form. This operation transforms the data or maintains it in place in the computer's memory system, which may reconfigure or otherwise alter the computer's operation in a manner well known to those skilled in the art. The data structure maintained by the data is the physical location of the memory, which has specific characteristics defined by the data format. However, the principles of the present application are described in the foregoing text and are not meant to be limiting, and one skilled in the art will recognize that various steps and operations described below may also be implemented in hardware.
The principles of the present application operate using many other general purpose or special purpose operations, communication environments, or configurations. Examples of computing systems, environments, and configurations that may be suitable for use with the application include, but are not limited to, hand-held telephones, personal computers, servers, multiprocessor systems, microcomputer-based systems, mainframe computers, and distributed computing environments that include any of the above systems or devices.
The terms "first," "second," and "third," etc. in this disclosure are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion.
The analysis method, the analysis device and the computer readable storage medium of the rumor event can be applied to analysis equipment of the rumor event, and are used for effectively analyzing the rumor event and obtaining the simulation result of the rumor simulation processing of the rumor event, so that related coping operations can be arranged on the rumor event within the first time according to the simulation result, and the rumor event can be effectively generated.
The analysis equipment of rumor events can be specifically a server, a physical host, a UE (user equipment) and other equipment, and can also exist in a mode of equipment cluster. The UE may be specifically a smart phone, a tablet computer, a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a desktop computer, a computer integrated machine, and other different types of terminal devices.
Next, the analysis method of rumor events provided by the present application will be described.
In a flow chart of the analysis method of rumor events according to the present application shown in fig. 1, the analysis method of rumor events according to the present application may specifically include the following steps:
step S101, determining that a target social platform with a target rumor event in a propagation state exists in a platform network;
step S102, obtaining user nodes in a target social platform, initial fitness of the user nodes to the ballad information and social relations of the user nodes, wherein the user nodes comprise infection nodes of target ballad events;
step S103, dividing the user nodes into a plurality of user sets as different frog populations formed by different frog individuals, and selecting target user nodes meeting the optimal adaptability requirement from each user set;
step S104, continuous rumor-creating simulation processing is carried out on a plurality of user sets through an SFLA algorithm and a PSO algorithm, and each iteration process of the continuous rumor-creating simulation processing comprises the following steps: pushing the rumor information to target user nodes, updating the fitness of each user node to the rumor information by combining with social relations, detecting whether each user node is updated to meet the optimal fitness requirement, and if so, meeting convergence criteria to complete continuous rumor simulation processing;
Step S105, obtaining simulation results of continuous rumor-creating simulation results.
In the embodiment shown in fig. 1, for the target rumor event in the propagation state, which occurs on the target social platform, before the target rumor event is processed, the rumor event can be simulated by using the SFLA algorithm and the PSO algorithm to analyze the rumor result of the target rumor event, and social relation factors are introduced in the clustering collaborative local search capability based on the SFLA algorithm and the rapid convergence of the PSO algorithm. Therefore, related coping operations can be arranged for the target rumor event in the first time according to the simulation result, rumors can be effectively formed, and the problem of low efficiency obviously existing in the existing rumors forming mechanism is avoided.
The steps of the embodiment shown in fig. 1 and the specific implementation that may be adopted in practical applications are specifically described below.
In the application, determining that a target social platform with a target rumor event in a propagation state exists can be understood as determining that the target rumor event exists first, at this time, determining which social platforms are not clear about which social platforms are propagating the target rumor event, and then determining the target social platform with the target rumor event in the propagation state in a platform network;
or, some specific social platforms can be monitored, for example, some social platforms with huge user quantity and high user liveness can be used as target social platforms, and whether rumor events in a propagation state exist in the platforms or not can be monitored.
In the present application, it is understood that, for the target rumor event, there is rumor information, or an event that has been proved to be a rumor event, and even if a certain transmitted event has been proved to be a rumor event, in the rumor mechanism of the prior art, rumor is difficult to complete in a short time due to limited rumor efficiency, rumor rate may be even slower than the transmission rate of the rumor event.
According to the rumor simulation processing of the application, after the target social platform of which the target rumor event is in a propagation state in the platform network is determined, the application can acquire the user nodes in the target social platform, wherein the nodes also comprise the infected nodes of which the target rumor event is infected, and can further acquire the initial fitness of each user node to the current target rumor event and the social relationship of each user node.
User nodes can be understood as user accounts corresponding one by one, real users correspond to the user accounts, and when user operations with identification properties such as comments, forwarding, collection and the like of target rumor events exist in the user accounts, the user accounts can be considered to be infected by the target rumor events and become infected nodes.
The initial fitness can be understood as the acceptance degree of the user node for the rumor information, and it can be understood that the rumor simulation process introduced by the application simulates the acceptance condition of each user for the rumor information, the fitness of the user is possibly changed in the simulation process, and when the fitness of all people has the best fitness requirement, accepts the rumor information and agrees with the content of the rumor information, the rumor simulation process of the rumor event can be considered as being completed, so that the user can be configured with the corresponding initial fitness before the rumor simulation process.
The initial fitness can be specifically configured by account operation habit of the user node, account corresponding mechanism and other factors. For example, for a related account number of a government agency, the initial fitness is better; or, for some related accounts with 'well known' labels, actively evaluating the actual matters on the target social platform, the related accounts can also have better initial fitness; for another example, for some related accounts where most of the individual user operations are forwarding entertainment eight diagrams, small messages, or there is a history of rumor information forwarding behavior, there is a poor initial fitness at which these accounts can be considered very vulnerable to the target rumor event.
Social relationships can be understood as correspondence between user nodes in information propagation. For example, different users have different social relationships, such as family, friends, colleagues, neighbors, strangers, etc., with different degrees of intimacy, and the node's own information absorbing capability to the outside is also different, e.g., although the user nodes A, B are family relationships with each other, the receiving situation of the user node a for the information transmitted by the user node B may be completely different from the receiving situation of the user node B for the information transmitted by the user node a.
The social relationship can be obtained from the account operation habit, the account basic information and other approaches of the user node. For example, user node X marks user node Y as a family in a buddy list; for another example, user node W forwards corporate industry dynamics to user node Q and reviews "we company further," when user nodes W, Q may be considered to be co-worker relationships with each other.
It should be understood that, in practical application, the above mentioned user node and its initial fitness, and the acquisition of social relationship are all processed based on the account information disclosed by the user node, or may also be processed from the account information disclosed by the user node for the rumor processing of the current target rumor on the premise of being allowed by the user for informing the requirement of the rumor processing of the target social platform.
Thus, in the present application, obtaining the initial fitness of the user node to the rumor formation and the social relationship of the user node includes:
acquiring account information disclosed by a user node in a target social platform;
and determining initial fitness and social relation according to the account information.
Of course, the information may also be historical configuration information, for example, obtained during the daylighting process of the historical rumor event; or, the information may be generated through a user questionnaire, and the specific acquisition mode of the information may be adjusted according to actual needs, which is not limited herein.
The continuous rumor-producing simulation process according to the present application is described below, and the following steps are specifically taken as follows: the SFLA algorithm and the PSO algorithm start.
The SFLA algorithm, frog-leaping algorithm, is a meta-heuristic algorithm, which can be understood as simulating the behavior of a group of frog in food searching, and can be used for performing intelligent heuristic searching in practical application to seek a solution to the combination optimization problem. Specifically, it is a decremental random search based algorithm that defines the initial population of frogs as the decision variable.
The PSO algorithm, particle swarm optimization algorithm, can be understood as a clustering behavior that mimics insects, herds, shoal and shoal, etc., which find food in a collaborative manner, each member of the population constantly changing its search pattern by learning its own experience and the experience of other members, in practice, by modifying the original version of PSO that was originally proposed by the simulation, and then describing the standard PSO algorithm with rapid convergence on the basis of inertial weights, which can search in a population manner.
On the one hand, the conventional SFLA algorithm is difficult to cover the actual situation, and on the other hand, the PSO algorithm may be in a locally optimal state for a long time or be converged to a globally optimal state for a long time. The application combines the two methods, has the cluster cooperation local search capability of SFLA and the rapid convergence of PSO algorithm, and improves the performance of the real-time and real-time ballad-avoiding algorithm.
Illustratively, in the continuous rumor simulation process, the analysis of rumors begins when rumors are entered into the network, where rumor infected population N is spread throughout the target social network, where rumor infected population may be divided into several (m) coordinates/similar clusters according to the characteristics of the family and community, where user (N) can learn autonomously to accept real-world, rumors from different information propagation paths. In each user cluster, users that may be infected or refuted by the rumor awareness of other users (e.g., moding in SFLA) may experience a true phase evolution regarding the refute of rumor events, meaning that when the user knows true phase from other users, the user may effectively reduce beliefs and anxiety associated with rumor events, increase the user's awareness of rumor events, and enhance the individual user's identifiable criteria for rumors, which is considered the user's fitness.
In order to ensure that the rumors are rejected more effectively and rapidly, the application can further require users with higher fitness to make a greater contribution to the development of new cognition from facts, namely, to the propagation of rumors information in a target social platform or user cluster.
In one scenario of the present application, as shown in fig. 2, the user node with the best fitness in these clusters may be selected as the target user node, denoted as the Cluster Head (CH), which may provide better cognition and rumination information for the Cluster Members (CM) in the same cluster. In the real-phase evolution process, the CM can improve its adaptability through the best rumor cognition from CH in the same cluster, and in this process, the CM can rotate around the social relationship of the user nodes. These clusters, which may be randomly partitioned; or dividing according to the number of the preset user nodes of the cluster; alternatively, the division may be performed centering on each infected user node; or, the method can also divide the target user nodes by taking each target user node as a center, and can be specifically adjusted according to actual needs.
The incremental change of the rumor cognition of the CM corresponds to the jumping step length of the frog, the new state (including the fitness of CH) is similar to the new position of the frog in the frog-jumping algorithm, after the single CM improves the state, the single CM returns to the cluster, and the rumor can be refuted immediately according to the information obtained from the CM state change, so that the instant access and update of the new information in the whole cluster are realized.
In the continuous rumor-forming simulation processing, on the basis of an initial allocation frog population (user set), a plurality of iterative processes are involved, in each iterative process, real-phase evolution is carried out according to social relations, the fitness of each user is updated, rumor-forming information is pushed to target user nodes which are considered to be fixedly existing and have the optimal fitness, so that the user nodes with the optimal rumor cognition continuously carry out real-phase propagation to other user nodes and perform rumor-forming, when the fitness of all user nodes is detected to be the optimal fitness in a certain iterative process, all users can be considered to complete real-phase cognition, rumor-forming processing is completed on target rumor events in a target social platform, convergence is finished at the moment, and a simulation result (iterative process) can be output for reducing the rumor-forming process for reference or application in practice.
For example, the rumor-seeking information may be pushed to the target user node according to the simulation result to seek rumor-seeking treatment for the target rumor event in the target social platform according to the simulation result.
Further, in practical applications, the social relationship of the user nodes may specifically include different affinities, self-reliability and credibility, where the affinities are used to indicate the affinities between the user nodes, the self-reliability is used to indicate the credibility of the user nodes for their own rumor distinguishing ability, the credibility is used to indicate the credibility between the user nodes, and the fitness may specifically be calculated according to the affinities, the self-reliability and the credibility.
Affinity, which is one of the main parameters representing the affinity between two users, is considered as a key factor in analyzing affinity. In general, high frequency contacts are used to reflect affinity, which means that the higher the frequency of contact between users, the tighter the affinity they establish. However, it may not be sufficient to establish true trust based on high frequency contacts such as colleague relationships, which high frequency contacts, multi-point communications and long-term collaboration do not make colleagues friends.
It should be noted that the degree of trust between any two users is not directly determined by the number of people they can directly contact, i.e. the relationship between two less acquainted individuals may also be closed, and thus, the dissemination of rumors involves a complex psychosocial process.
In particular, the application may also be used in practice to discuss deep contacts by analyzing various social relationships. There are four levels of affinity, including "most trusted", "more trusted", "generally trusted", and "untrusted" (defined as T 1 ，T 2 ，T 3 ，T 4 ). Considering the social affinity of users in a social platform, it can be assumed that 1>T 1 ≥0.75>T 2 ≥0.5>T 3 ≥0.25>T 4 0 so as to properly weight and adjust the affinity through deep contact. The application can start from measuring the affinity of urban population and introduce social relations such as family members, friends, colleagues/neighbors and strangers. Thus, the present application proposes family members >Friend(s)>Colleagues/neighbors>Strangers as a relational order with confidence, corresponding to T 1 >T 2 >T 3 >T 4 。
The affinity model between user node i and user node j may be built by combining high frequency and deep contacts, for example, as described by the following equation:
wherein I represents the affinity, h ij Is the number of contact frequencies, T K ij Representing user node i and useSocial relationship between user nodes j.
Self-reliability, an inherent attribute of each user node, represents the degree of trust due to good information dissemination capabilities. Based on past experience, it is believed that certain users will make more accurate decisions about the rumors in the social platform, and that the user will have a higher confidence in the distribution of those rumors, and that the user node will have a higher confidence and a higher self-reliability as the rumors flow around the social platform.
R= { Ri }, i=1, 2, …, N may be defined as the self-reliability of each user node.
The degree of reliability may be reflected by a certain probability between two user nodes. The confidence between strangers approaches zero, and they may increase after understanding each other and intimate contact. However, in various social relationships, there is no proportional relationship between intimacy and credibility. That is, despite frequent or deep contact between user nodes, it is not trusted, possibly due to low self-reliability of the user, insufficient trust, collision between two users, etc.
The whole online social network is in diffusion coupling, the rumor information can be propagated to the whole network, in the social relationship, the user node A can rumor the user node B through the rumor information, and the user node B can trust the user node A, which means that trust asymmetry can exist between two user node users, and the trust asymmetry can be described through a directed graph.
Essentially, the present application can combine (l) ij ) N×N 1.ltoreq.i, j.ltoreq.N as the Laplacian coupling matrix L, where the diagonal elements are considered to beIt represents the connection topology of the social relationship between user nodes, if there is a connection between user node i and user node j, lij= lji =1; otherwise lij= lji =0, define lii, the entire social receipt is connected, and matrix L is irreducible.
In addition, the Laplace coupling matrix L is weighted toEstablishing trust asymmetry, which can be converted into a confidence matrixWherein the sign is the Hadamard product (Hadamard product) of the matrix, matrix +.>Representing a trust asymmetry matrix, and c ij Then, based on the reputation of user node j for user node i, it is apparent that the confidence matrix is an asymmetric positive definite matrix, c ij ≠c ji ，i≠j.。
It should be noted that "stranger" users are generally considered as non-connected users, as previously described, there are l ij ＝l ji =0. However, due to the closeness of the analysis, there is a social relationship T 4 Can be limited in scope by the "stranger" user of [ 0.0.25), which is considered to be an accurate description of the current connection topology.
In the application, the social relationship of the user node can specifically comprise different affinities, self-reliability and credibility, and furthermore, the application can also introduce the factor of the credibility on the basis of the three factors, wherein the credibility is used for representing the social relationship consisting of the affinities, the self-reliability and the credibility on the whole level, and can be recorded as follows:
further, in the iteration process of continuous rumor simulation processing, the center node for distributing rumor information can update the fitness of each target user node (CH) (the user node which is fixed by default and meets the requirement of optimal fitness) in each iteration process, and the update of the fitness can be referred to as follows:
wherein v is k+1 i Is the speed of increasing the speed, the user node i is in the kth and (k+1) th iterations, f k,best i Is the target user node (CH), f with the best fitness at the kth iteration k+1,best i Is the target user node (CH) with the optimal fitness at the k+1st iteration, f is the preset fitness of the center node for the release of the balling information, xi 1 Is [0,1 ]]Random values within the range. It is worth mentioning here that it is preferable to update f in each iteration k i To achieve the applicability of rumor refute centers.
Taking family membership, friend relationship, colleague/neighbor relationship and stranger relationship as examples, updating the fitness of the user node to be updated according to the social relationship, which can be specifically the following four cases:
1. when the intimacy between the user node to be updated and the target user node for transmitting the rumor creating information to the user node to be updated is a family relationship, the user node to be updated updates the fitness through the target user node;
on the premise that the user node meeting the best fitness requirement is considered to be a fixed presence, the "family member" user node may more fully trust the target user node (CH) in the cluster, as the "family member" user node is considered to be a fixed branch of best fitness in the iteration. Thus, their suitability at (k+1) th iteration may be assigned by the target user node (CH) at the kth iteration, the update of its suitability may be referred to as:
due to the clear trust of the target user node (CH), the user node of the family member can quickly enhance the adaptability of the user node, and meanwhile, the adaptability of the target user node (CH) is continuously close to the preset adaptability f of the central node for the release of the breast cancer information.
2. When the affinity between the user node to be updated and the target user node is a friend relationship, the user node to be updated updates the fitness through the release center node of the ballad information or the target user node;
the continuous true phase propagation allows the "friend" user node to receive the true phase from the central node of the release of the ballad information, and thus, the adaptability and speed of the target user node (CH) can be adjusted based on its adaptability to the central node of the release of the ballad information, and the updating of the adaptability can be referred to as:
wherein T is 2 And T 3 Is a positive constant within [0.5,0.75 ] of the trust level T2 representing the family member of user node i, ζ 2 And xi 3 Is [0,1 ]]Random values within the range.
3. When the intimacy between the user node to be updated and the target user node is a colleague/neighbor relationship, the user node to be updated updates the fitness through the target user node based on the information propagation relationship established by the random user between the user node to be updated and the target user node;
the "colleague/neighbor" relationship is considered to be a common and necessary social relationship for each user node. In general, "colleague/neighbor" users having such a relationship with the target user node (CH) may not be open to their colleagues or neighbors, which also results in limited interaction with each other. Due to the low affinity of the "colleague/neighbor" relationship, conventional PSO algorithms are not sufficient to effectively reject the rumors.
Thus, the "colleague/neighbor" user is aided with a random user to enhance its fitness to approach the fitness of the target user node (CH), the random user providing a novel relationship for the "colleague/neighbor" user and the target user node (CH), one iteration comprising two steps: 1) The adaptation of random users to the target user node (CH); 2) The "colleague/neighbor" user may increase its fitness according to the fitness of the random user.
A "family member" or "friend" relationship between three users with a probability of occurrence of 50% can increase the rate of improvement in fitness, while a "stranger" relationship with a probability of occurrence of 25% may decrease the rate of improvement. Specifically, the updating of the adaptability can be referred to as follows:
wherein T is 4 And T 5 Is representative of the trust level, T, of the family members of the user node i 4 And T 5 In [0.25, 0.5) ] 4 And xi 5 Is in [0,1 ]]Random values in the range, the equation describes "colleague/neighbor" users that have been refined twice based on random users and iteratively strong users.
4. When the intimacy between the user node to be updated and the target user node is a stranger relationship, the user node to be updated updates the fitness through the release center node of the rumor-building information.
In a social platform, there are a number of isolated "stranger" users without any social relationship with other user nodes. The fact of finding a user varies due to the low trust of the user in the cluster. The application provides a distributing center node of the rumor-forming information, which directly transmits the true phase (rumor-forming information) to a stranger user based on SFLA. Thus, for a "stranger" user, the update of its fitness can be referred to:
wherein, xi 6 Is [0,1 ]]Random value of v M Is the maximum increment in fitness.
Further, in practical application, the optimal fitness requirement related in the continuous rumor-forming simulation processing may be a fitness threshold configured according to practical needs, where preferably, the preset fitness of the center node for distributing rumor-forming information may be selected as the fitness threshold, that is, the optimal fitness requirement, so when all user nodes in the target social platform complete real-phase evolution and complete rumor-forming, the fitness of each user node greatly tends to or equals to the preset fitness of the center node for distributing rumor-forming.
Further, in the present application, the target user node is considered as a user node that is fixedly present and always meets the requirement of optimal fitness, and accordingly, in practical application, the rumor event with more than one message needs to be updated for a long time, and is continuously rejected and ruminated in the social platform, for example, rumors related to health are easily propagated repeatedly and repeatedly, and therefore, rumors are also required to be repeatedly and repeatedly generated. In order to correct such rumors and to continuously propagate true phase, establishing a fixed branch of each branch of the anti-rumor centre is critical for long-term maintenance rumor anti-refuting, so that there is also the meaning of setting up fixed target user nodes, the target user node (CH) with the best adaptability to the fixed branch, i.e. all target user nodes (CH), will remain in each iteration of the continuous rumor simulation process.
In other words, the target rumor event is specifically a rumor event having a long-time repeated continuous rumor demand and issuing rumor information, or a rumor event having a dispute or a different rumor conclusion, and issuing rumor information.
The above is an explanation of the analysis method of rumor events provided by the present application, and in order to facilitate better implementation of the analysis method of rumor events provided by the present application, the present application further provides an analysis device of rumor events.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an analysis device for rumor events according to the present application, in which the analysis device 300 for rumor events may specifically include the following structure:
a determining unit 301, configured to determine that a target social platform in which a target rumor event is in a propagation state exists in a platform network;
the obtaining unit 302 is configured to obtain a user node in the target social platform, an initial fitness of the user node to the ballad information, and a social relationship of the user node, where the user node includes an infection node of the target ballad event;
a dividing unit 303, configured to divide the user node into a plurality of user sets, as different frog populations formed by different frog individuals;
A selecting unit 304, configured to select a target user node meeting the requirement of optimal fitness from each user set;
the simulation unit 305 is configured to perform continuous rumor-creating simulation on the plurality of user sets through SFLA algorithm and PSO algorithm, where each iteration process of the continuous rumor-creating simulation includes: pushing the rumor information to target user nodes, updating the fitness of each user node to the rumor information by combining with social relations, detecting whether each user node is updated to meet the optimal fitness requirement, and if so, meeting convergence criteria to complete continuous rumor simulation processing;
the obtaining unit 302 is further configured to obtain a simulation result of the continuous rumor-forming simulation process.
In one exemplary implementation, the social relationship includes different affinities for indicating the degree of affinity between user nodes, self-reliability for indicating the degree of trust of the user nodes for their own rumor discrimination ability, and credibility for indicating the degree of trust between the user nodes, the fitness being calculated from the affinities, self-reliability, and credibility.
In yet another exemplary implementation, the affinity includes family membership, friendship, colleague/neighbor relationship, stranger relationship, and when the affinity between the user node to be updated and the target user node that propagates the rumor information to the user node to be updated is family relationship, the user node to be updated updates the fitness through the target user node; or alternatively, the process may be performed,
When the affinity between the user node to be updated and the target user node is a friend relationship, the user node to be updated updates the fitness through the release center node of the ballad information or the target user node; or alternatively, the process may be performed,
when the intimacy between the user node to be updated and the target user node is a colleague/neighbor relationship, the user node to be updated updates the fitness through the target user node based on the information propagation relationship established by the random user between the user node to be updated and the target user node; or alternatively, the process may be performed,
when the intimacy between the user node to be updated and the target user node is a stranger relationship, the user node to be updated updates the fitness through the release center node of the rumor-building information.
In yet another exemplary implementation, the optimal fitness requirement is a preset fitness of the central node for the release of the ballad information.
In yet another exemplary implementation, the target rumor event is a rumor event having a long-term repetition of continuous rumor demand and release rumor information, or the target rumor event is a rumor event in which a dispute exists or a different rumor conclusion exists, and rumor information is released.
In yet another exemplary implementation, the obtaining unit 302 is specifically configured to:
Acquiring account information disclosed by a user node in a target social platform;
and determining initial fitness and social relation according to the account information.
In yet another exemplary implementation, the apparatus further includes a pushing unit 306 configured to:
pushing the rumor-forming information to the target user node according to the simulation result so as to perform rumor-forming processing on the target rumor event in the target social platform according to the simulation result.
The present application also provides a rumor event analysis device, referring to fig. 4, fig. 4 shows a schematic structural diagram of a rumor event analysis device according to the present application, specifically, the rumor event analysis device according to the present application includes a processor 401, a memory 402, and an input/output device 403, where the processor 401 is configured to implement steps of the rumor event analysis method according to the corresponding embodiment of fig. 1 when executing a computer program stored in the memory 402; alternatively, the processor 401 may be configured to implement the functions of the units in the corresponding embodiment as shown in fig. 3 when executing the computer program stored in the memory 402.
By way of example, a computer program may be partitioned into one or more modules/units that are stored in the memory 402 and executed by the processor 401 to perform the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing particular functions to describe the execution of the computer program in a computer device.
Analysis devices for rumor events may include, but are not limited to, processor 401, memory 402, input output device 403. It will be appreciated by those skilled in the art that the illustration is merely an example of an analysis device for a rumor event and does not constitute a limitation of the analysis device for a rumor event, and may include more or less components than illustrated, or may be combined with certain components, or different components, e.g., the analysis device for a rumor event may further include a network access device, a bus, etc., through which the processor 401, the memory 402, the input output device 403, and the network access device, etc., are connected.
The processor 401 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor being the control center of the rumor event analysis device, with various interfaces and lines connecting the various parts of the overall device.
The memory 402 may be used to store computer programs and/or modules, and the processor 401 may implement various functions of the computer device by executing or executing the computer programs and/or modules stored in the memory 402, and invoking data stored in the memory 402. The memory 402 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, application programs required for at least one function, and the like; the storage data area may store data created from the use of analysis devices for rumor events, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
The processor 401 may be used to execute the computer program stored in the memory 402, and may specifically implement the following functions:
determining that a target social platform with a target rumor event in a propagation state exists in a platform network;
acquiring user nodes in a target social platform, initial fitness of the user nodes to the rumor-forming information and social relations of the user nodes, wherein the user nodes comprise infection nodes of target rumor events;
Dividing the user nodes into a plurality of user sets as different frog populations formed by different frog individuals, and selecting target user nodes meeting the optimal adaptability requirement from each user set;
continuous daylighting simulation processing is carried out on a plurality of user sets through an SFLA algorithm and a PSO algorithm, and each iteration process of the continuous daylighting simulation processing comprises the following steps: pushing the rumor information to target user nodes, updating the fitness of each user node to the rumor information by combining with social relations, detecting whether each user node is updated to meet the optimal fitness requirement, and if so, meeting convergence criteria to complete continuous rumor simulation processing;
and obtaining simulation results of continuous rumor simulation processing.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the detailed working process of the rumor event analysis device, apparatus and corresponding units described above may refer to the description of the rumor event analysis method in the corresponding embodiment of fig. 1, and will not be repeated here.
Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.
For this reason, the present application provides a computer readable storage medium, in which a plurality of instructions capable of being loaded by a processor are stored, so as to execute the steps in the method for analyzing rumor events according to the corresponding embodiment of fig. 1, and the specific operation may refer to the description of the method for analyzing rumor events according to the corresponding embodiment of fig. 1, which is not repeated herein.
Wherein the computer-readable storage medium may comprise: read Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic or optical disk, and the like.
Since the instructions stored in the computer readable storage medium may perform the steps in the method for analyzing rumor events according to the embodiment of fig. 1, the beneficial effects of the method for analyzing rumor events according to the embodiment of fig. 1 may be achieved, which are detailed in the foregoing description and are not repeated herein.
The foregoing has outlined the detailed description of the method, apparatus, device and computer readable storage medium for analyzing rumor events of the present application, wherein specific examples are provided herein to illustrate the principles and embodiments of the present application, and the above examples are provided to assist in understanding the method and core concepts of the present application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, the present description should not be construed as limiting the present application.
Claims (3)
1. A method of analyzing rumor events, the method comprising:
determining that a target social platform with a target rumor event in a propagation state exists in a platform network;
acquiring user nodes in the target social platform, initial fitness of the user nodes to the ballad information and social relations of the user nodes, wherein the user nodes comprise infection nodes of the target ballad event;
dividing the user nodes into a plurality of user sets as different frog populations formed by different frog individuals, and selecting target user nodes meeting the optimal adaptability requirement from each user set;
and performing continuous rumination simulation processing on a plurality of user sets through a frog-leaping algorithm and a particle swarm optimization algorithm, wherein each iteration process of the continuous rumination simulation processing comprises the following steps: pushing the balling information to the target user nodes, updating the fitness of each user node to the balling information in combination with the social relationship, detecting whether each user node is updated to meet the optimal fitness requirement, and if so, meeting convergence criteria to complete the continuous balling simulation processing;
Obtaining a simulation result of the continuous rumor-avoiding simulation processing;
the social relationship comprises different affinities, self-reliability and credibility, wherein the affinities are used for indicating the affinities among the user nodes, the self-reliability is used for indicating the credibility of the user nodes for own rumor distinguishing capability, the credibility is used for indicating the credibility among the user nodes, and the adaption is calculated according to the affinities, the self-reliability and the credibility;
the affinity comprises family membership, friend relationship, colleague/neighbor relationship and stranger relationship, and when the affinity between a user node to be updated and a target user node for transmitting the breast-call information to the user node to be updated is family relationship, the user node to be updated updates the fitness through the target user node; or when the affinity between the user node to be updated and the target user node is a friend relationship, the user node to be updated updates the fitness through the release center node of the balling information or the target user node; or when the intimacy between the user node to be updated and the target user node is a colleague/neighbor relationship, the user node to be updated updates the fitness through the target user node based on an information propagation relationship established by a random user between the user node to be updated and the target user node; or when the intimacy between the user node to be updated and the target user node is a stranger relationship, the user node to be updated updates the fitness through the release center node of the rumor-free information;
The optimal fitness requirement is the preset fitness of the node of the center for issuing the balling information;
the target rumor event is a rumor event with long-time repeated continuous rumor-avoiding requirement and issuing the rumor-avoiding information, or the target rumor event is a rumor event with disputes or different rumor-avoiding conclusions and issuing the rumor-avoiding information;
the obtaining the initial fitness of the user node to the rumor formation information and the social relationship of the user node comprises the following steps: acquiring account information disclosed by the user node in the target social platform, and determining the initial fitness and the social relationship according to the account information;
after obtaining the simulation result of the continuous rumor-creating simulation process, the method further comprises: pushing the balling information to the target user node according to the simulation result, so as to carry out balling treatment on the target balling event in the target social platform according to the simulation result.
2. An analysis device for rumor events, comprising a processor and a memory, the memory having a computer program stored therein, the processor executing the method of claim 1 when calling the computer program in the memory.
3. A computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011241201.2A CN112396150B (en) | 2020-11-09 | 2020-11-09 | Rumor event analysis method, rumor event analysis device, rumor event analysis equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011241201.2A CN112396150B (en) | 2020-11-09 | 2020-11-09 | Rumor event analysis method, rumor event analysis device, rumor event analysis equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112396150A CN112396150A (en) | 2021-02-23 |
| CN112396150B true CN112396150B (en) | 2023-09-26 |
Family
ID=74600069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011241201.2A Active CN112396150B (en) | 2020-11-09 | 2020-11-09 | Rumor event analysis method, rumor event analysis device, rumor event analysis equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112396150B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107895010A (en) * | 2017-11-13 | 2018-04-10 | 华东师范大学 | A kind of method that detection network navy is thumbed up based on network |
| CN108304521A (en) * | 2018-01-25 | 2018-07-20 | 重庆邮电大学 | The analysis method and system of microblogging gossip propagation based on evolutionary Game |
| CN110008975A (en) * | 2018-11-30 | 2019-07-12 | 武汉科技大学 | Social networks navy detection method based on Danger Immune theory |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150188941A1 (en) * | 2013-12-26 | 2015-07-02 | Telefonica Digital Espana, S.L.U. | Method and system for predicting victim users and detecting fake user accounts in online social networks |
-
2020
- 2020-11-09 CN CN202011241201.2A patent/CN112396150B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107895010A (en) * | 2017-11-13 | 2018-04-10 | 华东师范大学 | A kind of method that detection network navy is thumbed up based on network |
| CN108304521A (en) * | 2018-01-25 | 2018-07-20 | 重庆邮电大学 | The analysis method and system of microblogging gossip propagation based on evolutionary Game |
| CN110008975A (en) * | 2018-11-30 | 2019-07-12 | 武汉科技大学 | Social networks navy detection method based on Danger Immune theory |
Non-Patent Citations (2)
| Title |
|---|
| 基于PSO-SVM算法的炒作微博识别研究;王恩贤;陶宏才;;成都信息工程学院学报(第06期);全文 * |
| 群智能算法优化支持向量机参数综述;李素;袁志高;王聪;陈天恩;郭兆春;;智能系统学报(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112396150A (en) | 2021-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104717124B (en) | A kind of friend recommendation method, apparatus and server | |
| CN111222029B (en) | Method for selecting key nodes in network public opinion information dissemination | |
| Zhang et al. | Understanding crowd-powered search groups: a social network perspective | |
| Graham et al. | Do socialbots dream of popping the filter bubble? The role of socialbots in promoting deliberative democracy in social media | |
| CN110781411B (en) | Rumor propagation control method based on rumor splitting message | |
| Beskow et al. | Agent based simulation of bot disinformation maneuvers in Twitter | |
| Bhowmick et al. | Temporal sequence of retweets help to detect influential nodes in social networks | |
| Zhao et al. | Competitive dynamics on complex networks | |
| Welles et al. | The Oxford handbook of networked communication | |
| Chen et al. | Understanding the user behavior of foursquare: A data-driven study on a global scale | |
| Shi et al. | Event detection and multi-source propagation for online social network management | |
| CN112396151B (en) | Rumor event analysis method, rumor event analysis device, rumor event analysis equipment and computer readable storage medium | |
| Wang et al. | Exploring the construction and infiltration strategies of social bots in sina microblog | |
| Liu et al. | A multi-granularity collective behavior analysis approach for online social networks | |
| CN112052399B (en) | Data processing method, device and computer readable storage medium | |
| Liu et al. | Nonlinear dynamic information propagation mathematic modeling and analysis based on microblog social network | |
| CN112396150B (en) | Rumor event analysis method, rumor event analysis device, rumor event analysis equipment and computer readable storage medium | |
| CN111966920A (en) | Public opinion propagation stable condition prediction method, device and equipment | |
| Dergacheva et al. | Government’s echo. Twitter discussions around news topics in Russian networked authoritarianism | |
| CN114928548B (en) | Social network information propagation scale prediction method and device | |
| CN110990706A (en) | Corpus recommendation method and apparatus | |
| CN115018333A (en) | Digital operation management method and system for industrial park | |
| CN113658015A (en) | Analysis method for influencing information propagation by position and intervention time of intervention information | |
| Sandim et al. | The Role of Social Capital in Information Diffusion over Twitter: A Study Case over Brazilian Posts. | |
| CN109669956B (en) | Memory, user relationship determination method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |