CN111861122A - Social network information credibility evaluation method based on propagation attribute similarity - Google Patents
Social network information credibility evaluation method based on propagation attribute similarity Download PDFInfo
- Publication number
- CN111861122A CN111861122A CN202010558019.3A CN202010558019A CN111861122A CN 111861122 A CN111861122 A CN 111861122A CN 202010558019 A CN202010558019 A CN 202010558019A CN 111861122 A CN111861122 A CN 111861122A
- Authority
- CN
- China
- Prior art keywords
- information
- propagation
- social network
- event
- history
- 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.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 80
- 230000005540 biological transmission Effects 0.000 claims abstract description 29
- 239000010410 layer Substances 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 12
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 11
- 230000001902 propagating effect Effects 0.000 claims description 10
- 230000006855 networking Effects 0.000 claims description 8
- 230000000644 propagated effect Effects 0.000 claims description 4
- 230000000977 initiatory effect Effects 0.000 claims description 3
- 239000011229 interlayer Substances 0.000 claims description 3
- 240000002234 Allium sativum Species 0.000 description 9
- 235000004611 garlic Nutrition 0.000 description 9
- 241000711573 Coronaviridae Species 0.000 description 7
- 230000007547 defect Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000007480 spreading Effects 0.000 description 3
- 241000700605 Viruses Species 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000034994 death Effects 0.000 description 1
- 231100000517 death Toxicity 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 235000019633 pungent taste Nutrition 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a social network information credibility evaluation method based on propagation attribute similarity, which comprises the following steps: step A: extracting social network information propagation content and constructing a social network information propagation network; and B: extracting attributes of social network information transmission nodes, calculating topological attributes of social network information transmission networks, marking the reliability of historical information, and establishing a historical information transmission attribute database; and C: calculating the propagation attribute similarity of the target social network and the historical social network so as to evaluate the information credibility of the target social network; through the steps, the purpose of evaluating the credibility of the social network information based on the similarity of the propagation attributes can be achieved, the method is strong in integrity, high in objectivity and good in universality, and the problem that the credibility of the social network information is difficult to objectively measure and evaluate is solved.
Description
Technical Field
The invention provides a social network information credibility assessment method based on propagation attribute similarity, and relates to the technical fields of network science, social network analysis and the like.
Background
Social networking information refers narrowly to information that is traceable, causes dissemination, and has some impact on society within a social networking environment for a certain period of time. Hot news, hot topics, dispute events, etc. are social network information that is common in social networks.
With the development of information technology and the emergence of new network media, social network information is spread faster and faster, the spreading scale is increased, and the spreading content has an increasing influence with the increase of the spreading hierarchy. For example, when facing a serious disaster event, people can quickly and accurately transmit social network information related to disaster situations through various social network platforms such as microblogs and the like to form hot news and disclose dispute events such as 'disaster relief measures are timely or not', so that governments and people can be promoted to take rescue measures better and faster; however, there are unrealistic information and rumors in social network information, such as dispute events and information related to pseudo-science and religious confusion, and these contents lack credibility, if widely spread in social network, may cause panic of the masses and even affect social stability. Therefore, how to evaluate the credibility of one piece of social network information becomes a problem of important research in all circles of society.
The social network information with higher credibility is generally information publishing organizations or individuals after social certification, so that the social network information can timely transmit real event conditions and timely announce or convey precious information and knowledge for people who have needs in all social boundaries. Social network information lacking credibility generally exists in a form of being "corrupt", the propagation range of the social network information is more dispersed and uncertain compared with social network information with higher credibility, and propagation groups are difficult to distinguish, so that the visual lines of the masses can be mixed on the social network, and the incredible information is also widely propagated.
Because the universality of social network information lacking in credibility and the loss caused by the social network information bring great influence to the life of people and even social operation, accurate credibility evaluation and judgment of the social network information by adopting a scientific and reasonable method are necessary. In the process of evaluating the credibility of the information, various evaluation methods can be adopted, including a credibility evaluation method based on the attributes of the information publisher such as authority, influence, activity degree, social relationship and the like, a credibility evaluation method based on the attributes of the information content such as information integrity, language analysis, content position judgment and the like, and a credibility evaluation method based on the macroscopic characteristics of time and quantity of information publishing. And how to quickly evaluate the credibility of the information through the propagation characteristics of the information is the key point of the invention.
Most of the existing methods are credibility assessment methods based on publisher attributes, information content attributes, or macroscopic attributes such as information time and quantity, or a large amount of manpower and material resources are needed to be consumed to collect and judge the assessed specific social network information attributes, so that the propagation attributes of the information are rarely researched and utilized, and the credibility assessment of the social network information is not carried out with reference to the historical information propagation attributes. Therefore, although the method can perform quantitative or qualitative evaluation on the credibility of specific social network information, the method cannot accurately grasp the significant and fundamental differences in the propagation characteristics of credible and unreliable information in the social network, so that the method has poor universality, low universal interpretability and huge manpower and time cost consumption. The research shows that social network information with similar credibility has obvious propagation attribute similarity, while social network information with different credibility has obvious difference between propagation structure attributes, and the difference is not changed due to the difference of the specific content of the information.
The method comprises the steps of firstly extracting a certain amount of propagation attributes of historical information and target social network information, wherein the propagation attributes comprise a propagator attribute and a propagation network structure, constructing an information propagation network by taking propagators as nodes and taking information forwarding relations as directed edges, carrying out propagation attribute calculation on the target social network information, calculating the similarity between the target information and the propagation attributes of the historical information by comparing the target information with an existing information propagation network database, and evaluating the credibility of the target social network information by comparing the similarity with the credibility of the historical information through similarity weighting.
According to the method, the reliability of the social network information is calculated and analyzed by introducing the propagation attribute characteristics, the reliability of the target social network information can be reasonably evaluated by considering the historical reliability and the propagation attribute characteristics of the social network information, and the method has good universality and innovativeness. A social network information credibility assessment method based on propagation attribute similarity is provided based on the method foundation and the practical significance.
Disclosure of Invention
Objects of the invention
The method is mainly used for solving the problem of information credibility evaluation under the background of social network platform propagation of unverified mass information. Most of the existing methods are credibility assessment methods based on publisher attributes, information content attributes, or macroscopic attributes such as information time and quantity, or a large amount of manpower and material resources are needed to be consumed to collect and judge the assessed specific social network information attributes, so that the propagation attributes of the information are rarely researched and utilized, and credibility assessment is not carried out on the social network information with reference to historical information propagation attributes. Therefore, aiming at the defects of the existing method, the method realizes the credibility evaluation of the social network information based on the similarity of the propagation attributes from the perspective of the propagation path.
By using the method, the propagation node attribute and the propagation structure attribute of the information in the social network environment are extracted, the propagation characteristic of the information and the historical information are reasonably calculated and compared to establish the credibility assessment method of the social network information, and then the credibility assessment aiming at the target information can be realized, so that a solid foundation is provided for monitoring intensity adjustment and public opinion grade assessment of the social network information and investigation and declaration of target events as necessary.
(II) technical scheme
In order to achieve the purpose, the method adopts the technical scheme that: a social network information credibility assessment method based on propagation attribute similarity is disclosed.
The method for evaluating the credibility of the social network information based on the propagation attribute similarity is an idea of applying complex network modeling, wherein a network is established by taking a forwarding relation of the social network information such as hot news, hot topics, dispute events and the like and a propagator as a connecting edge and a node in a social network platform, a historical social network information database is further established, and then the similarity between target social network information to be evaluated (such as specific hot news) and the propagation attribute of each historical social network information propagation network is extracted, so that the credibility of the social network information is measured and evaluated.
The invention relates to a social network information credibility assessment method based on propagation attribute similarity, which comprises the following steps:
step A: extracting social network information propagation content and constructing a social network information propagation network;
and B: extracting attributes of social network information transmission nodes, calculating topological attributes of social network information transmission networks, marking the reliability of historical information, and establishing a historical information transmission attribute database;
and C: and calculating the propagation attribute similarity of the target social network information and the historical social network information so as to evaluate the information credibility of the target social network.
Through the steps, the purpose of evaluating the credibility of the social network information based on the similarity of the propagation attributes can be achieved, the method is strong in integrity, high in objectivity and good in universality, and the problem that the credibility of the social network information is difficult to objectively measure and evaluate is solved.
Wherein, the step A of extracting the social network information propagation content and constructing the social network information propagation network comprises the following steps: selecting an information publisher as an initial propagation node for a given amount of historical social network information and target social network information with historical information credibility, and constructing a propagation network of the information according to the direct forwarding node and the direct forwarding directed relation of the initial propagation node; the specific steps of the process are as follows:
Step A1: according to the public content of the social network platform, a publisher of a certain social network information Event (which can be a hot topic, hot news, a dispute Event and the like) is selected as an initial propagation node V00The direct forwarder to the initial node is taken as the lower node V0jLooking at the direct forwarding relationship between the initial node and each lower-level node, propagating as social network information, directed connecting edges E0(V00,V0j) Building a first layer information propagation network G0(V0,E0) Wherein
In the formula: v0Representing an initial propagation node V00With a direct forwarder node V to the initiating node0jSet of nodes of, E0Representing an initial propagation node V00With its direct forwarder node V0jThe forwarding relation between the two is connected with the edge set;
step A2: setting a threshold value L of the number of the information transmission network levels, traversing each forwarding node of each layer, regarding the forwarding node as each initial node of the layer, repeating the step A1, and constructing the information transmission network between layers layer by layer until the transmission level reaches the threshold value to obtain an integral transmission network G (V, E) of the social network information Event; in the formula: g (V, E) represents the overall propagation network of the social network information Event, V represents a node set in the network, and E represents a node forwarding relation in the network;
Step A3: repeating the steps A1 and A2 for a given number Num of historical social network information eventshistoryEstablishing respective information propagation networks Ghistory(Vhistory,Ehistory) Establishing a target social network information EventobjInformation dissemination network Gobj(Vobj,Eobj) (ii) a In the formula: ghistory(Vhistory,Ehistory) Representing historical social network information eventshistoryOf the information dissemination network, VhistoryRepresenting a set of nodes in the network, EhistoryRepresents a node forwarding relationship in the network, and Gobj(Vobj,Eobj) Watch (A)Targeting social network information EventobjOf the information dissemination network, VobjRepresenting a set of nodes in the network, EobjRepresenting node forwarding relationships in the network.
The method for extracting the social network information propagation node attributes, calculating the social network information propagation network topology attributes, marking the reliability of the historical information and establishing the historical information propagation attribute database in the step B comprises the following steps: extracting propagation nodes and propagation topological structure attributes in the constructed social network information propagation network, then marking the credibility of each historical social network information, and establishing a historical social network information propagation attribute database; the specific steps of the process are as follows:
step B1: extracting the unique identification information of each propagation node V in the constructed social network information propagation network G (V, E) as the propagation node attribute F of the information vec；
Step B2: extracting the network topology structure of the constructed social network information propagation network G (V, E), and extracting the network propagation structure attribute FstrucIncluding, but not limited to:
(1) propagation network G (V, E) initial forwarding level number ratio r2/1(equation (1)), i.e., the number of layer 2 propagation network nodes nV(2) Number n of network nodes propagated from layer 1V(1) The ratio of (A) to (B);
(2) the characteristic distance a of the nodes of the propagation network G (V, E), namely the distance distribution between all node pairs in the fitting propagation network, is shown in the formula (2), wherein y is the distribution probability, x is the spacing distance of the node pairs, and b is a fitting constant;
(3) the homogeneity index H of the propagation network G (V, E), i.e. the homogeneity H of the propagation network G (V, E)GHomogeneity with same-scale star network HstarThe calculation method is shown as formula (3), wherein the homogeneity calculation method of the propagation network is shown as formula (4);
h＝log(Hstar)-log(HG)(3)
Step B3: setting historical social network information Event according to historical fact summary and authority authenticationhistoryEvaluation index of reliability of
Wherein the value 0 represents that the information is completely untrustworthy, the value 1 represents that the information is completely credible, and historical social network information Event is set historyPropagation node reliability evaluation index creditabilityvec(Eventhistory) Propagation topology reliability evaluation index creditabilitystruc(Eventhistory) The evaluation index is the same as the comprehensive credibility evaluation index;
step B4: for Num historical social network information Event collectedhistoryPropagating the historical information to node attributes Fvec(Eventhistory) Historical information propagation network structure attribute Fstruc(Eventhistory) Historical information reliability index creditability (Event)history) Joining a historical social network information dissemination Attribute database DS (Event)history)。
Wherein, the step C of calculating the propagation attribute similarity between the target social network information and the historical social network information to evaluate the information reliability of the target social network includes the following specific steps: computing target social network information EventobjEvent with historical social network informationhistorySpreading node similarity SimvecAnd obtaining target social network information EventobjPropagation node trustworthiness creditability ofvec(Eventobj) Then calculateTargeted social networking information EventobjEvent with historical social network informationhistoryThe propagation structure similarity is divided into bits, and further the propagation structure Credibility creditability is obtainedstruc(Eventobj) Distributing each propagation attribute reliability calculation weight, and calculating the reliability of the target social network information; the specific steps of the process are as follows:
Step C1: respectively calculating target social network information Event by adopting an aggregate similarity calculation method such as the Jaccard similarity method (formula (5))objWith the historical information dissemination attribute database DS (Event)history) All historical information Event inhistoryThe propagation node attribute similarity Simvec(Eventobj,Eventhistory) Then selecting the maximum propagation node attribute similarity value Sim in the calculation resultvec_maxAnd corresponding historical information Eventvec_maxRecording the reliability creditability of the corresponding history informationvec(Eventvec_max) Then target social networking information EventobjPropagation node trustworthiness creditability ofvec(Eventobj)＝Simvec_max×Credibilityvec(Eventvec_max)；
In the formula: fvec(Eventobj) Representing target information dissemination node attributes, Fvec(Eventhistory) Representing historical information dissemination node attributes;
step C2: propagating an attribute database DS (Event) to historical informationhistory) In each historical information EventhistoryBased on the propagation structure property FstrucM sub-attributes (including and not limited to r)2/1And a, h) are respectively sorted according to the same sorting mode (ascending or descending), and M historical information sequences are obtained after sorting:
step C3: for the ith rearranged history information sequence obtained by C2, dividing the history information into K intervals by equal amount, and each interval has
History information, and then comparing the i-th propagation structure sub-attribute value of the target social network information with each history information Event in the i-th rearranged history information sequence historyFinding the most similar historical information EventhistoryAnd the section number k to which it belongsstruc_iTargeting social network information eventsobjThe similarity of the propagation structure sub-attribute is divided into bits, and the step is repeated for i 1,2objDividing the similarity of each propagation structure sub-attribute into bits;
step C4: calculating target social network information Event according to formula (6)objEvent with historical social network informationhistoryPropagation structure sub-attribute reliability creditability of (1)struc_iWhere i is the ith of the M propagation structure sub-attributes,
respectively target social network information EventobjThe sub-attribute of the propagation structure to which it belongs is divided into kiIn the history information Event with reliability of 0 and 1historyThe number of the cells;
step C5: confidence creditability for propagating nodesvecM propagation structure sub-attribute Credibility creditabilitystruc_iI 1.. M assigns a calculation weight wvec,wstruc_1,...,wstruc_MWherein the sum of all weights is equal to 1, the distribution method can adopt an average distribution method, an analytic hierarchy process, a fuzzy evaluation method and the like, and the distribution is carried out according to the weight importance or other necessary information;
step C6: calculating by using the formula (7) to obtain the credibility of the target social network information, evaluating the credibility of the target social network information according to the result, wherein the credibility is weaker as the numerical value of the calculation result is closer to 0, and the credibility is stronger as the numerical value is closer to 1;
(III) advantage innovation
The invention has the following innovation points:
1. the universality is strong: the method is not a credibility assessment method based on propagation attribute similarity for certain specific social network information, but is a social network information credibility assessment method based on propagation attribute similarity and common to various types of social network information, and therefore the method has good universality.
2. The portability is good: the method does not limit the content of the propagation attributes and the calculation mode of similarity quantiles of the propagation attributes, so that deletion of the propagation attributes and adjustment of the calculation method can be carried out according to the requirements of actual conditions in the credibility evaluation of specific different social network information, and the method has good portability.
3. The objectivity is high: according to the method, the applicability of the method is improved by introducing the propagation characteristics of the social network information and the confirmed credibility of the historical information, and the credibility can be evaluated more objectively.
4. The integrity is strong: the social network information credibility assessment based on the propagation attribute similarity is carried out in the whole information propagation angle, so that the change of the global information can be grasped, and the social network information credibility assessment has good integrity.
In conclusion, the social network information credibility assessment method based on the propagation attribute similarity can better assess the credibility of the social network information by combining the historical information and the information propagation characteristics, and can make up the defects of the existing method; the method of the invention is scientific, has good manufacturability and has wide popularization and application value.
Drawings
FIG. 1 is a flow chart of a method framework of the present invention.
Detailed Description
In order to make the technical problems and technical solutions to be solved by the present invention clearer, the following detailed description is made with reference to the accompanying drawings and specific embodiments. It is to be understood that the embodiments described herein are for purposes of illustration and explanation only and are not intended to limit the invention.
The invention aims to solve the problem of social network information credibility evaluation under the background of social network platform propagation of unverified mass information. Most of the existing methods are credibility assessment methods based on publisher attributes, information content attributes, or macroscopic attributes such as information time and quantity, or a large amount of manpower and material resources are needed to be consumed to collect and judge the assessed specific social network information attributes, so that the propagation attributes of the information are rarely researched and utilized, and credibility assessment is not carried out on the social network information with reference to historical information propagation attributes. Therefore, based on the defects of the existing method, the social network information credibility assessment based on the similarity of the propagation attributes is realized from the perspective of the propagation path.
The method has the characteristics of strong universality, good transportability, high objectivity, strong integrity and the like. The invention is further described with reference to the following description and embodiments in conjunction with the accompanying drawings.
The embodiment of the invention uses target social network information EventobjThe reliability evaluation scenario of (1) is an example to illustrate the method of the present invention. Event is knownobjThe method is a piece of social network information which causes network discussion hotness and wide spread on a social network platform, whether the information is credible or true and is not explained and verified by an official or an authority, and the Event is used forobjThe method is explained by taking the example that the garlic can not kill the new coronavirus.
In order to achieve the purpose, the method adopts the technical scheme that: a social network information credibility assessment method based on propagation attribute similarity is disclosed.
The invention relates to a social network information credibility assessment method based on propagation attribute similarity, which is shown in figure 1 and comprises the following steps:
step A: extracting social network information propagation content and constructing a social network information propagation network;
and B: extracting attributes of social network information transmission nodes, calculating topological attributes of social network information transmission networks, marking the reliability of historical information, and establishing a historical information transmission attribute database;
And C: and calculating the similarity of the propagation attributes of the target social network and the historical social network so as to evaluate the information credibility of the target social network.
Through the steps, the purpose of evaluating the credibility of the social network information based on the similarity of the propagation attributes can be achieved, the method is strong in integrity, high in objectivity and good in universality, and the problem that the credibility of the social network information is difficult to objectively measure and evaluate is solved.
Wherein, the step A of extracting the social network information propagation content and constructing the social network information propagation network comprises the following steps: selecting an information publisher as an initial propagation node for a given amount of historical social network information and target social network information with historical information credibility, and constructing a propagation network of the information according to the direct forwarding node and the direct forwarding directed relation of the initial propagation node; the specific steps of the process are as follows:
step A1: according to the public content of the social network platform, selecting a publisher of a certain social network information Event as an initial propagation node V00The direct forwarder to the initial node is taken as the lower node V0jLooking at the direct forwarding relationship between the initial node and each lower-level node, propagating as social network information, directed connecting edges E 0(V00,V0j) Building a first layer information propagation network G0(V0,E0) Wherein
In the formula: v0Representing an initial propagation node V00With a direct forwarder node V to the initiating node0jSet of nodes of, E0Representing an initial propagation node V00With its direct forwarder node V0jThe forwarding relation between the two is connected with the edge set;
step A2: setting an information propagation network level quantity threshold value L, if L is 3, traversing each forwarding node of each layer, regarding the forwarding node as each initial node of the layer, repeating the step A1, building an interlayer information propagation network layer by layer until the propagation level reaches the threshold value, and obtaining an overall propagation network G (V, E) of the social network information Event, for example, aiming at the initial propagation node V00And collecting each direct forwarder as a lower node V0jJ 1,2, and establishing a continuous edge relation E0(V00,V0j) The number of levels of the propagation network is then 1, and then for each node V of the first level of the propagation network0jJ 1,2, their respective direct forwarders are collected again as the lower level nodes V1kK 1,2, and establishing a continuous edge relation E1(V0j,V1k) If the number of the propagation network levels is 2, constructing the interlayer information propagation network layer by layer until the propagation level reaches a threshold value, and obtaining an overall propagation network G (V, E) of the social network information Event;
Step A3: repeating steps a1, a2 for a given number Num (e.g., Num 100) of historical social network information eventshistoryEstablishing respective information propagation networks Ghistory(Vhistory,Ehistory) Wherein historical social networking information EventhistoryCan be a social networking information Event with a target on a social platformobjContent-related and verified content (for example, the situation that the garlic cannot be killed is taken as credible information, the situation that the wine can be killed as new coronavirus is taken as incredible information), and the situation that the target social network information Event is related to the contentobjContent-independent, certified content (e.g., "new coronavirus causes one million deaths in china" as untrusted information, "biocrisis is a conspiracy made in the united states" as untrusted information). Meanwhile, repeating the steps A1 and A2 to establish a target societyTraffic network information EventobjInformation transmission network G that eating garlic can not eliminate new corona virusobj(Vobj,Eobj)。
The method for extracting the social network information propagation node attributes, calculating the social network information propagation network topology attributes, marking the reliability of the historical information and establishing the historical information propagation attribute database in the step B comprises the following steps: extracting propagation nodes and propagation topological structure attributes in a constructed social network information propagation network (whether the propagation nodes are a historical information network or a target information network) for given quantity of historical social network information and target social network information with historical information credibility, then marking the historical social network information credibility, and establishing a historical social network information propagation attribute database; the specific steps of the process are as follows:
Step B1: extracting unique identification information of each propagation node V in the constructed social network information propagation network G (V, E), such as a user number of a social platform, as a propagation node attribute F of the informationvec；
Step B2: extracting the network topology structure of the constructed social network information transmission network G (V, E), and extracting the network transmission structure attribute F by using a computer method or a manual statistics method and the likestrucIncluding, but not limited to:
(1) propagation network G (V, E) initial forwarding level number ratio r2/1(equation (1)), i.e., the number of layer 2 propagation network nodes nV(2) Number n of network nodes propagated from layer 1V(1) The ratio of (A) to (B);
(2) the propagation network G (V, E) node characteristic distance a is used for fitting the distance distribution among all node pairs in the propagation network, and a specific fitting equation is shown in formula (2), wherein y is the distribution probability, and x is the spacing distance of the node pairs;
(3) the homogeneity index h of the transmission network G (V, E), namely the logarithmic value difference between the homogeneity of the transmission network G (V, E) and the homogeneity of the same-scale star network, is calculated according to the formula (3), wherein the homogeneity calculation method of the transmission network is shown in the formula (4);
step B3: according to calendarSummarizing history facts, authenticating authoritative institution, and setting historical social network information Event historyComprehensive reliability evaluation index of
Wherein a value of 0 indicates that the message is completely untrusted, and a value of 1 indicates that the message is completely trusted, for example, for a piece of such historical social network information Event 1: the garlic can not kill viruses, if the information is completely credible according to the historical fact, the comprehensive Credibility creditability (Event1) is 1, and if the comprehensive Credibility evaluation index creditability (Event1) is 1, the historical social network information Event is correspondingly sethistoryPropagation node reliability evaluation index creditabilityvec(Event1) propagation topology reliability evaluation index creditabilitystruc(Event1) is the same as the comprehensive reliability evaluation index and is 1;
step B4: for the collected number of the historical social network information events which is Num to 100historyPropagating the historical information to node attributes Fvec(Eventhistory) Historical information propagation network structure attribute Fstruc(Eventhistory) Historical information reliability index creditability (Event)history) Joining a historical social network information dissemination Attribute database DS (Event)history)。
Wherein, the step C of calculating the propagation attribute similarity between the target social network information and the historical social network information to evaluate the information reliability of the target social network includes the following specific steps: propagating each collected information Event in attribute database to historical social network information historyAll calculate target social network information EventobjWith the EventhistorySpreading node similarity SimvecAnd obtaining target social network information EventobjPropagation node trustworthiness creditability ofvec(Eventobj) Subsequently calculating target social network information EventobjEvent with historical social network informationhistoryThe propagation structure similarity is divided into bits, and further the reliability of the propagation structure is obtainedCredibilitystruc(Eventobj) Distributing each propagation attribute reliability calculation weight, and calculating the reliability of the target social network information; the specific steps of the process are as follows:
step C1: respectively calculating target social network information Event by adopting an aggregate similarity calculation method such as the Jaccard similarity method (formula (5))objWith the historical information dissemination attribute database DS (Event)history) All historical information Event inhistoryThe propagation node attribute similarity Simvec(Eventobj,Eventhistory) Then selecting the maximum propagation node attribute similarity value Sim in the calculation resultvec_max(e.g., Sim)vec_max0.8) and its corresponding history information Eventvec_max(for example, the information content is 'no virus can be killed when garlic is eaten'), and the Credibility creditability of the corresponding historical information is recordedvec(Eventvec_max) (known as Creditability)vec(Eventvec_max) 1), then the target social network information Event is generatedobjPropagation node trustworthiness creditability ofvec(Eventobj)＝Simvec_max×Credibilityvec(Eventvec_max)＝0.8×1＝0.8；
Step C2: propagating an attribute database DS (Event) to historical information history) In each historical information EventhistoryBased on the propagation structure property FstrucThe size of M (M is 3 in this example) sub-attributes is sorted in descending order, for example, for each history information EventhistorySorting in descending order based on the size of the propagation structure sub-attribute struc _1, wherein the order of obtaining the historical information is Eventhistory1,Eventhistory2,., it indicates Eventhistory1The value of sub-attribute struc _1 in the historical information dissemination attribute database DS (Event)history) The highest of the M pieces of history information is obtained by sorting the history information according to the remaining sub-attribute values, and finally obtaining M (for example, M is 3) pieces of rearranged sequences of history information:
step C3: for the ith (for example, i equals 1) rearranged history information sequence obtained by C2, the history information is divided into K equals 10 sections by equal number, and each section has
Individual history information
(e.g., List)struc_1(Eventhistory1,Eventhistory2,..) total 100 history information which is sorted in descending order based on the size of the sub-attribute struc _1 of the propagation structure, the first 10 history information with the largest sub-attribute struc _1 is divided into a section number 1, the second 11 to 20 th history information with the largest sub-attribute struc _1 is divided into a section number 2, and the 100 history information is divided into 100 history information in sequence
Individual interval) and then compares the target social network information Event obj(i.e. "eating garlic can not eliminate new coronavirus") and ith propagation structure sub-attribute value and ith rearrangement historical information sequence, each historical information EventhistoryFinding the most similar historical information EventhistoryAnd the section number k to which it belongsstruc_i3 as a target social network information EventobjPropagating similarity quantiles of sub-attributes of a structure, e.g. sub-attribute struc _1, target social network information EventobjHas the attribute value of 0.34, and Liststruc_123 th history information Event in (1)history23The corresponding sub-attribute struc _1 is most similar due to Eventhistory23In the 3 rd section of the sequence, the section sequence number k is assignedstruc_13 as a target social network information EventobjThe similarity of the propagation structure sub-attribute struc _1 is divided into bits, and the steps are repeated for the M propagation structure attribute sub-attributes i 1,2objSimilarity decideds (3, 4, 2) of each propagation structure sub-attribute;
step C4: calculating the target society according to formula (6)Traffic network information EventobjThat is, eating garlic can not eliminate new coronavirus, and Event is historical social network informationhistoryPropagation structure sub-attribute reliability creditability of (1)struc_iWhere i is the ith of the 3 propagation structure sub-attributes, 
Respectively target social network information EventobjThe sub-attribute of the propagation structure to which it belongs is divided into kiIn the history information Event with reliability of 0 and 1historyNumber, e.g. for the 1 st propagation structure sub-attribute struc _1, its quantile value kstruc_1History information Event with reliability of 0 and 1 in 3 rd section corresponding to ith 1historyNumber of
Equal to 3 and 7 respectively, the first propagation structure sub-attribute value of the target social network information
And then the credibility of the sub-attributes of the other two propagation structures is respectively 0.7 and 0.8 by the same method;
step C5: confidence creditability for propagating nodesvecReliability of sub-attributes of 3 propagation structures
Credibilitystruc_iI 1.. M assigns a calculation weight wvec,wstruc_1,...,wstruc_MIn which the sum of all weights is equal to 1, the allocation method being, in this case, an average allocation method, e.g.
Step C6: calculating to obtain target social network information by using the formula (7), namely, the credibility that the garlic eating cannot eliminate the new corona virus is 0.75, evaluating the credibility of the target social network information according to the result, wherein the lower the calculated result value is closer to 0, the weaker the credibility is, otherwise, the higher the credibility is closer to 1, the more reliable the target social network information can be seen, the credibility value is 0.75, the comprehensive credibility of the social network that the garlic eating cannot eliminate the new corona virus is 0.75, the information can be believed with a higher probability, and the social network user can be considered to be generally credible when seeing the information on a social network platform;
Claims (4)
1. A social network information credibility assessment method based on propagation attribute similarity is characterized by comprising the following steps: the method comprises the following steps:
step A: extracting social network information propagation content and constructing a social network information propagation network;
and B: extracting attributes of social network information transmission nodes, calculating topological attributes of social network information transmission networks, marking the reliability of historical information, and establishing a historical information transmission attribute database;
and C: and calculating the similarity of the propagation attributes of the target social network and the historical social network so as to evaluate the information credibility of the target social network.
2. The method of claim 1, wherein the social network information credibility assessment based on propagation attribute similarity is characterized in that:
in step a, "extracting social network information propagation content and constructing social network information propagation network" includes the following steps: for a piece of social network information, selecting an information publisher as an initial propagation node, constructing a propagation network of the information by using a direct forwarding node and a direct forwarding directed relationship of the initial propagation node according to layers, and constructing the propagation network for a given amount of historical social network information with historical information credibility and target social network information; the specific steps of the process are as follows:
Step A1: selecting a publisher of a social network information Event as an initial propagation node V according to public information of the social network platform00The direct forwarder to the initial node is taken as the lower node V0jLooking at the direct forwarding relationship between the initial node and each lower-level node, propagating as social network information, directed connecting edges E0(V00,V0j) Building a first layer information propagation network G0(V0,E0) Wherein
In the formula: v0Representing an initial propagation node V00With a direct forwarder node V to the initiating node0jSet of nodes of, E0Representing an initial propagation node V00With its direct forwarder node V0jThe forwarding relation between the two is connected with the edge set;
step A2: setting the number threshold of the information transmission network levels, traversing a plurality of forwarding nodes on each level, regarding the forwarding nodes as a plurality of initial nodes on the level, repeating the step A1, and constructing the interlayer information transmission network layer by layer until the transmission level reaches the threshold, so as to obtain the overall transmission network G (V, E) of the social network information Event; in the formula: v represents a node set in the network, and E represents a node forwarding relation in the network;
step A3: repeating the steps A1 and A2 for a given number Num of historical social network information eventshistoryEstablishing respective information propagation networks G history(Vhistory，Ehistory) Establishing a target social network information EventobjInformation dissemination network Gobj(Vobj，Eobj) (ii) a In the formula: ghistory(Vhistory，Ehistory) Representing historical social network information eventshistoryOf the information dissemination network, VhistoryRepresenting a set of nodes in the network, EhistoryRepresents a node forwarding relationship in the network, and Gobj(Vobj，Eobj) Representing targeted social networking messagesEventobjOf the information dissemination network, VobjRepresenting a set of nodes in the network, EobjRepresenting node forwarding relationships in the network.
3. The method of claim 1, wherein the social network information credibility assessment based on propagation attribute similarity is characterized in that:
in step B, "extract social network information propagation node attributes, calculate social network information propagation network topology attributes, mark historical information credibility, and establish a historical information propagation attribute database", the method is as follows: extracting propagation nodes and propagation topological structure attributes in the constructed social network information propagation network, then marking the credibility of each historical social network information, and establishing a historical social network information propagation attribute database; the specific steps of the process are as follows:
step B1: extracting the unique identification information of each propagation node V in the constructed social network information propagation network G (V, E) as the propagation node attribute F of the information vec；
Step B2: extracting the network topology structure of the constructed social network information propagation network G (V, E), and extracting the network propagation structure attribute FstrucIncluding, but not limited to:
(1) propagation network G (V, E) initial forwarding level number ratio r2/1I.e. formula (1), i.e. the number of layer 2 propagation network nodes nV(2) Number n of network nodes propagated from layer 1V(1) The ratio of (A) to (B);
(2) the propagation network G (V, E) node characteristic distance a is used for fitting the distance distribution among all node pairs in the propagation network, and a specific fitting equation is shown in formula (2), wherein y is the distribution probability, and x is the spacing distance of the node pairs;
(3) the homogeneity index h of the transmission network G (V, E), namely the logarithmic value difference between the homogeneity of the transmission network G (V, E) and the homogeneity of the same-scale star network, is calculated according to the formula (3), wherein the homogeneity calculation method of the transmission network is shown in the formula (4);
h＝log(Hstar)-log(HG) (3)
Step B3: setting historical social network information Event according to historical fact summary and authority authenticationhistoryEvaluation index of reliability of
Wherein the value 0 represents that the letter En is completely untrustworthy, the value 1 represents that the letter En is completely credible, and the historical social update network information Event is sethistoryPropagation node reliability evaluation index creditability vec(Eventhistory) Propagation topology reliability evaluation index creditabilitystruc(Eventhistory) The evaluation index is the same as the comprehensive credibility evaluation index;
step B4: for Num historical social network information Event collectedhistoryPropagating the historical information to node attributes Fvec(Eventhistory) Historical information propagation network structure attribute Fstruc(Eventhistory) Historical information reliability index creditability (Event)history) Joining a historical social network information dissemination Attribute database DS (Event)history)。
4. The method of claim 1, wherein the social network information credibility assessment based on propagation attribute similarity is characterized in that:
in step C, the propagation attribute similarity between the target social network and the historical social network is calculated, so as to evaluate the information credibility of the target social networkDegree ", it does as follows: computing target social network information EventobjEvent with historical social network informationhistorySpreading node similarity SimvecAnd obtaining target social network information EventobjPropagation node trustworthiness creditability ofvec(Eventobj) Subsequently calculating target social network information EventobjAnd
historical social network information EventhistoryThe propagation structure similarity is divided into bits, and further the propagation structure Credibility creditability is obtainedstruc(Eventobj) Distributing each propagation attribute reliability calculation weight, and calculating the reliability of the target social network information; the specific steps of the process are as follows:
Step C1: respectively calculating target social network information Event by adopting an aggregate similarity calculation method such as Jaccard similarity method namely formula (5)objWith the historical information dissemination attribute database DS (Event)history) All historical information Event inhistoryThe propagation node attribute similarity Simvec(Eventobj，Eventhistory) Then selecting the maximum propagation user attribute similarity value Sim in the calculation resultvec_maxAnd corresponding historical information Eventvec_maxRecording the reliability creditability of the corresponding history informationvec(Eventvec_max) Then target social networking information EventobjPropagation node reliability (reliability)vec(Eventobj)＝Simvec_max×Credibilityvec(Eventvec_max)；
In the formula: fvec(Eventobj) Representing target information dissemination node attributes, Fvec(Eventhistory) Representing historical information dissemination node attributes;
step C2: propagating an attribute database DS (Event) to historical informationhistory) In each historical information EventhistoryBased on the propagation structure property FstrucAnd the sizes of the M middle sub attributes are respectively sorted according to the same sorting mode, and M historical information sequences are obtained after sorting:
step C3: for the ith rearranged history information sequence obtained by C2, dividing the history information into K intervals by equal amount, and each interval has
History information is compared with a history information propagation attribute database DS (Event)history) Middle history information EventhistoryCorresponding to the ith propagation structure sub-attribute value, finding the most similar historical information Event historyAnd the section number k to which it belongsstruc_iTargeting social network information eventsobjThe similarity of the propagation structure sub-attribute is divided into bits, and the step is repeated for i 1, 2objDividing the similarity of each propagation structure sub-attribute into bits;
step C4: calculating target social network information Event according to formula (6)objEvent with historical social network informationhistoryPropagation structure sub-attribute reliability creditability of (1)struc_iWhere i is the ith of the M propagation structure sub-attributes,
respectively target social network information EventobjThe sub-attribute of the propagation structure to which it belongs is divided into kiIn the history information Event with reliability of 0 and 1historyThe number of the cells;
step C5: confidence creditability for propagating nodesvecM propagation structure sub-attribute Credibility creditabilitystruc_iI 1.. M assigns a calculation weight wvec，wstruc_1，...，wstruc_MWherein the sum of all weights is equal to 1, and the distribution method can adopt an average distribution method, an analytic hierarchy process and a fuzzy evaluation method and carries out distribution according to the weight importance and other necessary information;
step C6: calculating by using the formula (7) to obtain the credibility of the target social network information, evaluating the credibility of the target social network information according to the result, wherein the credibility is weaker as the numerical value of the calculation result is closer to 0, and the credibility is stronger as the numerical value is closer to 1;
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010558019.3A CN111861122B (en) | 2020-06-18 | 2020-06-18 | Social network information credibility evaluation method based on propagation attribute similarity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010558019.3A CN111861122B (en) | 2020-06-18 | 2020-06-18 | Social network information credibility evaluation method based on propagation attribute similarity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111861122A true CN111861122A (en) | 2020-10-30 |
| CN111861122B CN111861122B (en) | 2022-10-18 |
Family
ID=72986261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010558019.3A Active CN111861122B (en) | 2020-06-18 | 2020-06-18 | Social network information credibility evaluation method based on propagation attribute similarity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111861122B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113395263A (en) * | 2021-05-26 | 2021-09-14 | 西南科技大学 | Method for calculating trust of shared video in online social network |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1675060A1 (en) * | 2004-12-23 | 2006-06-28 | IBM Corporation | A method and system for managing customer network value |
| US20130091222A1 (en) * | 2011-10-05 | 2013-04-11 | Webtrends Inc. | Model-based characterization of information propagation time behavior in a social network |
| EP2937824A1 (en) * | 2014-04-22 | 2015-10-28 | Athens Technology Center S.A. | System and method for evaluating the credibility of news emerging in social networks for information and news reporting purposes |
| US9317567B1 (en) * | 2011-02-16 | 2016-04-19 | Hrl Laboratories, Llc | System and method of computational social network development environment for human intelligence |
| CN107273396A (en) * | 2017-03-06 | 2017-10-20 | 扬州大学 | A kind of social network information propagates the system of selection of detection node |
| CN107451923A (en) * | 2017-07-14 | 2017-12-08 | 北京航空航天大学 | A kind of online social networks rumour Forecasting Methodology based on forwarding Analytic Network Process |
| US20180018709A1 (en) * | 2016-05-31 | 2018-01-18 | Ramot At Tel-Aviv University Ltd. | Information spread in social networks through scheduling seeding methods |
| CN107908645A (en) * | 2017-10-09 | 2018-04-13 | 北京航空航天大学 | A kind of immunization method of the online social platform gossip propagation based on Analysis of The Seepage |
| CN108304867A (en) * | 2018-01-24 | 2018-07-20 | 重庆邮电大学 | Information popularity prediction technique towards social networks and system |
| US20180341696A1 (en) * | 2017-05-27 | 2018-11-29 | Hefei University Of Technology | Method and system for detecting overlapping communities based on similarity between nodes in social network |
| CN109919794A (en) * | 2019-03-14 | 2019-06-21 | 哈尔滨工程大学 | A kind of microblog users method for evaluating trust based on belief propagation |
-
2020
- 2020-06-18 CN CN202010558019.3A patent/CN111861122B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1675060A1 (en) * | 2004-12-23 | 2006-06-28 | IBM Corporation | A method and system for managing customer network value |
| US9317567B1 (en) * | 2011-02-16 | 2016-04-19 | Hrl Laboratories, Llc | System and method of computational social network development environment for human intelligence |
| US20130091222A1 (en) * | 2011-10-05 | 2013-04-11 | Webtrends Inc. | Model-based characterization of information propagation time behavior in a social network |
| EP2937824A1 (en) * | 2014-04-22 | 2015-10-28 | Athens Technology Center S.A. | System and method for evaluating the credibility of news emerging in social networks for information and news reporting purposes |
| US20180018709A1 (en) * | 2016-05-31 | 2018-01-18 | Ramot At Tel-Aviv University Ltd. | Information spread in social networks through scheduling seeding methods |
| CN107273396A (en) * | 2017-03-06 | 2017-10-20 | 扬州大学 | A kind of social network information propagates the system of selection of detection node |
| US20180341696A1 (en) * | 2017-05-27 | 2018-11-29 | Hefei University Of Technology | Method and system for detecting overlapping communities based on similarity between nodes in social network |
| CN107451923A (en) * | 2017-07-14 | 2017-12-08 | 北京航空航天大学 | A kind of online social networks rumour Forecasting Methodology based on forwarding Analytic Network Process |
| CN107908645A (en) * | 2017-10-09 | 2018-04-13 | 北京航空航天大学 | A kind of immunization method of the online social platform gossip propagation based on Analysis of The Seepage |
| CN108304867A (en) * | 2018-01-24 | 2018-07-20 | 重庆邮电大学 | Information popularity prediction technique towards social networks and system |
| CN109919794A (en) * | 2019-03-14 | 2019-06-21 | 哈尔滨工程大学 | A kind of microblog users method for evaluating trust based on belief propagation |
Non-Patent Citations (7)
| Title |
|---|
| LIANG WU等: "Gleaning Wisdom from the Past:Early Detection of Emerging Rumors in Social Media", 《COMPUTER SCIENCE AND ENGINEERING》 * |
| ZHE ZHAO等: "Enquiring Minds: Early Detection of Rumors in Social Media from Enquiry Posts", 《THE INTERNATIONAL WORLD WIDE WEB CONFERENCE COMMITTEE(IW3C2)》 * |
| 刘银萍等: "基于AHP的社交网络信息可信度评价模型构建", 《情报探索》 * |
| 尹熙成等: "在线社交网络中具有传播价值的弱关系识别研究", 《情报杂志》 * |
| 朱晓明等: "社交网络传播节点影响力建模分析", 《电子设计工程》 * |
| 王天博等: "面向分层网络的社交蠕虫仿真建模研究", 《电子学报》 * |
| 陈燕方等: "在线社会网络谣言检测综述", 《计算机学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113395263A (en) * | 2021-05-26 | 2021-09-14 | 西南科技大学 | Method for calculating trust of shared video in online social network |
| CN113395263B (en) * | 2021-05-26 | 2022-07-26 | 西南科技大学 | Trust calculation method for sharing video in online social network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111861122B (en) | 2022-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao et al. | Fake news propagates differently from real news even at early stages of spreading | |
| Cui et al. | Malicious URL detection with feature extraction based on machine learning | |
| CN109218304B (en) | Network risk blocking method based on attack graph and co-evolution | |
| WO2020177484A1 (en) | Localized difference privacy urban sanitation data report and privacy calculation method | |
| CN107451923A (en) | A kind of online social networks rumour Forecasting Methodology based on forwarding Analytic Network Process | |
| CN108764267A (en) | A kind of Denial of Service attack detection method integrated based on confrontation type decision tree | |
| Monk et al. | Uncovering tor: An examination of the network structure | |
| CN115640305B (en) | Fair and reliable federal learning method based on blockchain | |
| CN115412354B (en) | Network security vulnerability detection method and system based on big data analysis | |
| Boshmaf et al. | Thwarting fake OSN accounts by predicting their victims | |
| CN110011976B (en) | Network attack destruction capability quantitative evaluation method and system | |
| Soundarya et al. | Recommendation System for Criminal Behavioral Analysis on Social Network using Genetic Weighted K-Means Clustering. | |
| CN106603538A (en) | Invasion detection method and system | |
| CN115150182B (en) | Information system network attack detection method based on flow analysis | |
| CN111861122B (en) | Social network information credibility evaluation method based on propagation attribute similarity | |
| CN117336011A (en) | Mining behavior detection method and device, electronic equipment and storage medium | |
| Zhou et al. | An efficient victim prediction for Sybil detection in online social network | |
| Yokotani et al. | Effects of suspensions on offences and damage of suspended offenders and their peers on an online chat platform | |
| Yang et al. | Evaluating highway traffic safety: an integrated approach | |
| Xu et al. | A new analytical framework for network vulnerability on subway system | |
| Zhou et al. | Predicting the tendency of topic discussion on the online social networks using a dynamic probability model | |
| CN115865708B (en) | Complex social network information handling method based on SIR-D model | |
| CN103902690A (en) | Method for improving accuracy of influence of user generate content (UGC) information of social network | |
| CN109063485A (en) | A kind of vulnerability classification statistical system and method based on loophole platform | |
| Chen et al. | Severity assessment and the early warning mechanism of public events based on the comparison of microblogging characteristics |
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 |