CN110929168A - Key audience determining method and device and electronic equipment - Google Patents
Key audience determining method and device and electronic equipment Download PDFInfo
- Publication number
- CN110929168A CN110929168A CN201911100324.1A CN201911100324A CN110929168A CN 110929168 A CN110929168 A CN 110929168A CN 201911100324 A CN201911100324 A CN 201911100324A CN 110929168 A CN110929168 A CN 110929168A
- Authority
- CN
- China
- Prior art keywords
- audience
- node
- social network
- text
- target topic
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000006399 behavior Effects 0.000 claims abstract description 90
- 238000011156 evaluation Methods 0.000 claims abstract description 74
- 230000003993 interaction Effects 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 6
- 238000013016 damping Methods 0.000 claims description 3
- 238000012552 review Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 17
- 230000000694 effects Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 238000005065 mining Methods 0.000 description 4
- 230000006855 networking Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000007480 spreading Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 102000040430 polynucleotide Human genes 0.000 description 2
- 108091033319 polynucleotide Proteins 0.000 description 2
- 239000002157 polynucleotide Substances 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000003997 social interaction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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 invention discloses a method, a device and electronic equipment for determining a key audience, wherein the method comprises the following steps: constructing a social network of an audience of a target topic based on text data and text propagation behavior data of the audience of the target topic, wherein nodes of the social network are used for representing the audience, weights of the nodes are determined by the text data of the audience represented by the nodes, directed edges from a first node to a second node in the social network are used for representing text propagation behaviors of the first audience to the second audience, and the weights of the directed edges are determined by the text propagation behavior data corresponding to the text propagation behaviors; determining an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge; determining a key audience of the target topic based on an importance evaluation parameter of the audience of the target topic. The scheme disclosed by the invention can improve the accuracy of the determined key audience.
Description
Technical Field
The application relates to the technical field of computers, in particular to a method and a device for determining a key audience and electronic equipment.
Background
In recent years, social media based on the internet are rapidly developed, and people can achieve the purpose of social interaction without going out. For example, people can obtain, publish, and propagate the speech through the social networking platform, and comment on the speech published or propagated by others to express their opinion and feelings about a topic or event. The people who participate in the social activities through the social networking platform are users of the social networking platform, and the user who receives a certain text transmitted on the social networking platform is an audience of the text.
In the process of spreading a certain text related to a certain topic (or event), users often exist, which have the ability to influence the attitudes of other users on the topic, and the intervention of the users accelerates the spreading speed of the text and enlarges the influence, thereby guiding the spreading of the topic. These users may be referred to as key audiences (or as opinion leaders). Finding out key audiences is one of the means for the web social platform to provide better services to users.
At present, the key audience is determined by considering single factors, so that the determined key audience is not accurate enough, and improvement is urgently needed.
Disclosure of Invention
The embodiment of the application provides a method and a device for determining a key audience and electronic equipment, so that the accuracy of the determined key audience is improved.
In order to solve the above technical problem, the embodiment of the present application is implemented as follows:
in a first aspect, a method for determining a key audience is provided, where the method includes:
acquiring the text data and the text propagation behavior data of audiences of the target topic;
constructing a social network of the audience of the target topic based on the text data and the text propagation behavior data, wherein nodes of the social network are used for representing the audience, the weight of each node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used for representing the text propagation behavior of the first audience to the second audience, and the weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior;
determining an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge;
determining a key audience of the target topic based on an importance evaluation parameter of the audience of the target topic.
In a second aspect, a key audience determination apparatus is provided, the apparatus comprising:
the data acquisition module is used for acquiring the text data and the text propagation behavior data of the audiences of the target topic;
a network construction module, configured to construct a social network of an audience of the target topic based on the text data and the text propagation behavior data, where a node of the social network is used to represent the audience, a weight of the node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used to represent a text propagation behavior of the first audience to the second audience, and a weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior;
a parameter determination module, configured to determine an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge;
and the key audience determining module is used for determining the key audience of the target topic based on the importance evaluation parameter of the audience of the target topic.
In a third aspect, an electronic device is provided, including:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring the text data and the text propagation behavior data of audiences of the target topic;
constructing a social network of the audience of the target topic based on the text data and the text propagation behavior data, wherein nodes of the social network are used for representing the audience, the weight of each node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used for representing the text propagation behavior of the first audience to the second audience, and the weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior;
determining an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge;
determining a key audience of the target topic based on an importance evaluation parameter of the audience of the target topic.
In a fourth aspect, a computer-readable storage medium is presented, the computer-readable storage medium storing one or more programs that, when executed by an electronic device that includes a plurality of application programs, cause the electronic device to:
acquiring the text data and the text propagation behavior data of audiences of the target topic;
constructing a social network of the audience of the target topic based on the text data and the text propagation behavior data, wherein nodes of the social network are used for representing the audience, the weight of each node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used for representing the text propagation behavior of the first audience to the second audience, and the weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior;
determining an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge;
determining a key audience of the target topic based on an importance evaluation parameter of the audience of the target topic.
As can be seen from the technical solutions provided in the embodiments of the present application, the solutions provided in the embodiments of the present application have at least one of the following technical effects: because the social network of the target topic audience is determined based on the two aspects of the text data and the text propagation behavior data of the target topic audience, and when the importance evaluation parameter of the target topic audience is determined, the weight of the audience (node) and the interactive relation (edge weight) between the audiences are considered, the accuracy of the determined importance parameter of the target topic audience can be improved, and the accuracy of the determined key audience is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart illustrating a key audience determination method according to an embodiment of the present disclosure.
Fig. 2 is a schematic diagram of a social network provided in an embodiment of the present specification.
Fig. 3 is a detailed flow chart of step 103 shown in fig. 1.
Fig. 4 is a schematic diagram illustrating an effect of the key audience determination method provided in the embodiment of the present specification.
Fig. 5 is a second schematic diagram illustrating the effect of the key audience determination method according to the embodiment of the present disclosure.
Fig. 6 is a schematic structural diagram of a key audience determination apparatus according to an embodiment of the present disclosure.
Fig. 7 is a schematic structural diagram of an electronic device provided in an embodiment of the present specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to improve the accuracy of the determined key audience, embodiments of the present specification provide a method, an apparatus, and a device for determining a key audience, where an execution subject of the method and the apparatus may be any one of a terminal device and a server.
As shown in fig. 1, an embodiment of the present specification provides a key audience determining method, including:
step 101, obtaining the text data and the text propagation behavior data of the audience of the target topic.
The target topic (also called target topic) is a topic to be determined as a key audience (also called opinion leader) on a social network platform. As an example, detailed text data related to a target topic (e.g., detailed blog data related to a certain topic on a microblog) may be collected from the social network platform; then, according to the collected detailed text data, determining part or all audiences of the target topic; after determining the audience of the target topic, collecting the text data and the text propagation behavior data of the audience of the target topic from the social network platform.
For example, if the social network platform is a microblog, a piece of detailed text data collected from the social network platform may be as shown in table 1 below, and the piece of detailed text data is related to the target topic, then determining the user ID for approval, comment, and share of the blog in table 1 may determine a part of the audience of the target topic. It can be understood that according to all the collected detailed text data related to the target topic, all audiences of the target topic can be determined. Further, after determining the audience of the target topic, all text data and all text propagation behavior data of the audience of the target topic may be collected according to the audience ID of the target topic, and table 2 below exemplarily lists one piece of text propagation behavior data.
TABLE 1
In one example, the textual data for an audience of a target topic may include, but is not limited to, at least one of the following:
the number of utterances from the audience member,
the number of reviews the audience receives may be,
the number of praise received by the audience,
the number of times the audience received the reward,
the amount of the reward received by the audience (including at least one of the amount of the single reward, the highest reward amount and the total reward amount),
the number of times the audience's text is collected,
the number of publications that the audience receives shared by other audiences of the target topic, and so on.
TABLE 2
| Bo Wen ID | Act of spreading of a message | Sharing time | Sharing user ID | Sharing a nickname of a user |
| 4302708846623740 | Sharing | 11-05 | 2747934781 | A polynucleotide sequence |
It is to be understood that in addition to the sharing (or forwarding) in table 2, the text dissemination behavior includes, but is not limited to, the actions of like, comment, share (forwarding), reward, and collection, and not just the sharing action (or forwarding action). Accordingly, the text transmission behavior data corresponding to the text transmission behavior of the first audience to the second audience may include, but is not limited to, at least one of the following data:
the number of times the first audience member likes the second audience member,
the number of times the first audience commented to the second audience,
the number of times the first audience shares the text to the second audience,
the number of times the first audience enjoys the second audience,
the amount the first audience enjoys to the second audience,
the number of times the first audience collected the prose of the second audience, and so on.
It should be noted that in the embodiment of the present specification, the audience of the target topic is a user of the social network platform.
Optionally, in another example, the step 101 may specifically include: and acquiring attribute information, text data and text propagation behavior data of audiences of the target topic. The attribute information of the audience may include, but is not limited to, at least one of identity, occupation, work area, title, obtained honor, employment unit, and the like of the audience.
102, constructing a social network of the audience of the target topic based on the text data and the text propagation behavior data, wherein nodes of the social network are used for representing the audience, weights of the nodes are determined by the text data of the audience represented by the nodes, directed edges from first nodes to second nodes in the social network are used for representing the text propagation behavior of the first audience to the second audience, and the weights of the directed edges are determined by the text propagation behavior data corresponding to the text propagation behavior.
In detail, in step 102, the text data and the text propagation behavior data of the audience of the target topic acquired in step 101 may be preprocessed to obtain two data tables. Wherein a data table is used to store data reflecting the basic importance of the audience itself of the target topic, and table 3 shows one such data; another data table is used to store data reflecting the interaction between different audiences of the target topic, and table 4 shows one such data.
TABLE 3
| Name of user (audience) | Number of praise | Number of messages sent | Number of comments | Number of forwarding | First weight |
| Headline news | 149188 | 3 | 38434 | 51359 | 359810.53 |
The first weight in table 3, which is used to reflect the basic importance of the audience itself, may be calculated according to the posting data of the audience, such as by weighting the posting number of the audience, the received praise number, the received comment number, and the received posting number shared by other audiences. It can be understood that if the number of comments received by the audience and the number of received messages shared by other audiences are considered when the first weight of the audience of the target topic is calculated, the influence of the indirect audience and the potential audience of the target topic is considered, so that the determined first weight can accurately reflect the basic influence of the audience, and the finally determined key audience is more accurate.
TABLE 4
| Propagator | Receiver | Second weight |
| XX News periodical | A polynucleotide sequence | 9.5 |
The second weight in table 4, which is used to reflect the interaction relationship between the propagator (one audience of the target topic) and the receiver (another audience of the target topic), may be obtained by calculation according to the text transmission behavior data corresponding to the text transmission behavior made by the propagator to the receiver, for example, by weighting according to the data such as the praise, comment, and sharing frequency made by the propagator to the receiver.
Further, in step 102, after determining the data shown in tables 3 and 4, a node in the social network may be established according to one piece of data in table 3, wherein the first weight may be a weight of the established node; a directed edge in the social network may be established according to a piece of data in table 4, where the second weight may be used as a weight of the established directed edge, and finally, the social network of the audience of the target topic is obtained.
Optionally, after the attribute information of the audience of the target topic is further obtained in step 101, the first weight may also be determined by the text data and the attribute information of the audience represented by the node.
It is understood that, in addition to the text data of the audience, the attribute information of the audience (e.g., at least one of the identity, occupation, work area, title, acquired honor, employment unit, etc. of the audience) also determines the importance (or influence) of the audience. As shown in fig. 5, the audience is the forty-fifth president of the united states of china, Donald, tlplate (Donald Trump), since the president of a country usually has extraordinary influence, and is itself an opinion leader, it is necessary to consider attribute information such as its identity when determining the importance of the audience, so that the determined weight can represent the influence of the audience more, thereby further improving the accuracy of the finally determined key audience.
As shown in fig. 2, in the constructed social network of the audience of the target topic, there may be a directed edge directed from the first node to the second node (e.g., node a is directed to node B), or there may be a directed edge directed from the second node to the first node (e.g., node B is directed to node a). If the audience represented by the first node does a posting of the spam to the audience represented by the second node, there is a directed edge that the first node points to the second node. If the audience represented by the second node does a posting action to the audience represented by the first node, there is a directed edge that the second node points to the first node. If the audience represented by the first node makes a text propagation behavior to the audience represented by the second node, and the audience represented by the second node makes a text propagation behavior to the audience represented by the first node, a directed edge exists, in which the first node points to the second node, and a directed edge exists, in which the second node points to the first node.
In the social network constructed in step 102, the text propagation behavior data corresponding to the text propagation behavior made by the first node to the second node includes at least one of the following data:
a number of times that the first audience member likes the second audience member,
a number of times the first audience commented on the second audience,
the number of times the first audience shares the prose with the second audience,
a number of times the first audience awards the second audience,
an amount that the first audience awards to the second audience,
the number of times the first audience collected the second audience's text, and so on.
And 103, determining importance evaluation parameters of audiences represented by the nodes in the social network based on the weights of the nodes in the social network and the weights of the directed edges.
The audience importance assessment parameter is an index for evaluating the importance of an audience, and as an example, the importance assessment parameter may be an importance value.
And determining a key audience, namely mining opinion leaders. The essence of opinion leader mining is to assess the importance of individual nodes in a social network that represent the audience, i.e., centrality analysis. Common centrality analysis methods include centrality analysis, centrality of compactness analysis, centrality of betweenness analysis, and centrality of feature vectors.
The basic idea of the degree-centrality analysis is that the importance of a node is related to the number (degree) of the node. The greater the degree of a node, the more important the node appears.
Wherein the affinity centrality analysis considers that one central node can reach other nodes in the social network faster than non-central nodes. The affinity centrality analysis is used to evaluate the affinity of a node to all other nodes, and is generally measured by the average distance of the node to all other nodes in the social network.
The betweenness centrality analysis is to measure the importance of a node by using the betweenness size of the node, wherein the node is more important when the betweenness of the node is larger. The betweenness of a node represents the number of shortest paths through the node in the social network.
The basic idea of feature vector centrality analysis is that the importance of a person depends on the importance of friends, and a link voting strategy is adopted, namely, a node distributes own weight to adjacent nodes according to the degree of emittance average until convergence.
Based on the idea of feature vector centrality analysis, as an example, step 103 may include: the specified steps are executed in a loop for each second node in the social network until the importance evaluation parameters of the audiences represented by the nodes in the social network converge (for example, the importance evaluation parameters of the audiences do not change any more). As shown in fig. 3, steps 301 to 304 are performed in a loop for each second node in the social network, and after the importance evaluation parameter of the audience represented by the node in the social network converges, step 306 is performed.
Specifically, as shown in fig. 3, step 103 may include:
step 301, determining a first importance assessment parameter of the second audience based on the weight of the second node in the social network.
Specifically, the weight of the second node may be directly used as the first importance evaluation parameter of the second audience. It will be appreciated that the second audience is the audience represented by the second node.
Step 302, determining a weight of a target node in the social network, wherein the target node is the first node pointing to the second node through a directed edge.
I.e., determining other nodes associated with the second node to determine the impact of other audiences on the importance rating parameter of the second audience.
Step 303, determining a second importance evaluation parameter for the audience represented by the target node to pass to the second audience based on the weight of the target node and the weight of the directional edge of the target node pointing to the second node.
As an example, a second importance assessment parameter may be determined for the audience represented by the target node to be passed to the second audience by multiplying the weight of the target node by the weight of the target node pointing to the directed edge of the second node.
Step 304, determining an importance evaluation parameter for the second audience based on the first importance evaluation parameter and the second importance evaluation parameter.
As an example, the sum of the first importance rating parameter and the second importance rating parameter may be determined as the importance rating parameter for the second audience.
And 305, judging whether the importance evaluation parameters of the audiences represented by the nodes in the social network are converged, if not, returning to execute the step 301, otherwise, executing the step 306.
And step 306, ending.
The Pagerank algorithm is a variation of the feature vector centrality analysis method, and thus, as another example, the step 103 may include: and determining importance evaluation parameters of audiences represented by the nodes in the social network based on the weights of the nodes in the social network and the weights of the directed edges and a PageRank algorithm.
The PageRank algorithm adopts a link voting strategy, namely that the first node viPointing to a second node vjDirected edge e ofijRepresenting a first node viTo the second node vjWhen the first node votes for the second node, the first node will press its own weight as the directed edge eijIs assigned to the second node. As shown in fig. 2, if the weight of node a is 10, the weight of node B is 9, the weight of node C is 8, the weight of the directed edge AB pointed to by node a to node B is 5, and the weight of the directed edge CB pointed to by node C to node B is 4, the importance evaluation parameter of node B in one iteration process can be represented as: p (b) ═ 10 × 5+8 × 4 ═ 82. It can be seen that when the importance evaluation parameter of the audience represented by the node in the social network is calculated by adopting the PageRank algorithm, the second node related to the second node is also consideredThe impact of the importance of one node on the importance of a second node.
Specifically, in the embodiment of the present specification, the PageRank algorithm is as follows:
π(k+1)T＝(1-α)eT+απ(k)TV
wherein pi represents a matrix formed by importance evaluation parameters P of nodes in the social network, pi(k)TA matrix, pi, of importance evaluation parameters P representing nodes in the social network before iteration(k+1)TA matrix of importance assessment parameters P representing nodes in the social network after iteration, α being a damping coefficient, eTRepresenting a unit row vector, V representing a voting matrix, the element V in VijRepresenting a node v in the social networkiTo node vjProportion of assigned weights, vijIs equal to the first node viPointing to said second node vjDirected edge e ofijThe weight of (c).
During specific calculation, the dead nodes (nodes with out degrees of 0) in the social network may be deleted first, and then the importance evaluation parameter P of each node is calculated by repeatedly using the iterative formula of the PageRank algorithm until convergence (that is, until the importance evaluation parameter of each node is not changed any more).
As can be seen from the above two examples, in the step 103, when determining the importance evaluation parameter of the audience, not only the importance of the audience itself but also the influence of the importance of other audiences related to the audience on the audience itself are considered, so that the finally determined importance evaluation parameter can better represent the real influence of the audience, and the finally determined key audience is more accurate.
It should also be noted that in the embodiment of the present specification, the importance of the first audience is transferred to the second audience through the weight of the directed edge pointed to the second audience by the first audience. The importance of the second audience is, in turn, passed to the first audience through the weights of the directed edges pointed to the first audience by the second audience. The influence degree of the first audience on the second important audience and the influence degree of the second audience on the first audience may be different, which is consistent with the situation in a real social network, so that the key audience finally determined by the method provided by the embodiment of the specification can be more accurate.
And 104, determining a key audience of the target topic based on the importance evaluation parameter of the audience of the target topic.
In one example, step 104 may include: ranking the audience of the target topic based on an importance evaluation parameter of the audience of the target topic; and sequencing at least one audience meeting preset conditions from the audiences of the target topic, and determining the audiences as key audiences of the target topic.
Specifically, a preset number of audiences with the importance evaluation parameter ranked most ahead (for example, top n audiences) in the audiences of the target topic is determined as the key audience of the target topic, table 5 shows the relevant data of a determined key audience (named reldonaldjump), and fig. 4 and 5 show the display effect of the determined key audience at the front end of the social network platform.
TABLE 5
| User name | Importance assessment parameter | Key audience |
| relDonaldTrump | 1 | 1 |
It is understood that the importance evaluation parameter of the audience of the target topic may reflect the influence of the audience in the propagation process of the target topic, and therefore, the importance evaluation parameter may also be referred to as the influence index 41 as shown in fig. 4.
Optionally, as shown in fig. 5, the method provided in the embodiment of the present disclosure may further display an opinion leader identifier 51 and/or an "opinion leader 52" at the front end of the social network platform to indicate that the audience is a key audience.
In addition, as shown in fig. 5, the method provided in the embodiment of the present specification may further display attribute information of the audience at a front end of the social network platform, such as "45 th american president"; or the text data of the audience, such as 'Bo Wen 4.0W', the text data and the text propagation behavior data of 'the number of users concerned', 'the number of fans' and 'the number of people concerned' can be displayed, so that the characteristics of the opinion leader can be visually displayed.
Optionally, after determining the key audience, the effectiveness of the determined key audience may be further evaluated. Specifically, the evaluation can be performed according to coverage, core rate, even manual evaluation, and the like.
The coverage is calculated from the perspective of a social network formed by user interaction, the proportion of the number of the audiences which can be covered by the single-step propagation of the n key audiences to all the audiences of the target topic is calculated, and generally speaking, if the proportion of the audiences covered by the information propagated by the preset number of the audiences to the audiences of the target topic exceeds a first preset proportion (such as 80%), the key audiences determined by the key audience determination method provided by the embodiment of the invention are considered to be accurate, have the capability of being used as opinion leaders and have good determination effect.
The core rate is also the ratio of the information amount of interaction between the key audience and other audiences of the target topic to the total information amount of the target topic from the perspective of user interaction, and generally speaking, if the information amount of interaction between the preset number of audiences and the other audiences of the target topic is greater than a second preset ratio (such as 85%) in the total information amount of the target topic, the key audience determined by the method for determining the key audience provided by the embodiment of the invention is considered to be accurate, has the capability of being used as an opinion leader, and has a good determination effect.
The manual evaluation is an evaluation method for judging whether the determined key audience is the opinion leader or not by manually analyzing the relevant characteristics of the key audience.
In summary, according to the method for determining the key audience provided in the embodiment of the present specification, since the social network of the audience of the target topic is determined based on the two aspects of the text data and the text propagation behavior data of the audience of the target topic, and when determining the importance evaluation parameter of the audience of the target topic, the weight of the audience (node) itself and the interactive relationship (the directed edge and the weight thereof) between the audiences are considered, the accuracy of the determined importance parameter of the audience of the target topic can be improved, so that the accuracy of the determined key audience is improved, and the determined key audience has the ability of opinion leader, and the determination effect is good.
The above is a description of a key audience determination method and system provided in this specification, and the following is a description of a key audience determination apparatus provided in this specification.
The following describes a key audience determination apparatus provided in the present specification.
As shown in fig. 6, an embodiment of the present specification provides a key audience determination apparatus, and in one software implementation, the key audience determination apparatus 600 may include: a data acquisition module 601, a network construction module 602, a parameter determination module 603, and a key audience determination module 604.
The data obtaining module 601 is configured to obtain the text data and the text propagation behavior data of the audience of the target topic.
The target topic (also called target topic) is a topic to be determined as a key audience (also called opinion leader) on a social network platform. As an example, the data obtaining module 601 may first collect detailed text data related to a target topic (e.g., detailed blog data related to a certain topic on a microblog) from the social network platform; then, according to the collected detailed text data, determining part or all audiences of the target topic; after determining the audience of the target topic, collecting the text data and the text propagation behavior data of the audience of the target topic from the social network platform.
In one example, the textual data for an audience of a target topic may include, but is not limited to, at least one of the following:
the number of utterances from the audience member,
the number of reviews the audience receives may be,
the number of praise received by the audience,
the number of times the audience received the reward,
the amount of the reward received by the audience (including at least one of the amount of the single reward, the highest reward amount and the total reward amount),
the number of times the audience's text is collected,
the number of publications that the audience receives shared by other audiences of the target topic, and so on.
As another example, the textual dissemination behavior data corresponding to one audience of the target topic (referred to as the first audience) relative to the textual dissemination behavior of another audience (referred to as the second audience) may include, but is not limited to, at least one of the following data reds:
the number of times the first audience member likes the second audience member,
the number of times the first audience commented to the second audience,
the number of times the first audience shares the text to the second audience,
the number of times the first audience enjoys the second audience,
the amount the first audience enjoys to the second audience,
the number of times the first audience collected the prose of the second audience, and so on.
A network construction module 602, configured to construct a social network of an audience of the target topic based on the text data and the text propagation behavior data, where a node of the social network is used to represent the audience, a weight of the node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used to represent a text propagation behavior of the first audience to the second audience, and a weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior.
In detail, the network construction module 602 may be configured to: the method comprises the steps of preprocessing the text data and the text transmission behavior data of the audience of the target topic acquired by the data acquisition module 601 to obtain two data tables. Wherein, a data table is used for storing data reflecting the basic importance of the target topic audience, and the upper table 3 shows one such data, specifically referring to the upper table 3; another data table is used to store data reflecting the interaction between different audiences of the target topic, and one such data is shown in table 4 above, see table 4 above in particular.
In detail, in the social network constructed by the network construction module 602, the text propagation behavior data corresponding to the text propagation behavior made by the first node to the second node includes at least one of the following data:
a number of times that the first audience member likes the second audience member,
a number of times the first audience commented on the second audience,
the number of times the first audience shares the prose with the second audience,
a number of times the first audience awards the second audience,
an amount that the first audience awards to the second audience,
the number of times the first audience collected the second audience's text, and so on.
A parameter determining module 603, configured to determine an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge.
The audience importance assessment parameter is an index for evaluating the importance of an audience, and as an example, the importance assessment parameter may be an importance value.
And determining a key audience, namely mining opinion leaders. The essence of opinion leader mining is to assess the importance of individual nodes in a social network that represent the audience, i.e., centrality analysis. Common centrality analysis methods include centrality analysis, centrality of compactness analysis, centrality of betweenness analysis, and centrality of feature vectors. As an example, the parameter determination module 603 may be configured to: and determining importance evaluation parameters of audiences represented by the nodes in the social network based on the weights of the nodes in the social network and the weights of the directed edges and a PageRank algorithm.
The PageRank algorithm adopts a link voting strategy, namely that the first node viPointing to a second node vjDirected edge e ofijRepresenting a first node viTo the second node vjWhen the first node votes for the second node, the first node will press its own weight as the directed edge eijIs assigned to the second node. As shown in fig. 2, if the weight of node a is 10, the weight of node B is 9, the weight of node C is 8, the weight of the directed edge AB pointed to by node a to node B is 5, and the weight of the directed edge CB pointed to by node C to node B is 4, the importance evaluation parameter of node B in one iteration process can be represented as: p (b) ═ 10 × 5+8 × 4 ═ 82.
Specifically, in the embodiment of the present specification, the PageRank algorithm is as follows:
π(k+1)T＝(1-α)eT+απ(k)TV
wherein pi represents a matrix formed by importance evaluation parameters P of nodes in the social network, pi(k)TA matrix, pi, of importance evaluation parameters P representing nodes in the social network before iteration(k+1)TA matrix of importance assessment parameters P representing nodes in the social network after iteration, α being a damping coefficient, eTRepresenting a unit row vector, V representing a voting matrix, the element V in VijRepresenting a node v in the social networkiTo node vjProportion of assigned weights, vijIs equal to the first node viPointing to said second node vjDirected edge e ofijThe weight of (c).
During specific calculation, the dead nodes (nodes with out degrees of 0) in the social network may be deleted first, and then the importance evaluation parameter P of each node is calculated by repeatedly using the iterative formula of the PageRank algorithm until convergence (that is, until the importance evaluation parameter of each node is not changed any more).
A key audience determination module 604 for determining a key audience of the target topic based on the importance evaluation parameter of the audience of the target topic.
In one example, the key audience determination module 604 may be configured to: ranking the audience of the target topic based on an importance evaluation parameter of the audience of the target topic; and sequencing at least one audience meeting preset conditions from the audiences of the target topic, and determining the audiences as key audiences of the target topic.
Specifically, the audience with the highest importance evaluation parameter in the audience of the target topic is ranked at the top preset number of audiences (such as the top n audiences), and is determined as the key audience of the target topic.
Optionally, after determining the key audience, the effectiveness of the determined key audience may be further evaluated. Specifically, the evaluation can be performed according to coverage, core rate, even manual evaluation, and the like.
The coverage is calculated from the perspective of a social network formed by user interaction, the proportion of the number of the audiences which can be covered by the single-step propagation of the n key audiences to all the audiences of the target topic is calculated, and generally speaking, if the proportion of the audiences covered by the information propagated by the preset number of the audiences to the audiences of the target topic exceeds a first preset proportion (such as 80%), the key audiences determined by the key audience determination method provided by the embodiment of the invention are considered to be accurate, have the capability of being used as opinion leaders and have good determination effect.
The core rate is also the ratio of the information amount of interaction between the key audience and other audiences of the target topic to the total information amount of the target topic from the perspective of user interaction, and generally speaking, if the information amount of interaction between the preset number of audiences and the other audiences of the target topic is greater than a second preset ratio (such as 85%) in the total information amount of the target topic, the key audience determined by the method for determining the key audience provided by the embodiment of the invention is considered to be accurate, has the capability of being used as an opinion leader, and has a good determination effect.
The manual evaluation is an evaluation method for judging whether the determined key audience is the opinion leader or not by manually analyzing the relevant characteristics of the key audience.
In summary, according to the key audience determining apparatus provided in the embodiments of the present specification, since the social network of the target topic audience is determined based on the two aspects of the text data and the text propagation behavior data of the target topic audience, and when determining the importance evaluation parameter of the target topic audience, the weight of the audience (node) itself and the interaction relationship (edge weight) between the audiences are considered at the same time, the accuracy of the determined importance parameter of the target topic audience can be improved, so that the accuracy of the determined key audience is improved, and the determined key audience has the ability of opinion leader, and the determining effect is good.
It should be noted that the key audience determining apparatus 600 can implement the method in the embodiment of the method in fig. 1, and specifically, reference may be made to the key audience determining method in the embodiment shown in fig. 1, which is not described again.
Fig. 7 is a schematic structural diagram of an electronic device provided in an embodiment of the present specification. Referring to fig. 7, at a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (peripheral component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 7, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form the key audience determination device on a logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:
acquiring the text data and the text propagation behavior data of audiences of the target topic;
constructing a social network of the audience of the target topic based on the text data and the text propagation behavior data, wherein nodes of the social network are used for representing the audience, the weight of each node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used for representing the text propagation behavior of the first audience to the second audience, and the weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior;
determining an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge;
determining a key audience of the target topic based on an importance evaluation parameter of the audience of the target topic.
The key audience determination method disclosed in the embodiment of fig. 1 may be implemented in or by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in one or more embodiments of the present specification may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with one or more embodiments of the present disclosure may be embodied directly in hardware, in a software module executed by a hardware decoding processor, or in a combination of the hardware and software modules executed by a hardware decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may also perform the key audience determination method of fig. 1, which is not described herein again.
Of course, besides the software implementation, the electronic device in this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or logic devices.
This specification embodiment also proposes a computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a portable electronic device comprising a plurality of application programs, are capable of causing the portable electronic device to perform the method of the embodiment shown in fig. 6, and in particular to perform the following operations:
acquiring the text data and the text propagation behavior data of audiences of the target topic;
constructing a social network of the audience of the target topic based on the text data and the text propagation behavior data, wherein nodes of the social network are used for representing the audience, the weight of each node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used for representing the text propagation behavior of the first audience to the second audience, and the weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior;
determining an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge;
determining a key audience of the target topic based on an importance evaluation parameter of the audience of the target topic.
While certain embodiments of the present disclosure have been described above, other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
In short, the above description is only a preferred embodiment of the present disclosure, and is not intended to limit the scope of the present disclosure. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the present disclosure should be included in the scope of protection of one or more embodiments of the present disclosure.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Claims (10)
1. A method for determining a key audience, the method comprising:
acquiring the text data and the text propagation behavior data of audiences of the target topic;
constructing a social network of the audience of the target topic based on the text data and the text propagation behavior data, wherein nodes of the social network are used for representing the audience, the weight of each node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used for representing the text propagation behavior of the first audience to the second audience, and the weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior;
determining an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge;
determining a key audience of the target topic based on an importance evaluation parameter of the audience of the target topic.
2. The method of claim 1,
the textual data for an audience of the target topic includes at least one of:
the number of utterances from the audience member,
the number of reviews the audience receives may be,
the number of praise received by the audience,
the number of times the audience received the reward,
the amount of the reward received by the audience,
the number of times the audience's text is collected,
the number of publications that the audience receives shared by other audiences of the target topic.
3. The method of claim 1,
the message propagation behavior data corresponding to the message propagation behavior comprises at least one of the following data:
a number of times that the first audience member likes the second audience member,
a number of times the first audience commented on the second audience,
the number of times the first audience shares the prose with the second audience,
a number of times the first audience awards the second audience,
an amount that the first audience awards to the second audience,
the number of times the first audience collected the second audience's text.
4. The method of claim 1, wherein determining an importance assessment parameter for an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge comprises:
executing the specified steps on each second node in the social network in a circulating way until the importance evaluation parameters of the audiences represented by the nodes in the social network converge;
wherein the specifying step comprises:
determining a first importance assessment parameter for the second audience based on a weight of the second node in the social network;
determining a weight of a target node in the social network, wherein the target node is the first node pointing to the second node through a directed edge;
determining a second importance assessment parameter for the audience represented by the target node to pass to the second audience based on the weight of the target node and the weight of the target node pointing to the directed edge of the second node;
determining an importance rating parameter for the second audience based on the first importance rating parameter and the second importance rating parameter.
5. The method of claim 1, wherein determining an importance assessment parameter for an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge comprises:
determining importance evaluation parameters of audiences represented by the nodes in the social network based on the weights of the nodes and the weights of the directed edges in the social network and a PageRank algorithm;
wherein, the PageRank algorithm is as follows:
π(k+1)T＝(1-α)eT+απ(k)TV
wherein pi represents a matrix of importance evaluation parameters of nodes in the social network, pi(k)TA matrix, π, of importance evaluation parameters representing nodes in the social network before iteration(k+1)TA matrix of importance assessment parameters representing nodes in the social network after iteration, α being a damping coefficient, eTRepresenting a unit row vector, V representing a voting matrix, the element V in VijRepresenting a node v in the social networkiTo node vjProportion of assigned weights, vijIs equal to the first node viPointing to said second node vjDirected edge e ofijThe weight of (c).
6. The method of any of claims 1-5, wherein determining a key audience for the target topic based on an importance evaluation parameter for the audience of the target topic comprises:
ranking the audience of the target topic based on an importance evaluation parameter of the audience of the target topic;
and sequencing at least one audience meeting preset conditions from the audiences of the target topic, and determining the audiences as key audiences of the target topic.
7. The method of claim 6,
the step of determining at least one audience, of the audiences of the target topic, of which the sequence meets preset conditions as a key audience of the target topic comprises the following steps: ranking the audience with the importance evaluation parameters of the target topics at the top by a preset number of audiences, and determining the audience as the key audiences of the target topics;
the audience covered by the information spread by the audience with the preset number exceeds a first preset proportion in the audience of the target topic; or the ratio of the information amount of interaction between the preset number of audiences and the rest of audiences of the target topic in the total information amount of the target topic exceeds a second preset ratio.
8. A key audience determination apparatus, the apparatus comprising:
the data acquisition module is used for acquiring the text data and the text propagation behavior data of the audiences of the target topic;
a network construction module, configured to construct a social network of an audience of the target topic based on the text data and the text propagation behavior data, where a node of the social network is used to represent the audience, a weight of the node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used to represent a text propagation behavior of the first audience to the second audience, and a weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior;
a parameter determination module, configured to determine an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge;
and the key audience determining module is used for determining the key audience of the target topic based on the importance evaluation parameter of the audience of the target topic.
9. An electronic device, comprising:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring the text data and the text propagation behavior data of audiences of the target topic;
constructing a social network of the audience of the target topic based on the text data and the text propagation behavior data, wherein nodes of the social network are used for representing the audience, the weight of each node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used for representing the text propagation behavior of the first audience to the second audience, and the weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior;
determining an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge;
determining a key audience of the target topic based on an importance evaluation parameter of the audience of the target topic.
10. An electronic device, comprising:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring the text data and the text propagation behavior data of audiences of the target topic;
constructing a social network of the audience of the target topic based on the text data and the text propagation behavior data, wherein nodes of the social network are used for representing the audience, the weight of each node is determined by the text data of the audience represented by the node, a directed edge from a first node to a second node in the social network is used for representing the text propagation behavior of the first audience to the second audience, and the weight of the directed edge is determined by the text propagation behavior data corresponding to the text propagation behavior;
determining an importance evaluation parameter of an audience represented by a node in the social network based on the weight of the node in the social network and the weight of the directed edge;
determining a key audience of the target topic based on an importance evaluation parameter of the audience of the target topic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911100324.1A CN110929168A (en) | 2019-11-12 | 2019-11-12 | Key audience determining method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911100324.1A CN110929168A (en) | 2019-11-12 | 2019-11-12 | Key audience determining method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110929168A true CN110929168A (en) | 2020-03-27 |
Family
ID=69852806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911100324.1A Pending CN110929168A (en) | 2019-11-12 | 2019-11-12 | Key audience determining method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929168A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617279A (en) * | 2013-12-09 | 2014-03-05 | 南京邮电大学 | Method for achieving microblog information spreading influence assessment model on basis of Pagerank method |
| CN104216954A (en) * | 2014-08-20 | 2014-12-17 | 北京邮电大学 | Prediction device and prediction method for state of emergency topic |
| CN105260474A (en) * | 2015-10-29 | 2016-01-20 | 俞定国 | Microblog user influence computing method based on information interaction network |
| CN106991617A (en) * | 2017-03-30 | 2017-07-28 | 武汉大学 | A kind of microblogging social networks extraction algorithm based on Information Communication |
| CN107341571A (en) * | 2017-06-27 | 2017-11-10 | 华中科技大学 | A kind of social network user behavior prediction method based on quantization social effectiveness |
| CN109063010A (en) * | 2018-07-11 | 2018-12-21 | 成都爱为贝思科技有限公司 | A kind of leader of opinion's method for digging based on PageRank |
| CN109145090A (en) * | 2018-08-31 | 2019-01-04 | 东北大学 | A kind of microblog users emotion influence power analysis method based on deep learning |
| CN109684454A (en) * | 2018-12-26 | 2019-04-26 | 北京壹捌零数字技术有限公司 | A kind of social network user influence power calculation method and device |
-
2019
- 2019-11-12 CN CN201911100324.1A patent/CN110929168A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617279A (en) * | 2013-12-09 | 2014-03-05 | 南京邮电大学 | Method for achieving microblog information spreading influence assessment model on basis of Pagerank method |
| CN104216954A (en) * | 2014-08-20 | 2014-12-17 | 北京邮电大学 | Prediction device and prediction method for state of emergency topic |
| CN105260474A (en) * | 2015-10-29 | 2016-01-20 | 俞定国 | Microblog user influence computing method based on information interaction network |
| CN106991617A (en) * | 2017-03-30 | 2017-07-28 | 武汉大学 | A kind of microblogging social networks extraction algorithm based on Information Communication |
| CN107341571A (en) * | 2017-06-27 | 2017-11-10 | 华中科技大学 | A kind of social network user behavior prediction method based on quantization social effectiveness |
| CN109063010A (en) * | 2018-07-11 | 2018-12-21 | 成都爱为贝思科技有限公司 | A kind of leader of opinion's method for digging based on PageRank |
| CN109145090A (en) * | 2018-08-31 | 2019-01-04 | 东北大学 | A kind of microblog users emotion influence power analysis method based on deep learning |
| CN109684454A (en) * | 2018-12-26 | 2019-04-26 | 北京壹捌零数字技术有限公司 | A kind of social network user influence power calculation method and device |
Non-Patent Citations (1)
| Title |
|---|
| 吴岘辉: "面向社交网络的社会影响力分析及意见领袖挖掘研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6367289B2 (en) | Network-oriented product rollout in online social networks | |
| US9276894B2 (en) | Resource management of social network applications | |
| US9542503B2 (en) | Estimation of closeness of topics based on graph analytics | |
| JP5944927B2 (en) | Sponsor article unit generation from organic activity streams | |
| US20100049534A1 (en) | Determining User Affinity Towards Applications on a Social Networking Website | |
| JP6379309B2 (en) | Geometric | |
| KR100952391B1 (en) | System and method for evaluating contents on the internet network and computer readable medium processing the method | |
| US20060059130A1 (en) | System and method of automatically modifying an online dating service search using compatibility feedback | |
| US20220012772A1 (en) | Systems and methods for leveraging social queuing to identify and prevent ticket purchaser simulation | |
| JP2016532943A (en) | Large page recommendation in online social networks | |
| US9418119B2 (en) | Method and system to determine a category score of a social network member | |
| JP7119124B2 (en) | Action indicator for search behavior output element | |
| US8874559B1 (en) | Ranking and ordering items in user-streams | |
| KR102162544B1 (en) | Integration of messaging systems and third party programs | |
| US20110321129A1 (en) | Disambiguating online identities | |
| RU2649797C1 (en) | Interactive system, method and computer reading medium data of presentation of advertising content | |
| JP6349331B2 (en) | Aggregation of contacts in social networks | |
| WO2017003710A1 (en) | Automatic invitation delivery system | |
| US20110307465A1 (en) | System and method for metadata transfer among search entities | |
| JP2016539580A (en) | Content owner module | |
| JP6255098B2 (en) | Serving content in time slots on client computing devices | |
| US20150278836A1 (en) | Method and system to determine member profiles for off-line targeting | |
| CN110929168A (en) | Key audience determining method and device and electronic equipment | |
| Wang et al. | A cooperation based metric for mobile applications recommendation | |
| US10061817B1 (en) | Social ranking for apps |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: No.27, 1st floor, building 14, Haidian Road, zhongjiancai District, Beijing 100096 Applicant after: Beijing PERCENT Technology Group Co.,Ltd. Address before: 100096 101 / F, building 14, 27 Jiancai Middle Road, Haidian District, Beijing Applicant before: BEIJING BAIFENDIAN INFORMATION SCIENCE & TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200327 |