Unlock instant, AI-driven research and patent intelligence for your innovation.

A Semantic Social Network Community Discovery Method Based on Topic Influence Percolation

A social network and community discovery technology, applied in the field of semantic social network community discovery based on topic influence seepage, can solve the problems of inability to describe the acceptance of text topics, low cohesion of community results, insufficient internal consistency, etc.

Active Publication Date: 2021-07-30
HARBIN UNIV OF SCI & TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a semantic social network community discovery method based on topic influence seepage. The technical problem to be solved is that the current semantic community recognition algorithm cannot describe the user's acceptance of text topics, resulting in relatively low cohesion of the output community results. The problem of low and insufficient internal consistency

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Semantic Social Network Community Discovery Method Based on Topic Influence Percolation
  • A Semantic Social Network Community Discovery Method Based on Topic Influence Percolation
  • A Semantic Social Network Community Discovery Method Based on Topic Influence Percolation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0106] A semantic social network community discovery method based on topic influence seepage, the semantic social network community discovery method comprises the following steps:

[0107] Step 1: Construct the semantic space coordinate representation of the semantic social network nodes;

[0108] Step 2: While constructing step 1, construct the differential equation of seepage influence based on the topic of seepage mechanics;

[0109] Step 3: According to the topic influence seepage differential equation in step 2, solve the topic influence partial differential equation;

[0110] Step 4: Formulate the game rules for generating communities according to Step 3;

[0111] Step 5: In the game rules of step 4, select the seed node with the most influential topic as the initial unbalanced node of influence seepage;

[0112] Step 6: Use the game rules in step 4 and the initial unbalanced nodes in step 5 to generate a social network community structure.

[0113] Further, the step ...

Embodiment 2

[0201] A Semantic Social Network Community Discovery Method SGSC Based on Topic Influence Seepage.

[0202] Step 1: Generate the semantic space coordinate representation of the semantic social network nodes based on the LDA model that comes with the Python toolkit Gensim.

[0203] Step 2: Based on the seepage theory in the field of physics, construct a partial differential equation of topic influence seepage in semantic space based on instantaneous point source functions.

[0204] Step 3: Solve the partial differential equation of topic influence, and construct the expression of topic influence seepage intensity.

[0205] Step 4: Formulate the game rules for generating communities. Accept and forward topics with high influence seepage intensity and social individuals are interested in, and finally realize the maximization of benefits and reach Nash equilibrium.

[0206] Step 5: Select the unbalanced node with the largest influence seepage intensity as the initial seed node, ...

Embodiment 3

[0211] Suppose there is a weighted directed network G=(V,E), as attached figure 2 shown.

[0212] According to formula (19), the weight adjacency matrix can be calculated as follows:

[0213]

[0214] Then the transition matrix can be obtained:

[0215]

[0216] Propagate spatial coordinates according to topic in step 2 The available topic propagation space coordinate matrix Z i,j :

[0217]

[0218] Calculate the influence value iteratively for each node according to the formula (20), and convert it into a topic influence value, and store each node in the seedSet and hashMap according to the topic influence, as shown in the following table:

[0219] Table 1 Topic influence of each node

[0220] node ID topic influence value 1 31.15 2 38.3 3 88.65 4 607.25 5 57.5 6 346.1 7 38.0 8 76.7 9 6.4 10 6.4 11 6.4 12 6.4 13 6.4 14 6.4

[0221] The node 4 with the most influential topic...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a semantic social network community discovery method based on topic influence percolation. Step 1: Construct the semantic space coordinate representation of semantic social network nodes; Step 2: Construct the topic influence seepage differential equation based on seepage mechanics at the same time as Step 1; Step 3: Solve the topic according to the topic influence seepage differential equation in Step 2 Partial differential equation of influence; step 4: formulate the game rules for generating communities according to step 3; step 5: select the seed node with the most influential topic in the game rules of step 4 as the initial unbalanced node of influence seepage; step 6: use The game rules in step 4 and the initial unbalanced nodes in step 5 generate a social network community structure. Existing methods only use the similarity of topics as the community generation standard, which will reduce the consistency of the internal nodes of the community, and the cohesion of the community is slightly insufficient.

Description

technical field [0001] The invention belongs to the field of semantic social networks; in particular, it relates to a method for discovering communities in semantic social networks based on percolation of topic influence. Background technique [0002] Semantic social network is a new type of social network composed of nodes, links and documents. Among them, a node represents an individual in a semantic social network; a link represents a relationship between nodes, such as a following relationship in a Weibo social network, a citation relationship in a scientific paper network, etc.; a document represents a text published by a network individual, such as a Weibo post , abstracts, etc. Compared with the traditional social network that only considers the network topology, the semantic social network contains rich topic attributes (topics). The user's post contains the user's views and attitudes on social events. It can be seen that the semantic social network is better at d...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F40/30G06F17/13G06F17/15G06F17/16G06Q50/00
CPCG06F17/13G06F17/15G06F17/16G06Q50/01G06F40/30
Inventor 杨海陆任旺张金陈德运王莉莉
Owner HARBIN UNIV OF SCI & TECH