A Community Discovery Method Based on User Interaction Reputation

Abstract

The invention discloses a community discovery method based on user interaction reputation. First, measure the influence of time, space, and behavior factors on user evaluation behavior by establishing a time-space-behavior three-layer model to measure the authenticity and reliability of user evaluation and calculate the user's direct and indirect reputation; then, based on the direct and indirect reputation calculation User reputation influence, select two users with the least difference from the core user reputation influence to establish a core triangular community and build other triangular communities to be expanded in sequence according to the level of reputation influence; finally, calculate the triangular community reputation and inter-community attribution, according to the community The reputation level is expanded step by step, and the degree of belonging between the community to be expanded and the original community is used as the standard to measure whether the community is merged into the original community, and the core triangular community is expanded. The division of users with the same reputation is realized, and the practical application value is relatively high.

Description

technical field [0001] The invention belongs to the technical field of community discovery in sharing mode, and in particular relates to a community discovery method based on user interaction reputation. Background technique [0002] With the development of sharing economy and mobile sensing technology, user reputation as a key factor determining the quality of information and service under participatory sensing has been widely valued and applied. Mining the commonality of user reputation and local community structure under social networks has also become a practical reality. Applied research hotspots. Early community discovery proposed non-overlapping community discovery methods based on algorithms such as graph segmentation, label propagation, hierarchical clustering, and modularity optimization. Overlapping community discovery methods for algorithms such as , density peak, etc. So far, although the research work on community discovery can identify the core points and is...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a community discovery method based on user interaction reputation, to solve the problem of ignoring user credibility and behavior authenticity in existing community discovery, and to realize the division of users with the same reputation

Images