Social Network Community Detection Based on Textual Content Similarity and Sentimental Tendency

TL;DR

This paper introduces a novel community detection algorithm for social networks that incorporates textual content similarity and sentimental tendency, improving the analysis of shared travel discussions on social platforms.

Contribution

It proposes a new algorithm combining network structure, content similarity, and sentiment analysis for more effective community detection in social networks.

Findings

High modularity in detected communities

Effective analysis of shared travel opinions

Improved community detection accuracy

Abstract

Shared travel has gradually become one of the hot topics discussed on social networking platforms such as Micro Blog. In a timely manner, deeper network community detection on the evaluation content of shared travel in social networks can effectively conduct research and analysis on the public opinion orientation related to shared travel, which has great application prospects. The existing community detection algorithms generally measure the similarity of nodes in the network from the perspective of spatial distance. This paper proposes a Community detection algorithm based on Textual content Similarity and sentimental Tendency (CTST), considering the network structure and node attributes at the same time. The content similarity and sentimental tendency of network community users are taken as node attributes, and on this basis, an undirected weighted network is constructed for community detection. This paper conducts experiments with actual data and analyzes the experimental results. It is found that the modularity of the community detection results is high and the effect is good.