A Network Analysis Approach to Detecting Social Issues with Web-Based Data

Abstract

Social issues refer to topics that occur and become increasingly focused in various areas of society. Because of the evolutionary pattern of issues, detecting social issues requires monitoring various stories formed by members of society over time. Various studies related to issue detection have been preceded, but it is necessary to supplement in two aspects: presenting the time when issues occurred and prioritizing issues by urgency. As a remedy, the purpose of this study is to propose a new approach to detecting social issues from web-based data through network analysis. Since stories that form social issues are composed of various keywords and topics, this study detects social issues by monitoring keyword co-occurrence networks constructed with web-based data. Specifically, this approach uses network structure entropy to identify a time period at which social issues occur. Next, a community detection algorithm is used to extract social issue candidates in the identified time period. Finally, social issues are detected by deriving the priority of social issue candidates through the centrality index of keywords constituting the candidates. This study detected South Korean social issue topics that attract people’s attention among the various topics of society. The proposed approach contributes to the existing literature by identifying when social issues occurred quantitatively based on the characteristics of issues. In addition, since the proposed approach detects urgent issues to be dealt with priority, it can support timely responses to social issues.