Social Climate Analysis based on Open Data

Abstract

The paper proposes an approach to identifying problematic issues according to open sources for socially oriented topics. The approach involves the use of texts and metadata of publications in open thematic groups and on public pages of users in social media. A multi-stage processing of publications is performed: data collection, spam removal, filtering by problem area, sentiment analysis, classification by topic, and clustering. The software implementation of the proposed approach is based on the Integrated Monitoring Digital Platform. Experimental testing was carried out on the data of the VK social media. The application of the approach makes it possible to identify acute social problematic issues of the administrative region in the operational mode.