Abstract
As one of the major platforms of communication, social networks have become a valuable source of opinions and emotions. Considering that sharing of emotions offline and online is quite similar, historical posts from social networks seem to be a valuable source of data for measuring observable subjective well-being (OSWB). In this study, we calculated OSWB indices for the Russian-speaking segment of Twitter using the Affective Social Data Model for Socio-Technical Interactions. This model utilises demographic information and post-stratification techniques to make the data sample representative, by selected characteristics, of the general population of a country. For sentiment analysis, we fine-tuned RuRoBERTa-Large on RuSentiTweet and achieved new state-of-the-art results of F1 = 0.7229. Several calculated OSWB indicators demonstrated moderate Spearman’s correlation with the traditional survey-based net affect (rs = 0.469 and rs = 0.5332, p < 0.05) and positive affect (rs = 0.5177 and rs = 0.548, p < 0.05) indices in Russia.
Reference91 articles.
1. Subjective well-being: conceptualization, assessment and Russian specifics;Almakaeva;Monitoring of Public Opinion: Economic and Social Changes,2020
2. Demographic changes are not good for the Russian language;Arefyev;Demoskop Weekly,2013
3. Hierarchical deep learning: a promising technique for opinion monitoring and sentiment analysis in Russian-language social networks;Averchenkov,2015
4. Graph convolution network model to include dependency trees in classification of the text’s author’s gender;Bogachev,2020
5. Opportunities and limitations of digital footprints and machine learning methods in sociology;Bogdanov;Monitoring of Public Opinion: Economic and Social Changes,2021