Research links mood of user posts in Odnoklassniki to weather

Researchers of the HSE Graduate School of Business used machine learning to review 2.7 million user posts on the Odnoklassniki social network. They found warm weather and light breezes to be associated with the higher share of posts expressing a positive mood. The study findings have been published in PeerJ Computer Science.

Sergey Smetanin, doctoral student of the HSE Graduate School of Business Department of Business Informatics, used natural language processing techniques to study the relationship between weather conditions and the sentiments expressed by social media users in their posts. He analysed a large sample of texts posted by users on Odnoklassniki (OK), a social network visited by more than 38 million people in Russia every month.

It was found that maximum daily temperatures between +20°C and +25°C were associated with the highest relative number of posts expressing positive sentiments, whereas a 15–20°C difference between the maximum and minimum daily temperatures was associated with fewer positive posts. A light breeze (between 5 to 11 km/h) was associated with a positive mood in user posts.  

The study used a dataset of 2.7 million Russian-language posts published on OK. Each dataset entry contained an anonymised user identifier, the text, the time of publication, and the city in which the author was located when posting. 

The data was processed using RuRoBERTA-Large-RuSentiment (a machine learning model for natural language processing) and classified according to the mood expressed in the posts. The study authors constructed a daily city-level expressed positive sentiment metric and studied its dynamics relative to daily weather conditions via regression modelling. 

'It seems obvious that weather can affect mood, but research focusing on this relationship often produces contradictory results. Over the past decade, the spread of social media use and the advancement of natural language processing have made it possible to study the relationship between weather conditions and internet users' moods. It is clearly important for businesses, when designing special offers and promotions, to understand and take into account changes in consumer behaviour caused by external factors,' explains Mikhail Komarov, Professor of the HSE Graduate School of Business Department of Business Informatics and academic supervisor of the project.

'This study is one of the first in this area of research. By focusing on social media posts, we were able to analyse more data than would have ever been possible using a traditional survey,' says study author Sergey Smetanin.