The role of emotional variables in the classification and prediction of collective social dynamics

TL;DR

This study shows that incorporating emotional variables improves the classification of social activities in Twitter data during the Olympics, but may hinder prediction accuracy, highlighting the importance of emotional factors in social dynamics analysis.

Contribution

It introduces a data mining approach that integrates emotional variables to analyze collective social dynamics in social media data.

Findings

Emotional variables improve classification accuracy of social activities.

Including emotional variables decreases activity prediction quality.

The approach is adaptable to various prediction and classification tasks.

Abstract

We demonstrate the power of data mining techniques for the analysis of collective social dynamics within British Tweets during the Olympic Games 2012. The classification accuracy of online activities related to the successes of British athletes significantly improved when emotional components of tweets were taken into account, but employing emotional variables for activity prediction decreased the classifiers' quality. The approach could be easily adopted for any prediction or classification study with a set of problem-specific variables.