How Do I Feel? Identifying Emotional Expressions on Facebook Reactions Using Clustering Mechanism

Abstract

The recognition of emotions and feelings through computer technology and devices has been widely explored in recent years. Social networks have become a natural environment in which users express their feelings and opinions through social media, and this includes their Facebook reactions. The aim of this study was to investigate whether the emoticons have chosen by users in social network news actually express the emotions they wish to express, having as indicative, the polarity of the emotions, and the six basic emotions. The data collection was carried out following three courses of action: (1) survey of the posts with higher reactions rates of popular news pages; (2) selection of news by a panel of experts to verify its reliability; and (3) identification of reactions, polarity, and basic emotions flagged by Facebook users for each news item. Finally, an Expectation-Maximization algorithm was deployed to find the relationship between the reactions and the basic emotions signaled. The results made it possible to determine the polarity and the correlation of the reactions with the emotional expressions. This suggests that the use of reactions in feelings analysis algorithms can increase the confidence in determining the emotion that the content reflects and the emotional state of the social network users.

Keywords

• Facebook reactions
• emoticons
• recognition of emotions
• emotional state
• sentiment analysis
• social media