Seeking Sinhala Sentiment: Predicting Facebook Reactions of Sinhala Posts

TL;DR

This study analyzes Facebook reactions to Sinhala posts over a decade to develop and compare sentiment analysis models, finding binary classification most effective and that 'like' reactions can hinder other reaction predictions.

Contribution

It introduces models for Sinhala sentiment detection based on Facebook reactions, highlighting the effectiveness of binary classification and the impact of 'like' reactions.

Findings

Binary classification outperforms other models in accuracy.

Including 'like' reactions reduces prediction accuracy for other reactions.

Models effectively capture observer reactions to Sinhala content.

Abstract

The Facebook network allows its users to record their reactions to text via a typology of emotions. This network, taken at scale, is therefore a prime data set of annotated sentiment data. This paper uses millions of such reactions, derived from a decade worth of Facebook post data centred around a Sri Lankan context, to model an eye of the beholder approach to sentiment detection for online Sinhala textual content. Three different sentiment analysis models are built, taking into account a limited subset of reactions, all reactions, and another that derives a positive/negative star rating value. The efficacy of these models in capturing the reactions of the observers are then computed and discussed. The analysis reveals that binary classification of reactions, for Sinhala content, is significantly more accurate than the other approaches. Furthermore, the inclusion of the like reaction hinders the capability of accurately predicting other reactions.