Seeking Sinhala Sentiment: Predicting Facebook Reactions of Sinhala Posts
This addresses sentiment analysis for Sinhala content, an incremental domain-specific problem for social media and NLP researchers.
The paper tackled sentiment detection for Sinhala Facebook posts by modeling user reactions, finding that binary classification was significantly more accurate than other approaches, with the inclusion of 'like' reactions hindering prediction of other reactions.
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.