Subjectivity Identification Through Lexical Rules

We can deduce a discourse into utterances with two types of information: subjective and objective. Objective utterances are factual in nature and have a truth value that can be validated against a fact. On the other hand, subjective utterances contain the emotional state or opinion of a speaker more than factual information. Languages use different devices to demonstrate subjectivity. In this paper, we present a comparative analysis of various linguistic devices that languages use to demonstrate subjectivity. For that, we analyze subjective constructions in five Indian languages, formalize lexical rules for subjective constructions and implement a Lexical Rule-based FST for subjectivity identification. We evaluate the FST on test data from entertainment, lifestyle, politics, sports, and technology domains. Our system achieves 91% accuracy in politics domain and ~ 84% accuracy on average.