The development of sentiment analysis from a linguistic perspective

Abstract EN

Although sentiment analysis by definition is that field of NLP that focuses on analyzing texts that that focus on evaluating, analyzing and detecting the state of mind of the human beings towards various topics and a range of domains, most of the studies deal with it as an opinion mining field.

Yet, opinion mining is just one sub-field of three sub-fields under the umbrella of sentiment analysis which are opinion mining, emotion mining and ambiguity detection.

Accordingly, ambiguity detection sub-field is considered to be a mix of the other two as thanks to its linguistic nature that consider statistical analysis syntactic-semantic levels of analysis are not adequate.

Henceforth, the current paper proposes digging deeply to reach pragmatic and socio-pragmatic which are deeper linguistic levels of analysis in order to get a closer understanding to the nature human language and communication.

Moreover, in order to eliminate ambiguity and avoid misjudgments over texts and social media posts specifically in the sub-tasks of detecting hate speech, it suggests using the theory of (im)politeness, with its three main perspectives, which is a pioneer theory in the socio-pragmatic field of linguistics.