An Account of Opinion Implicatures
This work addresses the need for deeper automatic interpretation of subjective language in natural language processing, though it is incremental as it builds on existing sentiment analysis by focusing on implicatures.
The paper tackles the problem of interpreting implicit opinions in text, introducing a rule-based framework for analyzing opinion implicatures that recognizes implicit sentiments and beliefs toward events and entities, producing richer interpretations than typical sentiment analysis.
While previous sentiment analysis research has concentrated on the interpretation of explicitly stated opinions and attitudes, this work initiates the computational study of a type of opinion implicature (i.e., opinion-oriented inference) in text. This paper described a rule-based framework for representing and analyzing opinion implicatures which we hope will contribute to deeper automatic interpretation of subjective language. In the course of understanding implicatures, the system recognizes implicit sentiments (and beliefs) toward various events and entities in the sentence, often attributed to different sources (holders) and of mixed polarities; thus, it produces a richer interpretation than is typical in opinion analysis.