Unraveling Ambivalence: A Novel Approach for Sarcasm Detection in Sentiment Analysis

Emotion ontologies have been developed in order to capture affect, a comprehensive construct that encompasses discrete emotions and feelings. The utilization of these ontologies holds significant relevance within the realm of sentiment analysis research, which seeks to examine a consumer's perception and disposition towards a corporation or a specific product. However, there have been limited attempts to modify and utilize these ontologies. This study undertakes a thorough examination and integration of prior research on emotion ontologies with the aim of developing a filtering framework for the identification of ambivalence in reviews, specifically for the purpose of sarcasm detection. The objective of our study is to improve the precision and dependability of sentiment analysis outcomes through the effective management of ambivalent reviews. These reviews contain mixed and contradictory emotions, which can potentially include sarcasm. Sentiment analysis models can better read complex emotional expressions using the filtering framework, improving consumer attitude analysis.