SentiQ: A Probabilistic Logic Approach to Enhance Sentiment Analysis Tool Quality

TL;DR

SentiQ introduces a probabilistic logic framework that enhances sentiment analysis tools by reducing inconsistencies and improving accuracy through semantic rule integration.

Contribution

The paper presents SentiQ, a novel unsupervised Markov logic network approach that injects semantic rules to improve sentiment analysis accuracy.

Findings

SentiQ reduces polarity inconsistencies in sentiment analysis.

SentiQ improves overall sentiment classification accuracy.

Preliminary results show effectiveness of the approach.

Abstract

The opinion expressed in various Web sites and social-media is an essential contributor to the decision making process of several organizations. Existing sentiment analysis tools aim to extract the polarity (i.e., positive, negative, neutral) from these opinionated contents. Despite the advance of the research in the field, sentiment analysis tools give \textit{inconsistent} polarities, which is harmful to business decisions. In this paper, we propose SentiQ, an unsupervised Markov logic Network-based approach that injects the semantic dimension in the tools through rules. It allows to detect and solve inconsistencies and then improves the overall accuracy of the tools. Preliminary experimental results demonstrate the usefulness of SentiQ.