Supervised Learning Based Approach To Aspect Based Sentiment Analysis

Abstract

What other people think or What other peoples opinion has always been an im- portant piece of information for most of us whenever we have to make a decision. Present day, World Wide Web o ers a great means to share knowledge, becoming one large repository of valuable opinions of di erent people on numerous prod- ucts and services. It is not straightforward to access these opinions because the available number is vast, and understanding what is actually meant has always been problematic with the complexity of human language. These texts could con- tain various attributes (or features) forming complex opinion relationships hidden inside large numbers of sentences. Most of the existing approaches for opinion mining are based on word-level analysis of texts and are able to detect only explicitly expressed opinions. In aspect-based sentiment analysis (ABSA) the aim is to identify the aspects of entities and the sentiment expressed for each aspect. The ultimate goal is to be able to generate summaries listing all the aspects and their overall polarity. In this thesis, we aim to investigate the e ectiveness of supervised learning meth- ods with text based features for the research problem of Aspect-Based Sentiment Analysis (ABSA), which attempts to capture both semantic and sentiment infor- mation encoded in user generated content such as product reviews. In particular, we target two ABSA sub-tasks: aspect category extraction and sentiment senti- ment prediction. We investigate the e ectiveness of supervised learning methods over di erent text based features, and evaluate the quality of domain-speci c fea- tures. Successful results were achieved by evaluating the proposed method using online customer review data spread over three diverse domains with the purpose of conducting domain-independent sentiment analysis. These experiments show state of the art promising results, proving that the proposed approach suits both domain dependent and domain independent sentiment analysis.