Unsupervised and Knowledge-poor Approaches to Sentiment Analysis

Abstract

Sentiment analysis focuses upon automatic classification of a document’s sentiment (and more generally extraction of opinion from text). Ways of expressing sentiment have been shown to be dependent on what a document is about (domain-dependency). This com- plicates supervised methods for sentiment analysis which rely on extensive use of training data or linguistic resources that are usually either domain-specific or generic. Both kinds of resources prevent classifiers from performing well across a range of domains, as this requires appropriate in-domain (domain-specific) data. This thesis presents a novel unsupervised, knowledge-poor approach to sentiment ana- lysis aimed at creating a domain-independent and multilingual sentiment analysis system. The approach extracts domain-specific resources from documents that are to be processed, and uses them for sentiment analysis. This approach does not require any training corpora, large sets of rules or generic sentiment lexicons, which makes it domain- and language- independent but at the same time able to utilise domain- and language-specific informa- tion. The thesis describes and tests the approach, which is applied to different data, including customer reviews of various types of products, reviews of films and books, and news items; and to four languages: Chinese, English, Russian and Japanese. The approach is applied not only to binary sentiment classification, but also to three-way sentiment classification (positive, negative and neutral), subjectivity classification of documents and sentences, and to the extraction of opinion holders and opinion targets. Experimental results suggest that the approach is often a viable alternative to supervised systems, especially when applied to large document collections.