A Comparison of Techniques for Sentiment Classification of Film Reviews

TL;DR

This paper compares lexicon-based and machine learning methods for film review sentiment classification, demonstrating machine learning's superiority and exploring feature impacts and potential enhancements.

Contribution

It provides a comparative analysis of sentiment classification techniques, highlighting the effectiveness of machine learning over lexicon-based methods and examining feature influences.

Findings

Machine learning outperforms lexicon-based classification.

Adding more features does not always improve performance.

Simple lexicon-based methods can achieve good results.

Abstract

We undertake the task of comparing lexicon-based sentiment classification of film reviews with machine learning approaches. We look at existing methodologies and attempt to emulate and improve on them using a 'given' lexicon and a bag-of-words approach. We also utilise syntactical information such as part-of-speech and dependency relations. We will show that a simple lexicon-based classification achieves good results however machine learning techniques prove to be the superior tool. We also show that more features do not necessarily deliver better performance as well as elaborate on three further enhancements not tested in this article.