Thumbs up? Sentiment Classification using Machine Learning Techniques

TL;DR

This paper evaluates machine learning methods for sentiment classification of movie reviews, showing they outperform human baselines but face unique challenges compared to topic classification.

Contribution

It compares Naive Bayes, maximum entropy, and SVM techniques for sentiment analysis, highlighting their strengths and limitations.

Findings

ML methods outperform human baselines

Performance is lower than topic classification

Challenges in sentiment classification identified

Abstract

We consider the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative. Using movie reviews as data, we find that standard machine learning techniques definitively outperform human-produced baselines. However, the three machine learning methods we employed (Naive Bayes, maximum entropy classification, and support vector machines) do not perform as well on sentiment classification as on traditional topic-based categorization. We conclude by examining factors that make the sentiment classification problem more challenging.