Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews

TL;DR

This paper compares various machine learning methods for sentiment analysis of movie reviews, combining generative and discriminative models to improve accuracy, and provides reproducible code for future research.

Contribution

It introduces an ensemble approach combining generative and discriminative techniques, achieving state-of-the-art results on IMDB reviews with reproducible experiments.

Findings

Strong results on IMDB dataset

Generative models complement discriminative methods

Reproducible code facilitates further research

Abstract

Sentiment analysis is a common task in natural language processing that aims to detect polarity of a text document (typically a consumer review). In the simplest settings, we discriminate only between positive and negative sentiment, turning the task into a standard binary classification problem. We compare several ma- chine learning approaches to this problem, and combine them to achieve the best possible results. We show how to use for this task the standard generative lan- guage models, which are slightly complementary to the state of the art techniques. We achieve strong results on a well-known dataset of IMDB movie reviews. Our results are easily reproducible, as we publish also the code needed to repeat the experiments. This should simplify further advance of the state of the art, as other researchers can combine their techniques with ours with little effort.