Semi-supervised and Transfer learning approaches for low resource sentiment classification

TL;DR

This paper explores semi-supervised and transfer learning techniques to improve sentiment classification accuracy in low-resource scenarios, especially when labeled data is scarce or unavailable for new languages or cultures.

Contribution

It demonstrates how dense feature representations, pre-training, and manifold regularization can significantly boost sentiment classification performance in low-resource settings.

Findings

Proposed methods outperform purely supervised models.

Significant improvements with limited training data.

Effective in cross-corpora and single corpus settings.

Abstract

Sentiment classification involves quantifying the affective reaction of a human to a document, media item or an event. Although researchers have investigated several methods to reliably infer sentiment from lexical, speech and body language cues, training a model with a small set of labeled datasets is still a challenge. For instance, in expanding sentiment analysis to new languages and cultures, it may not always be possible to obtain comprehensive labeled datasets. In this paper, we investigate the application of semi-supervised and transfer learning methods to improve performances on low resource sentiment classification tasks. We experiment with extracting dense feature representations, pre-training and manifold regularization in enhancing the performance of sentiment classification systems. Our goal is a coherent implementation of these methods and we evaluate the gains achieved by these methods in matched setting involving training and testing on a single corpus setting as well as two cross corpora settings. In both the cases, our experiments demonstrate that the proposed methods can significantly enhance the model performance against a purely supervised approach, particularly in cases involving a handful of training data.