Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning

TL;DR

This paper presents a semi-supervised learning approach using label propagation and graph-based pseudo-labeling to significantly cut down labeling costs in sentiment analysis, demonstrating effectiveness in text classification.

Contribution

It introduces a novel graph-based semi-supervised method leveraging manifold assumptions and deep neural networks for sentiment analysis, reducing the need for extensive labeled data.

Findings

Effective reduction in labeling costs demonstrated

Pseudo-labeling improves classification accuracy

Method outperforms traditional supervised approaches

Abstract

Labeling datasets is a noteworthy challenge in machine learning, both in terms of cost and time. This research, however, leverages an efficient answer. By exploring label propagation in semi-supervised learning, we can significantly reduce the number of labels required compared to traditional methods. We employ a transductive label propagation method based on the manifold assumption for text classification. Our approach utilizes a graph-based method to generate pseudo-labels for unlabeled data for the text classification task, which are then used to train deep neural networks. By extending labels based on cosine proximity within a nearest neighbor graph from network embeddings, we combine unlabeled data into supervised learning, thereby reducing labeling costs. Based on previous successes in other domains, this study builds and evaluates this approach's effectiveness in sentiment analysis, presenting insights into semi-supervised learning.