Self-training Strategies for Sentiment Analysis: An Empirical Study
This work addresses the problem of optimizing self-training strategies for sentiment analysis, which is incremental as it builds on existing techniques without introducing a new paradigm.
The paper empirically studies various self-training strategies for sentiment analysis, examining their impact on small language models in few-shot settings and exploring the use of large language models to assist self-training, with experiments conducted on three real-world datasets.
Sentiment analysis is a crucial task in natural language processing that involves identifying and extracting subjective sentiment from text. Self-training has recently emerged as an economical and efficient technique for developing sentiment analysis models by leveraging a small amount of labeled data and a large amount of unlabeled data. However, given a set of training data, how to utilize them to conduct self-training makes a significant difference in the final performance of the model. We refer to this methodology as the self-training strategy. In this paper, we present an empirical study of various self-training strategies for sentiment analysis. First, we investigate the influence of the self-training strategy and hyper-parameters on the performance of traditional small language models (SLMs) in various few-shot settings. Second, we also explore the feasibility of leveraging large language models (LLMs) to help self-training. We propose and empirically compare several self-training strategies with the intervention of LLMs. Extensive experiments are conducted on three real-world sentiment analysis datasets.