SentMix-3L: A Bangla-English-Hindi Code-Mixed Dataset for Sentiment Analysis
This addresses a gap in resources for multilingual sentiment analysis, but is incremental as it extends existing two-language datasets to three languages.
The paper tackles the lack of datasets for sentiment analysis on code-mixed text involving three languages by introducing SentMix-3L, a Bangla-English-Hindi dataset, and finds that zero-shot prompting with GPT-3.5 outperforms transformer-based models on this dataset.
Code-mixing is a well-studied linguistic phenomenon when two or more languages are mixed in text or speech. Several datasets have been build with the goal of training computational models for code-mixing. Although it is very common to observe code-mixing with multiple languages, most datasets available contain code-mixed between only two languages. In this paper, we introduce SentMix-3L, a novel dataset for sentiment analysis containing code-mixed data between three languages Bangla, English, and Hindi. We carry out a comprehensive evaluation using SentMix-3L. We show that zero-shot prompting with GPT-3.5 outperforms all transformer-based models on SentMix-3L.