CLNov 1, 2024

Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis

arXiv:2411.00691v123 citationsh-index: 1Has CodeProceedings of the Second Workshop on Social Influence in Conversations (SICon 2024)
Originality Incremental advance
AI Analysis

This work addresses data scarcity in code-mixed sentiment analysis for multilingual societies, but it is incremental as it builds on existing augmentation techniques.

The authors tackled the problem of limited data for code-mixed sentiment analysis by using a large language model to generate synthetic data, which improved the F1 score by 9.32% in Spanish-English but showed limited benefits in Malayalam-English with strong natural data.

Code-mixing (CM), where speakers blend languages within a single expression, is prevalent in multilingual societies but poses challenges for natural language processing due to its complexity and limited data. We propose using a large language model to generate synthetic CM data, which is then used to enhance the performance of task-specific models for CM sentiment analysis. Our results show that in Spanish-English, synthetic data improved the F1 score by 9.32%, outperforming previous augmentation techniques. However, in Malayalam-English, synthetic data only helped when the baseline was low; with strong natural data, additional synthetic data offered little benefit. Human evaluation confirmed that this approach is a simple, cost-effective way to generate natural-sounding CM sentences, particularly beneficial for low baselines. Our findings suggest that few-shot prompting of large language models is a promising method for CM data augmentation and has significant impact on improving sentiment analysis, an important element in the development of social influence systems.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes