From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis

Stanisław Woźniak, Jan Kocoń
12/7/2023
cs.CLcs.AIcs.LG

No official code found. Best implementation: CLARIN-PL/text-augumentation-with-chatgpt (3 stars, last commit 2023-10-12).

Abstract

In the era of artificial intelligence, data is gold but costly to annotate. The paper demonstrates a groundbreaking solution to this dilemma using ChatGPT for text augmentation in sentiment analysis. We leverage ChatGPT's generative capabilities to create synthetic training data that significantly improves the performance of smaller models, making them competitive with, or even outperforming, their larger counterparts. This innovation enables models to be both efficient and effective, thereby reducing computational cost, inference time, and memory usage without compromising on quality. Our work marks a key advancement in the cost-effective development and deployment of robust sentiment analysis models.

View on arXivView PDF

Code Implementations(1)

CLARIN-PL/text-augumentation-with-chatgptCommunity100%

Source code for paper "From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis" published at the 13th ICDM Workshop on Sentiment Elicitation from Natural Text for Information Retrieval and Extraction (SENTIRE) organized during the 23rd IEEE International Conference on Data Mining (ICDM 2023)

30Python, Jupyter NotebookOct 12, 20233 years ago

Similar Papers

Leveraging ChatGPT As Text Annotation Tool For Sentiment Analysis

84% match2023

Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks

83% match2023

Sentiment Analysis in the Era of Large Language Models: A Reality Check

83% match1 repo1152023

Bias in Emotion Recognition with ChatGPT

83% match2023

Will Affective Computing Emerge from Foundation Models and General AI? A First Evaluation on ChatGPT

82% match2023

Natural Language Processing Through Transfer Learning: A Case Study on Sentiment Analysis

82% match2023

Cite this paper

@article{woniak2023from,
  title  = {From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis},
  author = {Stanisław Woźniak and Jan Kocoń},
  year   = {2023},
  eprint = {2312.04720},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.04720v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.04720.svg)](https://codeofpaper.com/paper/2312.04720)

Discussion