Exploring the Flexibility and Accuracy of Sentiment Scoring Models through a Hybrid KNN-RNN-CNN Algorithm and ChatGPT

Abstract

This study aimed to address the limitations of sentiment analysis by developing a more accurate and flexible sentiment scoring model using ChatGPT in combination with KNN, RNN, and CNN algorithms. To achieve this, primary data from ChatGPT and secondary data from Kaggle were utilized for training. The model's performance was evaluated, yielding an impressive accuracy rate of 88.17%. This research underscores ChatGPT's pivotal role in offering theoretical insights and precise data for diverse applications. The novelty of this study lies in its innovative approach of combining KNN, RNN, and CNN algorithms to create a more adaptable and accurate sentiment scoring model. Additionally, the primary data from ChatGPT greatly enhances the creation of precise and relevant training data across various topics and languages. Despite these achievements, there remains a need for further exploration of testing methods to mitigate the impact of data limitations on result generalizability. Moreover, it is acknowledged that the model's effectiveness may be diminished when applied to languages other than English. Nevertheless, this research provides a promising avenue for users seeking enhanced and precise sentiment analysis by integrating KNN, RNN, and CNN algorithms with ChatGPT. The findings of this study can serve as a solid foundation for future research endeavors in the advancement of sophisticated and effective sentiment analysis technologies. Doi: 10.28991/HIJ-2023-04-02-06 Full Text: PDF