Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT
This incremental study addresses requirements classification for software engineering, providing empirical insights into AI method selection.
The paper compared ChatGPT models (gpt-3.5-turbo and gpt-4) in zero-shot and few-shot settings against SVM and LSTM for requirements classification across five datasets, finding no single best technique overall and that few-shot learning mainly helps when zero-shot performance is low.
Recently, Large Language Models like ChatGPT have demonstrated remarkable proficiency in various Natural Language Processing tasks. Their application in Requirements Engineering, especially in requirements classification, has gained increasing interest. This paper reports an extensive empirical evaluation of two ChatGPT models, specifically gpt-3.5-turbo, and gpt-4 in both zero-shot and few-shot settings for requirements classification. The question arises as to how these models compare to traditional classification methods, specifically Support Vector Machine and Long Short-Term Memory. Based on five different datasets, our results show that there is no single best technique for all types of requirement classes. Interestingly, the few-shot setting has been found to be beneficial primarily in scenarios where zero-shot results are significantly low.