Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910411595448320 |
|---|---|
| author | El-Hajjami, Abdelkarim Fafin, Nicolas Salinesi, Camille |
| author_facet | El-Hajjami, Abdelkarim Fafin, Nicolas Salinesi, Camille |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_11547 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT El-Hajjami, Abdelkarim Fafin, Nicolas Salinesi, Camille Artificial Intelligence Software Engineering 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. |
| title | Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT |
| topic | Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2311.11547 |