Abstract
Topic modeling has become a popular approach to identify semantic structures in text corpora. Despite its wide applications, interpreting the outputs of topic models remains challenging. This paper presents an initial study regarding a new approach to better understand this output, leveraging the large language model ChatGPT. Our approach is built on a three- stage process where we first use topic modeling to identify the main topics in the corpus. Then, we ask a domain expert to assign themes to these topics and prompt ChatGPT to generate human- readable summaries of the topics. Lastly, we compare the human- and machine-produced interpretations. The domain expert found half of ChatGPT’s descriptions useful. This explorative work demonstrates ChatGPT’s capability to describe topics accurately and provide useful insights if prompted accurately.
| Original language | English |
|---|---|
| Title of host publication | The 20th World Congress of the International Fuzzy Systems Association (IFSA 2023) |
| Publisher | International Fuzzy Systems Association |
| Pages | 269-275 |
| Number of pages | 7 |
| Publication status | Published - 31 Aug 2023 |
| Event | The 20th World Congress of the International Fuzzy Systems Association - EXCO, Daegu, Korea, Republic of Duration: 20 Aug 2023 → 23 Aug 2023 |
Conference
| Conference | The 20th World Congress of the International Fuzzy Systems Association |
|---|---|
| Abbreviated title | IFSA 2023 |
| Country/Territory | Korea, Republic of |
| City | Daegu |
| Period | 20/08/23 → 23/08/23 |
Keywords
- ChatGPT
- Electronic Health Records
- Fuzzy Topic Models
- Large Language Models
- Prompt Engineering
- Topic Modeling