Generative AI for automatic topic labelling
This addresses the need for automated labelling in topic modeling for researchers analyzing scientific trends, but it is incremental as it applies existing LLMs to a known bottleneck.
The paper tackled the problem of manual interpretation in topic modeling by evaluating three LLMs (flan, GPT-4o, GPT-4 mini) for automatic topic labelling on a dataset of 34,797 scientific articles in biology, finding that GPT models accurately label topics and 3-word labels are best for capturing complexity.
Topic Modeling has become a prominent tool for the study of scientific fields, as they allow for a large scale interpretation of research trends. Nevertheless, the output of these models is structured as a list of keywords which requires a manual interpretation for the labelling. This paper proposes to assess the reliability of three LLMs, namely flan, GPT-4o, and GPT-4 mini for topic labelling. Drawing on previous research leveraging BERTopic, we generate topics from a dataset of all the scientific articles (n=34,797) authored by all biology professors in Switzerland (n=465) between 2008 and 2020, as recorded in the Web of Science database. We assess the output of the three models both quantitatively and qualitatively and find that, first, both GPT models are capable of accurately and precisely label topics from the models' output keywords. Second, 3-word labels are preferable to grasp the complexity of research topics.