Biomolecule Papers

In this data story, we explore the abstracts of papers related to [biomolecule - `q-bio.BM`](https://arxiv.org/list/q-bio.BM/new) papers published on [arxiv.org](https://arxiv.org/) since its inception. The metadata is sourced from [Cornell's Kaggle arxiv dataset](https://www.kaggle.com/datasets/Cornell-University/arxiv/) which lists almost 1 million papers. We then used ChatGPT to **automatically** identify topics and cluster them. This visual explores which topic was mentioned where in the document.