Dataset and Analysis Files for "From ChatGPT to Large Language Models in Library and Information Science: An OpenAlex-Based Bibliometric and Thematic Mapping"

This dataset contains the cleaned OpenAlex metadata, search query log, screening terms, VOSviewer thesaurus file, analysis scripts and supporting documentation used for the bibliometric and thematic mapping of ChatGPT and large language model research in Library and Information Science. The metadata were retrieved from the OpenAlex REST API on 29 May 2026. The initial search returned 38,255 records, and the final analysis corpus consisted of 488 scholarly records after deduplication, automatic relevance filtering, manual screening and source-type restriction.