Location
Ngee Ann Kongsi Auditorium (NAKA)
Start Date
3-6-2026 4:30 PM
End Date
3-6-2026 5:00 PM
Description
Libraries and research offices are increasingly tasked with making sense of unstructured institutional data, such as research publications and strategic documents. These insights help inform decision-making and leadership planning. This session shares how SMU Libraries leveraged BERTopic, an open-source topic modeling tool, together with generative AI tools such as ChatGPT and Claude, to extract meaningful insights from faculty publications and support institutional sensemaking.
In one use case, we applied BERTopic to university-authored publications to surface thematic groupings related to research about Asia. Generative AI tools were then used to summarize each cluster into human-readable narratives, enabling research landscape mapping, identification of publication patterns and regional impact. A second use case explores the use of GenAI to classify research outputs according to strategic institutional themes (e.g., Digital Transformation, Sustainable Living). To support transparency, models were prompted to explain their classifications and flag uncertain cases for human validation.
These experiments demonstrate how generative tools when paired with interpretable NLP methods can support narrative-style research assessment and policy-aligned impact storytelling. We also reflect on practical considerations, including reproducibility, scalability, and the privacy-preserving nature of BERTopic, which makes it suitable for analyzing sensitive data and for academic research applications. Together, these initiatives highlight the evolving role of librarians in AI-enhanced research intelligence and institutional research support.
Mapping Themes, Aligning Strategies: Institutional Research Analytics with BERTopic and GenAI
Ngee Ann Kongsi Auditorium (NAKA)
Libraries and research offices are increasingly tasked with making sense of unstructured institutional data, such as research publications and strategic documents. These insights help inform decision-making and leadership planning. This session shares how SMU Libraries leveraged BERTopic, an open-source topic modeling tool, together with generative AI tools such as ChatGPT and Claude, to extract meaningful insights from faculty publications and support institutional sensemaking.
In one use case, we applied BERTopic to university-authored publications to surface thematic groupings related to research about Asia. Generative AI tools were then used to summarize each cluster into human-readable narratives, enabling research landscape mapping, identification of publication patterns and regional impact. A second use case explores the use of GenAI to classify research outputs according to strategic institutional themes (e.g., Digital Transformation, Sustainable Living). To support transparency, models were prompted to explain their classifications and flag uncertain cases for human validation.
These experiments demonstrate how generative tools when paired with interpretable NLP methods can support narrative-style research assessment and policy-aligned impact storytelling. We also reflect on practical considerations, including reproducibility, scalability, and the privacy-preserving nature of BERTopic, which makes it suitable for analyzing sensitive data and for academic research applications. Together, these initiatives highlight the evolving role of librarians in AI-enhanced research intelligence and institutional research support.