Mapping the Landscape: Gender and Research Funding in Canada Through the Lens of LLMs and Topic Modeling

Shirin Tavakoli Kafiabad, Andrea Schiffauerova and Ashkan Ebadi ()
Additional contact information
Shirin Tavakoli Kafiabad: Concordia University, Concordia Institute for Information Systems Engineering
Andrea Schiffauerova: Concordia University, Concordia Institute for Information Systems Engineering
Ashkan Ebadi: Concordia University, Concordia Institute for Information Systems Engineering

A chapter in Technology Management for Intelligent, Open and Responsible Organizations and Ecosystems, 2026, pp 322-329 from Springer

Abstract: Abstract Understanding the evolving landscape of scientific research is critical for ensuring fair and effective resource allocation, particularly in large-scale government funding programs. This study analyses historical scientific research proposals in Canada to identify trends and patterns, aiding in equitable resource allocation. We used various topic modelling techniques, including Latent Dirichlet Allocation (LDA) and Structural Topic Models (STM), and evaluated their performance against a large language model (LLM), specifically BERTopic. Our investigation focused on the coherence, interpretability, and relevance of the topics each model extracted. The results show that the BERTopic model is superior at generating distinctive and meaningful topics. Using this optimal model, we then analysed how research focus and funding have changed over time in relation to the gender of the researchers. Our findings demonstrate that the BERT-based approach provides more accurate insights and is better able to reveal the influence of gender on funding distribution.

Keywords: Large Language Models; Natural Language Processing; Topic Modeling; Research Trends (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prbchp:978-3-032-23282-3_39

Ordering information: This item can be ordered from
http://www.springer.com/9783032232823

DOI: 10.1007/978-3-032-23282-3_39

Access Statistics for this chapter

More chapters in Springer Proceedings in Business and Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().