Recommender System for Isidore based on IEML
Alexia Schneider
2025-11-06
Context
- Search engines for scientific literature.
- Recommender Systems (RS) based on :
- annotated keywords
- previous user searches and articles read -> filter bubbles (Pariser 2011; Underwood 2014)
- citation count -> citation concentration issue (Cardon 2013; Nielsen and Andersen 2021)
- sometimes opaque ‘IA assistant’ (Tay 2025)
Questions addressed and Solution proposed
- What kind of RS could overcome these limits?
- sere ndipity (finding what you didn’t know you didn’t know)
- using controlled vocabulary (Semantic Web langages)
- How to increase literacy in RS AI agents?
- side by side comparison of search strategies
Demo
Timeline and perspective
References
Cardon, Dominique. 2013. “Dans l’esprit Du PageRank: Une Enquête Sur l’algorithme de Google.” Réseaux n. 177 (1): 63–95. https://doi.org/10.3917/res.177.0063.
Nielsen, Mathias Wullum, and Jens Peter Andersen. 2021. “Global Citation Inequality Is on the Rise.” Proceedings of the National Academy of Sciences 118 (7): e2012208118. https://doi.org/10.1073/pnas.2012208118.
Pariser, Eli. 2011. “The Filter Bubble: What the Internet Is Hiding from You.” In.
Tay, Aaron. 2025. “The Reproducibility and Interpretability of Academic AI Search Engines Like Primo Research Assistant, Web of Science Research Assistant, Scopus AI and More.” Blog. Aaron Tay’s Musings about Librarianship.
Underwood, Ted. 2014. “Theorizing Research Practices We Forgot to Theorize Twenty Years Ago.” Representations 127 (1): 64–72. https://doi.org/10.1525/rep.2014.127.1.64.