{"ID":5937818,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-08T22:23:57.623805699Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04529","arxiv_id":"2607.04529","title":"Evaluation and Explainability of Unsupervised Scholarly Collaboration Recommendations","abstract":"In this paper, we examine unsupervised, content-based collaboration recommendations using publication text in scholarly settings. We compare three families of methods: a TF-IDF baseline, topic-based models (LDA and BERTopic, including clone variants), and embedding-based retrieval using SciBERT with Faiss. To evaluate model behavior beyond simple lexical matching, we introduce a constrained setting where publication overlap between researchers is partially removed while still using historical co-authorship as proxy ground truth for post-hoc evaluation. Results show clear differences across methods. TF-IDF performs best under full information but drops significantly as overlap is reduced. In contrast, topic-based and embedding-based approaches show more stable performance, suggesting they capture broader distributional similarities, rather than relying only on direct lexical overlap. We also examine explainability through two perspectives: intrinsic topic-based explanations and post-hoc, retrieval-based explanations generated using language models. These provide complementary trade-offs between transparency and human readability.","short_abstract":"In this paper, we examine unsupervised, content-based collaboration recommendations using publication text in scholarly settings. We compare three families of methods: a TF-IDF baseline, topic-based models (LDA and BERTopic, including clone variants), and embedding-based retrieval using SciBERT with Faiss. To evaluate...","url_abs":"https://arxiv.org/abs/2607.04529","url_pdf":"https://arxiv.org/pdf/2607.04529v1","authors":"[\"Md Asaduzzaman Noor\",\"John W. Sheppard\",\"Jason A. Clark\"]","published":"2026-07-05T22:23:50Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Language Model\"]","has_code":false}