Daily-Academic: A Semantic Literature Discovery and Journal Tracking Platform for Biomedical Research

Objective: Biomedical researchers monitoring newly published literature rely on fragmented combinations of keyword alerts, manual database searches, journal subscriptions and repository portals. We aimed to develop and evaluate an integrated platform that unifies semantic literature discovery, journal monitoring and linked omics dataset exploration within a single researcher-oriented workflow, driven by a user profile that remains explicit and editable. Methods: Daily-Academic aggregates publication metadata from biomedical literature repositories and public omics resources and encodes titles and abstracts as dense semantic representations to support similarity-based retrieval beyond keyword matching. Recommendations are ranked by combining semantic relevance to the user profile with publication recency and journal-level preferences. The profile is derived from three user-supplied signals: a free-text statement of research interests, an optional link to the user's own publication record, and interaction history. Retrieval quality was assessed on an offline benchmark of 30 biomedical queries over a fixed corpus of 259,246 publications, comparing Daily-Academic with a lexical BM25 baseline and a PubMedBERT bi-encoder under pooled assessment with graded relevance judgements. Results: [Insert the corrected figures once the re-annotation is complete: precision and nDCG at rank 10 for all three methods, and the outcome of the paired significance tests.] Query-level analysis indicated that the differences were distributed across queries rather than driven by a small subset. Conclusion: Integrating semantic retrieval into a unified discovery workflow with an inspectable user model improved the quality of top-ranked biomedical literature relative to established lexical and dense baselines. Because the benchmark is user-free, the adaptive component of personalisation was inactive and the ranking weights untuned; the observed advantage therefore reflects the semantic representation rather than adaptive personalisation. The platform is publicly available at https://www.daily-academic.com. Keywords: biomedical informatics, literature discovery, semantic retrieval, recommender systems, journal tracking, personalized feeds, scientific monitoring

Authors

Institutions

Publication Details

Journal
bioRxiv (Cold Spring Harbor Laboratory)
Published
2026-11-20
DOI
https://doi.org/10.64898/2026.11.19.767813
Primary Topic
Information Retrieval and Search Behavior
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Daily-Academic: A Semantic Literature Discovery and Journal Tracking Platform for Biomedical Research

Dimitris Grigoriadis, Ilias Georgakopoulos‐Soares, Nikos Perdikopanis, Georgios A. Pavlopoulos
1 links
bioRxiv (Cold Spring Harbor Laboratory)
Information Retrieval and Search Behavior
preprint

Daily-Academic: A Semantic Literature Discovery and Journal Tracking Platform for Biomedical Research

Dimitris Grigoriadis, Ilias Georgakopoulos‐Soares, Nikos Perdikopanis, Georgios A. Pavlopoulos
preprint en

Abstract

Objective: Biomedical researchers monitoring newly published literature rely on fragmented combinations of keyword alerts, manual database searches, journal subscriptions and repository portals. We aimed to develop and evaluate an integrated platform that unifies semantic literature discovery, journal monitoring and linked omics dataset exploration within a single researcher-oriented workflow, driven by a user profile that remains explicit and editable. Methods: Daily-Academic aggregates publication metadata from biomedical literature repositories and public omics resources and encodes titles and abstracts as dense semantic representations to support similarity-based retrieval beyond keyword matching. Recommendations are ranked by combining semantic relevance to the user profile with publication recency and journal-level preferences. The profile is derived from three user-supplied signals: a free-text statement of research interests, an optional link to the user's own publication record, and interaction history. Retrieval quality was assessed on an offline benchmark of 30 biomedical queries over a fixed corpus of 259,246 publications, comparing Daily-Academic with a lexical BM25 baseline and a PubMedBERT bi-encoder under pooled assessment with graded relevance judgements. Results: [Insert the corrected figures once the re-annotation is complete: precision and nDCG at rank 10 for all three methods, and the outcome of the paired significance tests.] Query-level analysis indicated that the differences were distributed across queries rather than driven by a small subset. Conclusion: Integrating semantic retrieval into a unified discovery workflow with an inspectable user model improved the quality of top-ranked biomedical literature relative to established lexical and dense baselines. Because the benchmark is user-free, the adaptive component of personalisation was inactive and the ranking weights untuned; the observed advantage therefore reflects the semantic representation rather than adaptive personalisation. The platform is publicly available at https://www.daily-academic.com. Keywords: biomedical informatics, literature discovery, semantic retrieval, recommender systems, journal tracking, personalized feeds, scientific monitoring

bioRxiv (Cold Spring Harbor Laboratory)
National and Kapodistrian University of Athens (GR), Alexander Fleming Biomedical Sciences Research Center (GR), The University of Texas at Austin (US)
Hellenic Foundation for Research and Innovation, Penn State College of Medicine
Information Retrieval and Search Behavior
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Daily-Academic: A Semantic Literature Discovery and Journal Tracking Platform for Biomedical Research — Dimitris Grigoriadis, Ilias Georgakopoulos‐Soares, et al. · bioRxiv (Cold Spring Harbor Laboratory) (2026) | TGRS Research Map | TGRS