A hybrid AI approach for recommending collaborators in research projects
Lade...
Autor:in (Körperschaft)
Publikationsdatum
2026
Typ der Arbeit
Studiengang
Typ
04B - Beitrag Konferenzschrift
Herausgeber:innen
Herausgeber:in (Körperschaft)
Betreuer:in
Übergeordnetes Werk
Society 5.0. 5th International Conference Society 5.0 2025, San Benedetto Del Tronto, Italy, June 25–27, 2025, Revised Selected Papers
Themenheft
DOI der Originalpublikation
Link
Zugehörige Forschungsdaten
Reihe / Serie
Communications in Computer and Information Science (CCIS)
Reihennummer
2787
Jahrgang / Band
Ausgabe / Nummer
Seiten / Dauer
252-264
Patentnummer
Verlag / Herausgebende Institution
Springer
Verlagsort / Veranstaltungsort
San Benedetto Del Tronto
Auflage
Version
Programmiersprache
Abtretungsempfänger:in
Praxispartner:in/Auftraggeber:in
Zusammenfassung
The success of research project proposals heavily depends on the consortium, which should be experienced and knowledgeable in the topics outlined in the corresponding calls, e.g., those in the EU’s research and innovation programme Horizon Europe. Yet, one of the most challenging activities in such a context is the formation of the consortium, which requires the identification of adequate research collaborators. Traditional methods take this challenge by relying solely on social networks and, or the number of author citations, which proved to be limited in efficacy. This paper proposes an Agentic Graph Retrieval-Augmented Generation (RAG) method, that provides contextual and explainable recommendations, which are tailored to researchers’ areas of expertise and project relevance, thus more effective than existing approaches. The proposed method combines Knowledge Graphs (KGs) and Large Language Models (LLMs) capabilities and has been developed following the Design Science research methodology. The new method has been evaluated by considering two of the highest-performant LLMs currently in the market: Claude Sonnet 3.5 and GPT-4o.
Schlagwörter
Veranstaltung
5th International Conference Society 5.0 2025
Startdatum der Ausstellung
Enddatum der Ausstellung
Startdatum der Konferenz
25.06.2025
Enddatum der Konferenz
27.06.2025
Datum der letzten Prüfung
ISBN
978-3-032-15462-0
978-3-032-15463-7
978-3-032-15463-7
ISSN
Sprache
Englisch
Während FHNW Zugehörigkeit erstellt
Ja
Zukunftsfelder FHNW
Publikationsstatus
Veröffentlicht
Begutachtung
peer-reviewed
Open Access-Status
Closed
Zitation
Rosati, P., Laurenzi, E., & Quadrini, M. (2026). A hybrid AI approach for recommending collaborators in research projects. In F. Corradini, K. Hinkelmann, H. Smuts, & B. Re (Eds.), Society 5.0. 5th International Conference Society 5.0 2025, San Benedetto Del Tronto, Italy, June 25–27, 2025, Revised Selected Papers (pp. 252–264). Springer. https://doi.org/10.1007/978-3-032-15463-7_21