ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives

Hamed Rahimi (1) , Hubert Naacke (1) , Camelia Constantin (1) , Bernd Amann (1)

1 BD - Bases de Données

This paper presents ATEM, a novel framework for studying topic evolution in scientific archives. ATEM is based on dynamic topic modeling and dynamic graph embedding techniques that explore the dynamics of content and citations of documents within a scientific corpus. ATEM explores a new notion of contextual emergence for the discovery of emerging interdisciplinary research topics based on the dynamics of citation links in topic clusters. Our experiments show that ATEM can efficiently detect emerging cross-disciplinary topics within the DBLP archive of over five million computer science articles.

Mots clés: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); FOS: Computer and information sciences

Domaines: Informatique [cs]; Base de données [cs.DB]

Hamed Rahimi, Hubert Naacke, Camelia Constantin, Bernd Amann. ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives. 2023. ⟨hal-04274426⟩