F-SED: Feature-Centric Social Event Detection

Elio Mansour (1) , Gilbert Tekli (2) , Philippe Arnould , Richard Chbeir (1) , Yudith Cardinale (3)

1 LIUPPA - Laboratoire Informatique de l'Université de Pau et des Pays de l'Adour
2 LT2C - Laboratoire Telecom Claude Chappe
3 USB - Universidad Simon Bolivar

In the context of social media, existent works offer social-event-based organization of multimedia objects (e.g., photos, videos) by mainly considering spatio-temporal data, while neglecting other user-related information (e.g., people, user interests). In this paper we propose an automated, extensible, and incremental Feature-centric Social Event Detection (F-SED) approach, based on Formal Concept Analysis (FCA), to organize shared multimedia objects on social media platforms and sharing applications. F-SED simultaneously considers various event features (e.g., temporal, geographical, social (user related)), and uses the latter to detect different feature-centric events (e.g., user-centric, location-centric). Our experimental results show that detection accuracy is improved when, besides spatio-temporal information, other features, such as social, are considered. We also show that the performance of our prototype is quasi-linear in most cases.

Mots clés: Formal Concept Analysis; Social Event Detection; Social Networks; Semantic Cluster- ing; Multimedia Sharing

Domaines: Réseaux sociaux et d'information [cs.SI]; Intelligence artificielle [cs.AI]

Elio Mansour, Gilbert Tekli, Philippe Arnould, Richard Chbeir, Yudith Cardinale. F-SED: Feature-Centric Social Event Detection. 28th International Conference on Database and Expert Systems Applications - DEXA 2017, Aug 2017, Lyon, France. ⟨10.1007/978-3-319-64471-4_33⟩. ⟨hal-01905727⟩