User Interests Clustering in Business Intelligence Interactions

Krista Drushku (1, 2) , Julien Aligon (3, 4, 5) , Nicolas Labroche (6) , Patrick Marcel (1) , Veronika Peralta (7) , Bruno Dumant (2)

1 LIFAT - Laboratoire d'Informatique Fondamentale et Appliquée de Tours
2 SAP Research
3 IRIT-SIG - Systèmes d’Informations Généralisées
4 UT - Université de Tours
5 UT Capitole - Université Toulouse Capitole
6 BDTLN - Bases de données et traitement des langues naturelles
7 PRISM - Parallélisme, Réseaux, Systèmes, Modélisation

It is quite common these days for experts, casual analysts, executives or data enthusiasts, to analyze large datasets using user-friendly interfaces on top of Business Intelligence (BI) systems. However , current BI systems do not adequately detect and characterize user interests, which may lead to tedious and unproductive interactions. In this paper, we propose to identify such user interests by characterizing the intent of the interaction with the BI system. With an eye on user modeling for proactive search systems, we identify a set of features for an adequate description of intents, and a similarity measure for grouping intents into coherent interests. We validate experimentally our approach with a user study, where we analyze traces of BI navigation. We show that our similarity measure outperforms a state-of-the-art query similarity measure and yields a very good precision with respect to expressed user interests.

Mots clés: Clustering; User interest; BI analyses; Feature construction

Domaines: Recherche d'information [cs.IR]; Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]

Krista Drushku, Julien Aligon, Nicolas Labroche, Patrick Marcel, Veronika Peralta, et al.. User Interests Clustering in Business Intelligence Interactions. International Conference on Advanced Information Systems Engineering (CAiSE 2017), Jun 2017, Essen, Germany. ⟨10.1007/978-3-319-59536-8_10⟩. ⟨hal-01629076⟩