Modeling a collaborative task with social commitments

Jean-Baptiste Louvet (1) , Guillaume Dubuisson Duplessis (2) , Nathalie Chaignaud (2) , Laurent Vercouter (3) , Jean-Philippe Kotowicz (2)

1 MIND - LITIS - Equipe Multi-agent, Interaction, Décision
2 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
3 ISCOD-ENSMSE - Département Informatique pour les Systèmes Coopératifs Ouverts et Décentralisés

Our goal is to design software agents able to collaborate with a user on a document retrieval task. To this end, we studied a corpus of human-human collaborative document retrieval task involving a user and an expert. Starting with a scenario built from the analysis of this corpus, we adapt it for a human-machine collaborative task. We propose a model based on social commitments to link the task itself (collaborative document retrieval) and the interaction with the user that our assistant agent has to manage. Then, we specify some steps of the scenario with our model. The notion of triggers in our model implements the deliberative process of the assistant agent.

Mots clés: collaborative document retrieval; human-machine interaction; social commitments

Domaines: Interface homme-machine [cs.HC]; Recherche d'information [cs.IR]

Jean-Baptiste Louvet, Guillaume Dubuisson Duplessis, Nathalie Chaignaud, Laurent Vercouter, Jean-Philippe Kotowicz. Modeling a collaborative task with social commitments. Procedia Computer Science, 2017, Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 21st International Conference, KES-20176-8 September 2017, Marseille, France, 112, pp.377 - 386. ⟨10.1016/j.procs.2017.08.218⟩. ⟨hal-01759690⟩