Résumé (EN)

Emails play, in the personal and particularly in the professional context, a central role in activity management. Emails can be harvested and re-engineered for understanding the undocumented business process activities and their corresponding metadata. Our goal in this paper is to recast emails into business activity centric resources. We describe an approach that is able to discover business process activities from emails. In addition, for each activity type, we extract metadata such as the roles of the people exchanging the email, type of the attached documents, or the domains of the mentioned links. In order to extract activities from emails, we compare several popular non-linear classification techniques. Activities are then clustered according to their types, which allows us to construct the metadata for each activity type. We validate our approach using a public email dataset