Discovery and analysis of e-mail-driven business processes

Abstract

E-mail is used as the primary tool for business communication and collaboration. This paper presents a novel e-mail interaction mining method to discover and analyze e-mail-driven business processes. An e-mail-driven business process is perceived as a human collaboration process that consists of interactions between people who may each play different roles. The notion of message threads (i.e. sets of e-mail messages that are replies to each other) is used as the fundamental building block to construct the interactions in the e-mail-driven business process. The proposed method adopts an interaction-centric business process modeling language to visualize the discovered e-mail-driven business process. The method identifies message threads from an e-mail archive, and constructs an interaction-centric process model based on the temporal order and similarity of the threads. Process-related information is extracted from e-mail header fields. A software tool, named E-mail Interaction Miner, implements the proposed method. A case study is used to apply and evaluate the method on a set of e-mails collected from a Dutch gas transport company. The evaluation results are discussed. These results comprise business process improvement opportunities for the case organization, and contributions to theory and language development.