Name Reference Resolution in Organizational Email Archives

Abstract

Online communications provide a rich resource for understanding social networks. Information about the actors, and their dynamic roles and relationships, can be inferred from both the communication content and traffic structure. A key component in the analysis of online communications such as email is the resolution of name references within the body of the message. Name reference resolution relies on the context of the message; both the content of the message and the sender and recipients' relationships can help to resolve a reference. Here we investigate a variety of approaches which make use of the email traffic network to disambiguate email name references. The email traffic network serves as a proxy for inferring relationships. These relationships in turn help us infer likely candidates for the name references. Our initial findings suggest that simple temporal models can help us effectively resolve name references. For the class of models proposed, performance is maximized by exploiting long-term traffic statistics to rank candidates.