Building Expert Recommenders from Email-Based Personal Social Networks

Abstract

In modern organisations there is the necessity to collabo-rate with people and establish interpersonal relationships. Contacting the right person is crucial for the success of the performed daily tasks. Personal email corpora contain rich information about all the people the user knows and their activities. Thus, an analysis of a person's emails allows automatically constructing a realistic image of the surroundings of that person. This chapter aims to develop ExpertSN, a personalised Ex-pert Recommender tool based on email Data Mining and Social Network Analysis. ExpertSN constructs a personal social network from the email corpus of a person by computing proles including topics represented by keywords and other attributes such as recency of communication for each contact found in the emails and by extracting relationships between people based on measures such as co-occurrence in To and CC elds of the emails or reciprocity of communication. Having constructed such a personal social network, we then consider its application for people search in a given work context. Through an analysis of several use cases, we have derived requirements for a query language that allows exploiting the personal social network for people search, taking into account a variety of information needs that go well beyond classical expert search scenarios known from the literature. We further discuss the application of the people search interface in a personal task management environment for eectively retrieving collaborators for a work task. Finally, we report on a user study undertaken to evaluate the personal social network in ExpertSN that shows very promising results.