Recipient recommendation in enterprises using communication graphs and email content

Authors:

Abstract
We address the task of recipient recommendation for emailing in enterprises. We propose an intuitive and elegant way of modeling the task of recipient recommendation, which uses both the communication graph (i.e., who are most closely connected to the sender) and the content of the email. Additionally, the model can incorporate evidence as prior probabilities. Experiments on two enterprise email collections show that our model achieves very high scores, and that it outperforms two variants that use either the communication graph or the content in isolation.
Funding Information
  • Netherlands eScience Center (027.012.105)
  • Nederlandse Organisatie voor Wetenschappelijk Onderzoek (612.001.116, 727.011.005, HOR-11-10, 640.006.013)
  • COMMIT
  • Yahoo! Faculty Research and Engagement Program
  • HPC Fund
  • CLARIN-nl program
  • European Social Fund Plus
  • Microsoft Research
  • Seventh Framework Programme (nr 312827 (VOX-Pol), nr 288024 (LiMoSINe))
  • Center for Creation Content and Technology (CCCT)
  • CLARIAH
  • Royal Netherlands Academy of Arts and Sciences