Activity modelling using email and web page classification

This work explores the modelling of a user’s current activity using a single document and a very small collection of classified documents. We describe the WeMAC approach for combining evidence from heterogeneous sources to give a prdict the user’s activity. We report evaluation of the WeMAC model using two different document types: emails and web pages; assess its performance on both tiny document sets and larger sets; and assess its performance against a “one bag” approach. We report promising results, with average F1 value of 0.5-0.7.