Inproceedings,
Recognizing user interest and document value from reading and organizing activities in document triage
IUI '06: Proceedings of the 11th international conference on Intelligent user interfaces, page 218--225. New York, NY, USA, ACM, (2006)
DOI: 10.1145/1111449.1111496
Abstract
People frequently must sort through large sets of documents to identify useful materials, for example, when they look through web search results. This document triage process may involve both reading and organizing, possibly using different applications for each activity. Users' interests may be inferred from what they read and how they interact with individual documents; these interests may in turn be used as a basis for identifying other documents or document elements of potential interest within the set. To most effectively identify related documents of interest, activity data must be collected from all applications used in document triage. In this paper we present a common framework (the Interest Profile Manager) for collecting and analyzing user interest. We also present models for detecting user interest based on reading activity alone, on organizing activity alone, and on combined reading and organizing activity. A study comparing document value calculated using the different models shows that incorporating interest information from both reading and organizing activity better predicted users' valuation of documents. This difference was statistically significant when compared to using reading activity alone.
