Using Web Browser Interactions to Predict Task

• Melanie Kellar, Dalhousie University, Canada
• Carolyn Watters, Dalhousie University, Canada

Full text:

Track: Posters

The automatic identification of a user's task has the potential to improve information filtering systems. Many information filtering systems rely on implicit measures of interest, whose effectiveness may be dependant upon the task at hand. An understanding of the user's current task would allow the system to apply the most useful measures of interest. We recently conducted a field study where participants were asked to use a custom web browser that logged all of their interactions and annotate all their web usage with task information according to a high-level task schema. Using the data collected during this study, we conduct a preliminary exploration of the usefulness of logged web browser interactions to predict users' tasks.