Most search and recommender systems today operate at the level of an individual’s actions as a way to model what their needs may be and what suggestions they may like. In doing so, they are often ignoring the context in which such activities happen or the person performing those actions. In this talk, I will argue that knowing the context of task in which search and recommendation activities happen as well as the knowledge about the taskers could provide us with crucial information in a recommendation application. Specifically, I will describe our efforts to model a search task and/or how a user is approaching that task as a way to identify potential problems and come up with process-based recommendations in online exploratory searches. I will then present some recent work to connect exploratory searching in online and physical contexts, allowing us to do cross-context task analysis. These works are primarily based on several user studies done in the lab and in the field. Finally, I will bring these together under a new research theme called Information Fostering, where such nuanced analysis of task is used to predict problems or opportunities that may occur in the future. This kind of work fits squarely in a relatively new, interdisciplinary community called CHIIR, created through the collaboration of ACM CHI and ACM SIGIR.
Chirag Shah is an Associate Professor in Information School (iSchool) at University of Washington (UW) in Seattle. Before UW, he was a faculty at Rutgers University. His research interests include studies of interactive information retrieval/seeking, trying to understand the task a person is doing and providing proactive recommendations. Dr. Shah received his MS in Computer Science from University of Massachusetts (UMass) at Amherst, and PhD in Information Science from University of North Carolina (UNC) at Chapel Hill. He directs the InfoSeeking Lab where he investigates issues related to information seeking, human-computer interaction (HCI), and fairness in machine learning, supported by grants from National Science Foundation (NSF), National Institute of Health (NIH), Institute of Museum and Library Services (IMLS), Amazon, Google, and Yahoo. He spent his sabbatical last year at Spotify working on voice-based search and recommendation problems. As an Amazon Scholar he is working with Amazon’s Personalization team on applications involving personalized and task-oriented recommendations. More information about Dr. Shah can be found at http://chiragshah.org/.