An Integrated Model of Tasks and Uncertainties for Designing Task-aware Search Assistants

Abstract

Search behaviors are usually motivated by some task that prompts users into the search process. Complex tasks often initiate long, evolving, interactive search processes with shifting goals and cognitive focus at different search stages. Users' search strategies are influenced by their search motivation, encountered problems, and cognitive focus or state of knowledge at these search stages. However, existing search systems are primarily designed to optimize one request at a time, ignoring the underlying overarching task, shifting task phases and sub-tasks with users' cognitive focus, or even the holistic nature of a task-based search session. Although a set of descriptive and theoretical models of the search process can be found in the literature that characterizes tasks, there is a gap in research focused on exploiting dynamic task characteristics in search personalization processes. More importantly, there is a lack of support for users to complete their tasks in an adaptive, dynamic way. To address this issue, this dissertation adopts a multi-disciplinary, human-centered approach and applies a mixed-methods design-based approach to meet three broad objectives: First, develop a conceptual framework for understanding how different types of tasks trigger specific information needs that can lead to different methods and strategies for seeking different forms of information and information sources and, in the due process, identify any barriers they perceive and potential help they choose to overcome those limitations; Second, apply new computational models to construct unified task representations using underlying search behavioral signals that can be transferable and functional to any task circumstances; and Third make existing search and retrieval systems more responsible and efficient to meet the changing state of users' cognitive focus during the search process by using knowledge gained about users' tasks and problems. Specifically, this dissertation aims to develop a task-information need-strategy-problem-based task representation that can be leveraged in search and retrieval models to provide task-based supports in different information formats, thus empowering users to make informed decisions about different aspects of their lives by providing information more relevant to their current task state. The result of this study is a step towards developing task-aware intelligent systems capable of supporting users at each stage of their complex task-completion process.