A Context-Independent Representation of Task

Most of the existing search and recommender systems do not adequately support complex search tasks. However, according to the theories and empirical evidence from interactive information seeking and retrieval studies, in people's search behaviors, actions, and outcomes, tasks that trigger the information search process in the first place generate different search actions. Also, defined successes and failures to find information and accomplish tasks are relative to the motivating task end goals, rather than the fulfillment of subtasks and goals of query segments along the search process. Based on this idea, the primary purpose of the proposed research is to explore how to leverage users' search behaviors and actions in developing methods to construct task representations that can be applied in all search contexts by conducting field studies. Then based on the data collected from the user studies, evaluate the task representations in designing search and recommendation techniques in naturalistic settings to examine the extent to which the context-independent task approach can approximate users' actual tasks and provide task-specific recommendations. The research will adopt a multi-disciplinary, multi-method approach with human-centered ML-based techniques in the process. The outcomes can help us better understand users' tasks and thus have implications for the task, user modeling, and system recommendations design.