Think like a Human: Constructing Cognitive-oriented Retrieval Model for Web Search

Abstract

Existing retrieval models have gained much success, however, we have to admit that the models work in a rather different manner than how humans make relevance judgments. To bridge the gap between practical user behavior and retrieval model, it is essential to construct cognitive-oriented retrieval model. The cognitive process in IR includes two important aspects: searching and reading. Searching is the user behaviors interacted with retrieval system such as query formulation and click while reading is the information seeking behavior in a specific landing page or document. We plan to better understand user cognitive behaviors in these two aspects by conducting a lab-based user study. More importantly, the heuristics drawn from cognitive behaviors are then incorporated into retrieval models.