Inferring user knowledge level from eye movement patterns

Abstract

The acquisition of information and the search interaction process is influenced strongly by a person's use of their knowledge of the domain and the task. In this paper we show that a user's level of domain knowledge can be inferred from their interactive search behaviors without considering the content of queries or documents. A technique is presented to model a user's information acquisition process during search using only measurements of eye movement patterns. In a user study (n=40) of search in the domain of genomics, a representation of the participant's domain knowledge was constructed using self-ratings of knowledge of genomics-related terms (n=409). Cognitive effort features associated with reading eye movement patterns were calculated for each reading instance during the search tasks. The results show correlations between the cognitive effort due to reading and an individual's level of domain knowledge. We construct exploratory regression models that suggest it is possible to build models that can make predictions of the user's level of knowledge based on real-time measurements of eye movement patterns during a task session.

Expertise estimation based on simple multimodal features

“…The work of Scherer et al [3], similarly to the approach followed in the present study, researched features more based on what a human could superficially hear in audios and interpret from drawings and found that the Peak Slope of the audio could discriminate between Experts and Non-Experts. Some studies suggest that it is possible to build models that can make predictions of the user's level of knowledge or expertise, based on real-time measurements of eye movement patterns during a task session [23]. In this line, distinguishing levels of expertise, based on features gathered from video while building solutions based on physics knowledge, was studied by Worsley and Blikstein [24]; their research concluded that two-handed interaction is positively correlated to expertise.…”

A new paradigm for the scientific article

“…Cole et al [9] show that you can recognize existing domain knowledge of a person with this method. Further they find: "Of particular importance is the fact that eyes fixate until the meaning of the word(s) is acquired."…”

“…Further they find: "Of particular importance is the fact that eyes fixate until the meaning of the word(s) is acquired." [10]. Eye tracking can visualize the different passages of a text already known.…”

Supporting Exploratory Search Through Interaction Modeling

“…A recent development is to develop computational models for predicting the domain knowledge of a user. These models consider different types of interactions such as dwell time, selected document ranks, query length, reading patterns, as well as cognitive effort measured through external sensors [7,9]. While these models are useful in customizing results according to the domain knowledge of the user, they however, do not capture situations where domain experts search information in narrower sub-fields of a familiar domain.…”