Can eyes reveal interest? Implicit queries from gaze patterns

Abstract

We study a new research problem, where an implicit information retrieval query is inferred from eye movements measured when the user is reading, and used to retrieve new documents. In the training phase, the user's interest is known, and we learn a mapping from how the user looks at a term to the role of the term in the implicit query. Assuming the mapping is universal, that is, the same for all queries in a given domain, we can use it to construct queries even for new topics for which no learning data is available. We constructed a controlled experimental setting to show that when the system has no prior information as to what the user is searching, the eye movements help significantly in the search. This is the case in a proactive search, for instance, where the system monitors the reading behaviour of the user in a new topic. In contrast, during a search or reading session where the set of inspected documents is biased towards being relevant, a stronger strategy is to search for content-wise similar documents than to use the eye movements.

A Real-Time Eye Tracking Based Query Expansion Approach via Latent Topic Modeling

“…After we have calculated the weight of each term, we use Lemur toolkit 1 and Indri 2 search engine to implement our algorithm and to generate the expanded queries from W Eye and W Eye+LDA :…”

“…Gwizdka et al [5] have thoroughly examined the relevance of a document and cognitive effort a user may take using eye movement data. Ajanki et al [1] designed an eye tracking experiment, in which participants were asked to search for relevant documents given a topic, and then the gaze locations were used to find relevant terms to reformulate the queries. However, they had to avoid scrolling the text due to the risk of missing some gaze location to word mappings.…”

Inferring word relevance from eye-movements of readers

“…Finally, a relatively new research direction on information access systems has used eye movement data as a source of implicit relevance [32,33] and to aid generation of implicit search queries for proactive search systems [1,26]. Eye tracking technology has also been employed to identify relevant parts of documents that can be used as a source of relevance feedback in personalized search systems [4].…”

“…The second analysis addressed the main goal of this research, i.e., investigating if values of word-based eye movement metrics are contingent upon the word being relevant or non-relevant. In these analyses, we focused on variables that capture both first-pass reading 1 and rereading (compare, e.g., GD and TT below). These variables can be divided into two categories: Note that inspection probabilities are usually reported in the reading literature.…”

“…Eye tracking emerged as a powerful source of information that can be used to achieve both of the above goals, i.e., help to identify relevant documents and locate relevant parts within them [1,4,26,32,33].…”