Using low‐cost electroencephalography (EEG) sensor to identify perceived relevance on web search

This poster presents preliminary results from a user study designed to evaluate the feasibility to use a low‐cost EEG sensor in the identification of information relevance as perceived by users. The study involved 10 participants, both graduate and undergraduate students, performing a self‐motivated exploratory search task contextualized on the literature review for their own thesis work. The study design comprised two stages that focus on (1) snippets collection and (2) explicit relevance assessments. In both stages, participants wore a low‐cost electroencephalography (EEG) sensor that provides measures related to two mental states (i.e. attention and meditation). Analyses focused on comparing the presence and intensity of these mental states in the set of pages (both relevant and non‐relevant) classified by the users themselves. Results showed that attention levels and blink intensity in relevant pages are significantly higher than in non‐relevant ones.

[1]  Samuel Kaski,et al.  Towards brain-activity-controlled information retrieval: Decoding image relevance from MEG signals , 2015, NeuroImage.

[2]  Yiannis Kompatsiaris,et al.  Modeling facial expressions and peripheral physiological signals to predict topical relevance , 2009, SIGIR.

[3]  Jonathan L. Herlocker,et al.  Click data as implicit relevance feedback in web search , 2007, Inf. Process. Manag..

[4]  Thorsten Joachims,et al.  Optimizing search engines using clickthrough data , 2002, KDD.

[5]  Chirag Shah,et al.  Coagmento: A system for supporting collaborative information seeking , 2011, ASIST.

[6]  Pia Borlund,et al.  The IIR evaluation model: a framework for evaluation of interactive information retrieval systems , 2003, Inf. Res..

[7]  Wentao Jiang,et al.  THE CREATIVE INVESTIGATION OF BRAIN ACTIVITY WITH EEG FOR GENDER AND LEFT/RIGHT-HANDED DIFFERENCES , 2015 .

[8]  Samuel Kaski,et al.  Exploring Peripheral Physiology as a Predictor of Perceived Relevance in Information Retrieval , 2015, IUI.

[9]  Steve Fox,et al.  Evaluating implicit measures to improve web search , 2005, TOIS.

[10]  Susan T. Dumais,et al.  Improving Web Search Ranking by Incorporating User Behavior Information , 2019, SIGIR Forum.

[11]  Jacek Gwizdka,et al.  Characterizing relevance with eye-tracking measures , 2014, IIiX.

[12]  Benjamin Blankertz,et al.  Live Demonstrator of EEG and Eye-Tracking Input for Disambiguation of Image Search Results , 2015, Symbiotic.

[13]  Joemon M. Jose,et al.  An effective implicit relevance feedback technique using affective, physiological and behavioural features , 2013, SIGIR.