Exploring Peripheral Physiology As a Predictor of Perceived Relevance in Information Retrieval

Oswald Barral, Manuel J.A. Eugster, Tuukka Ruotsalo, Michiel M. Spapé, Ilkka Kosunen, Niklas Ravaja, Samuel Kaski, Giulio Jacucci

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Peripheral physiological signals, as obtained using electrodermal activity and facial electromyography over the corrugator supercilii muscle, are explored as indicators of perceived relevance in information retrieval tasks. An experiment with 40 participants is reported, in which these physiological signals are recorded while participants perform information retrieval tasks. Appropriate feature engineering is defined, and the feature space is explored. The results indicate that features in the window of 4 to 6 seconds after the relevance judgment for electrodermal activity, and from 1 second before to 2 seconds after the relevance judgment for corrugator supercilii activity, are associated with the users' perceived relevance of information items. A classifier verified the predictive power of the features and showed up to 14% improvement predicting relevance. Our research can help the design of intelligent user interfaces for information retrieval that can detect the user's perceived relevance from physiological signals and complement or replace conventional relevance feedback.
Original languageEnglish
Title of host publicationProceedings of the 20th International Conference on Intelligent User Interfaces
Number of pages11
Place of PublicationAtlanta, Georgia, USA
Publication date2015
ISBN (Print)978-1-4503-3306-1
Publication statusPublished - 2015
MoE publication typeA4 Article in conference proceedings
EventInternational Conference on Intelligent User Interfaces - Atlanta, United States
Duration: 29 Mar 20151 Apr 2015
Conference number: 20

Bibliographical note

Proceeding volume:

Fields of Science

  • corrugator supercilii, electrodermal activity, implicit relevance feedback, information retrieval, peripheral physiology, relevance prediction
  • 113 Computer and information sciences

Cite this