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

Barral, Oswald and Eugster, Manuel J.A. and Ruotsalo, Tuukka and Spapé, Michiel M. and Kosunen, Ilkka and Ravaja, Niklas and Kaski, Samuel and Jacucci, Giulio (2015) Exploring Peripheral Physiology as a Predictor of Perceived Relevance in Information Retrieval. IUI'15 20th International Conference on Intelligent User Interfaces, 26 (5). pp. 389-399. ISSN 0924-1868

Text Barral (2015) - Exploring.pdf Download (3MB)

Abstract

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.

Item Type:	Article
Faculty / Department:	Faculty of Human and Digital Sciences > School of Psychology
Depositing User:	Michiel Spape
Date Deposited:	30 Aug 2017 08:29
Last Modified:	30 Aug 2017 08:29
URI:	https://hira.hope.ac.uk/id/eprint/2043

Available Versions of this Item

• Exploring Peripheral Physiology as a Predictor of Perceived Relevance in Information Retrieval. (deposited 14 Dec 2016 15:45)
  • Exploring Peripheral Physiology as a Predictor of Perceived Relevance in Information Retrieval. (deposited 30 Aug 2017 08:29) [Currently Displayed]
    • Extracting Relevance and Affect Information from Physiological Text Annotation. (deposited 21 Jun 2017 14:50)

Actions (login required)

View Item