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

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

Sammanfattning

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.
Originalspråkengelska
Titel på gästpublikationProceedings of the 20th International Conference on Intelligent User Interfaces
Antal sidor11
UtgivningsortAtlanta, Georgia, USA
FörlagACM
Utgivningsdatum2015
Sidor389-399
ISBN (tryckt)978-1-4503-3306-1
DOI
StatusPublicerad - 2015
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangInternational Conference on Intelligent User Interfaces - Atlanta, Förenta Staterna (USA)
Varaktighet: 29 mar 20151 apr 2015
Konferensnummer: 20

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap

Citera det här

Barral, O., Eugster, M. J. A., Ruotsalo, T., Spapé, M. M., Kosunen, I., Ravaja, N., ... Jacucci, G. (2015). Exploring Peripheral Physiology As a Predictor of Perceived Relevance in Information Retrieval. I Proceedings of the 20th International Conference on Intelligent User Interfaces (s. 389-399). Atlanta, Georgia, USA: ACM. https://doi.org/10.1145/2678025.2701389
Barral, Oswald ; Eugster, Manuel J.A. ; Ruotsalo, Tuukka ; Spapé, Michiel M. ; Kosunen, Ilkka ; Ravaja, Niklas ; Kaski, Samuel ; Jacucci, Giulio. / Exploring Peripheral Physiology As a Predictor of Perceived Relevance in Information Retrieval. Proceedings of the 20th International Conference on Intelligent User Interfaces. Atlanta, Georgia, USA : ACM, 2015. s. 389-399
@inproceedings{ec5686fdc6c7485c952a0c17bfd78708,
title = "Exploring Peripheral Physiology As a Predictor of Perceived Relevance in Information Retrieval",
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.",
keywords = "corrugator supercilii, electrodermal activity, implicit relevance feedback, information retrieval, peripheral physiology, relevance prediction, 113 Computer and information sciences",
author = "Oswald Barral and Eugster, {Manuel J.A.} and Tuukka Ruotsalo and Spap{\'e}, {Michiel M.} and Ilkka Kosunen and Niklas Ravaja and Samuel Kaski and Giulio Jacucci",
note = "IUI'15. Volume: Proceeding volume:",
year = "2015",
doi = "10.1145/2678025.2701389",
language = "English",
isbn = "978-1-4503-3306-1",
pages = "389--399",
booktitle = "Proceedings of the 20th International Conference on Intelligent User Interfaces",
publisher = "ACM",
address = "International",

}

Barral, O, Eugster, MJA, Ruotsalo, T, Spapé, MM, Kosunen, I, Ravaja, N, Kaski, S & Jacucci, G 2015, Exploring Peripheral Physiology As a Predictor of Perceived Relevance in Information Retrieval. i Proceedings of the 20th International Conference on Intelligent User Interfaces. ACM, Atlanta, Georgia, USA, s. 389-399, International Conference on Intelligent User Interfaces, Atlanta, Förenta Staterna (USA), 29/03/2015. https://doi.org/10.1145/2678025.2701389

Exploring Peripheral Physiology As a Predictor of Perceived Relevance in Information Retrieval. / Barral, Oswald; Eugster, Manuel J.A.; Ruotsalo, Tuukka; Spapé, Michiel M.; Kosunen, Ilkka; Ravaja, Niklas; Kaski, Samuel; Jacucci, Giulio.

Proceedings of the 20th International Conference on Intelligent User Interfaces. Atlanta, Georgia, USA : ACM, 2015. s. 389-399.

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

TY - GEN

T1 - Exploring Peripheral Physiology As a Predictor of Perceived Relevance in Information Retrieval

AU - Barral, Oswald

AU - Eugster, Manuel J.A.

AU - Ruotsalo, Tuukka

AU - Spapé, Michiel M.

AU - Kosunen, Ilkka

AU - Ravaja, Niklas

AU - Kaski, Samuel

AU - Jacucci, Giulio

N1 - IUI'15. Volume: Proceeding volume:

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

KW - corrugator supercilii, electrodermal activity, implicit relevance feedback, information retrieval, peripheral physiology, relevance prediction

KW - 113 Computer and information sciences

U2 - 10.1145/2678025.2701389

DO - 10.1145/2678025.2701389

M3 - Conference contribution

SN - 978-1-4503-3306-1

SP - 389

EP - 399

BT - Proceedings of the 20th International Conference on Intelligent User Interfaces

PB - ACM

CY - Atlanta, Georgia, USA

ER -

Barral O, Eugster MJA, Ruotsalo T, Spapé MM, Kosunen I, Ravaja N et al. Exploring Peripheral Physiology As a Predictor of Perceived Relevance in Information Retrieval. I Proceedings of the 20th International Conference on Intelligent User Interfaces. Atlanta, Georgia, USA: ACM. 2015. s. 389-399 https://doi.org/10.1145/2678025.2701389