An effective implicit relevance feedback technique using affective, physiological and behavioural features

Yashar Moshfeghi, Joemon M. Jose

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

33 Citations (Scopus)

Abstract

The effectiveness of various behavioural signals for implicit relevance feedback models has been exhaustively studied. Despite the advantages of such techniques for a real time information retrieval system, most of the behavioural signals are noisy and therefore not reliable enough to be employed. Among many, a combination of dwell time and task information has been shown to be effective for relevance judgement prediction. However, the task information might not be available to the system at all times. Thus, there is a need for other sources of information which can be used as a substitute for task information. Recently, affective and physiological signals have shown promise as a potential source of information for relevance judgement prediction. However, their accuracy is not high enough to be applicable on their own.

This paper investigates whether affective and physiological signals can be used as a complementary source of information for behavioural signals (i.e. dwell time) to create a reliable signal for relevance judgement prediction. Using a video retrieval system as a use case, we study and compare the effectiveness of the affective and physiological signals on their own, as well as in combination with behavioural signals for the relevance judgment prediction task across four different search intentions: seeking information, re-finding a particular information object, and two different entertainment intentions (i.e. entertainment by adjusting arousal level, and entertainment by adjusting mood). Our experimental results show that the effectiveness of studied signals varies across different search intentions, and when affective and physiological signals are combined with dwell time, a significant improvement can be achieved. Overall, these findings will help to implement better search engines in the future.
Original languageEnglish
Title of host publicationProceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval
Place of PublicationNew York
Pages133-142
Number of pages10
DOIs
Publication statusPublished - 28 Jul 2013
Event36th international ACM SIGIR conference on Research and development in information retrieval - Dublin, Ireland
Duration: 28 Jul 20131 Aug 2013

Conference

Conference36th international ACM SIGIR conference on Research and development in information retrieval
CountryIreland
CityDublin
Period28/07/131/08/13

Fingerprint

Feedback
Information retrieval systems
Search engines

Keywords

  • implicit relevance feedback
  • affective
  • physiological
  • behavioural
  • dwell time
  • search intentions

Cite this

Moshfeghi, Y., & Jose, J. M. (2013). An effective implicit relevance feedback technique using affective, physiological and behavioural features. In Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 133-142). New York. https://doi.org/10.1145/2484028.2484074
Moshfeghi, Yashar ; Jose, Joemon M. / An effective implicit relevance feedback technique using affective, physiological and behavioural features. Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, 2013. pp. 133-142
@inproceedings{5a7ecfad256746289e5f5ab376ea0898,
title = "An effective implicit relevance feedback technique using affective, physiological and behavioural features",
abstract = "The effectiveness of various behavioural signals for implicit relevance feedback models has been exhaustively studied. Despite the advantages of such techniques for a real time information retrieval system, most of the behavioural signals are noisy and therefore not reliable enough to be employed. Among many, a combination of dwell time and task information has been shown to be effective for relevance judgement prediction. However, the task information might not be available to the system at all times. Thus, there is a need for other sources of information which can be used as a substitute for task information. Recently, affective and physiological signals have shown promise as a potential source of information for relevance judgement prediction. However, their accuracy is not high enough to be applicable on their own.This paper investigates whether affective and physiological signals can be used as a complementary source of information for behavioural signals (i.e. dwell time) to create a reliable signal for relevance judgement prediction. Using a video retrieval system as a use case, we study and compare the effectiveness of the affective and physiological signals on their own, as well as in combination with behavioural signals for the relevance judgment prediction task across four different search intentions: seeking information, re-finding a particular information object, and two different entertainment intentions (i.e. entertainment by adjusting arousal level, and entertainment by adjusting mood). Our experimental results show that the effectiveness of studied signals varies across different search intentions, and when affective and physiological signals are combined with dwell time, a significant improvement can be achieved. Overall, these findings will help to implement better search engines in the future.",
keywords = "implicit relevance feedback, affective, physiological, behavioural, dwell time, search intentions",
author = "Yashar Moshfeghi and Jose, {Joemon M.}",
year = "2013",
month = "7",
day = "28",
doi = "10.1145/2484028.2484074",
language = "English",
isbn = "9781450320344",
pages = "133--142",
booktitle = "Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval",

}

Moshfeghi, Y & Jose, JM 2013, An effective implicit relevance feedback technique using affective, physiological and behavioural features. in Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, pp. 133-142, 36th international ACM SIGIR conference on Research and development in information retrieval , Dublin, Ireland, 28/07/13. https://doi.org/10.1145/2484028.2484074

An effective implicit relevance feedback technique using affective, physiological and behavioural features. / Moshfeghi, Yashar; Jose, Joemon M.

Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, 2013. p. 133-142.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - An effective implicit relevance feedback technique using affective, physiological and behavioural features

AU - Moshfeghi, Yashar

AU - Jose, Joemon M.

PY - 2013/7/28

Y1 - 2013/7/28

N2 - The effectiveness of various behavioural signals for implicit relevance feedback models has been exhaustively studied. Despite the advantages of such techniques for a real time information retrieval system, most of the behavioural signals are noisy and therefore not reliable enough to be employed. Among many, a combination of dwell time and task information has been shown to be effective for relevance judgement prediction. However, the task information might not be available to the system at all times. Thus, there is a need for other sources of information which can be used as a substitute for task information. Recently, affective and physiological signals have shown promise as a potential source of information for relevance judgement prediction. However, their accuracy is not high enough to be applicable on their own.This paper investigates whether affective and physiological signals can be used as a complementary source of information for behavioural signals (i.e. dwell time) to create a reliable signal for relevance judgement prediction. Using a video retrieval system as a use case, we study and compare the effectiveness of the affective and physiological signals on their own, as well as in combination with behavioural signals for the relevance judgment prediction task across four different search intentions: seeking information, re-finding a particular information object, and two different entertainment intentions (i.e. entertainment by adjusting arousal level, and entertainment by adjusting mood). Our experimental results show that the effectiveness of studied signals varies across different search intentions, and when affective and physiological signals are combined with dwell time, a significant improvement can be achieved. Overall, these findings will help to implement better search engines in the future.

AB - The effectiveness of various behavioural signals for implicit relevance feedback models has been exhaustively studied. Despite the advantages of such techniques for a real time information retrieval system, most of the behavioural signals are noisy and therefore not reliable enough to be employed. Among many, a combination of dwell time and task information has been shown to be effective for relevance judgement prediction. However, the task information might not be available to the system at all times. Thus, there is a need for other sources of information which can be used as a substitute for task information. Recently, affective and physiological signals have shown promise as a potential source of information for relevance judgement prediction. However, their accuracy is not high enough to be applicable on their own.This paper investigates whether affective and physiological signals can be used as a complementary source of information for behavioural signals (i.e. dwell time) to create a reliable signal for relevance judgement prediction. Using a video retrieval system as a use case, we study and compare the effectiveness of the affective and physiological signals on their own, as well as in combination with behavioural signals for the relevance judgment prediction task across four different search intentions: seeking information, re-finding a particular information object, and two different entertainment intentions (i.e. entertainment by adjusting arousal level, and entertainment by adjusting mood). Our experimental results show that the effectiveness of studied signals varies across different search intentions, and when affective and physiological signals are combined with dwell time, a significant improvement can be achieved. Overall, these findings will help to implement better search engines in the future.

KW - implicit relevance feedback

KW - affective

KW - physiological

KW - behavioural

KW - dwell time

KW - search intentions

UR - https://dl.acm.org

U2 - 10.1145/2484028.2484074

DO - 10.1145/2484028.2484074

M3 - Conference contribution book

SN - 9781450320344

SP - 133

EP - 142

BT - Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval

CY - New York

ER -

Moshfeghi Y, Jose JM. An effective implicit relevance feedback technique using affective, physiological and behavioural features. In Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York. 2013. p. 133-142 https://doi.org/10.1145/2484028.2484074