Towards predicting a realisation of an information need based on brain signals

Yashar Moshfeghi, Peter Triantafillou, Frank E. Pollick

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

Abstract

The goal of Information Retrieval (IR) systems is to satisfy searchers ’Information Need (IN). Our research focuses on next-generation IR engines, which can proactively detect, identify, and serve INs without receiving explicit queries. It is essential, therefore, to be able to detect when INs occur. Previous research has established that a realisation of INs physically manifests itself with specific brain activity. With this work we take the next step, showing that monitoring brain activity can lead to accurate predictions of a realisation of IN occurrence. We have conducted experiments whereby twenty-four participants performed a Q/A Task, while their brain activity was being monitored using functional Magnetic Resonance Imaging (fMRI) technology. The questions were selected and developed from the TREC-8 and TREC 2001 Q/A Tracks. We present two methods for predicting the realisation of an IN, i.e. Generalised method (GM) and Personalised method (PM). GM is based on the collective brain activity of all twenty-four participants in a predetermined set of brain regions known to be involved in representing a realisation of INs. PM is unique to each individual and employs a 'Searchlight' analysis to locate brain regions informative for distinguishing when a "specific" user realises an information need. The results of our study show that both methods were able to predict a realisation of an IN (statistically) significantly better than chance. Our results also show that PM (statistically) significantly outperformed GM interms of prediction accuracy. These encouraging findings make the first fundamental step towards proactive IR engines based on brain signals.
LanguageEnglish
Title of host publicationThe Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
Place of PublicationNew York, NY
Pages1300-1309
Number of pages10
ISBN (Electronic)9781450366748
DOIs
Publication statusPublished - 13 May 2019
EventThe Web Conference 2019 - San Francisco , United States
Duration: 13 May 201917 May 2019

Conference

ConferenceThe Web Conference 2019
CountryUnited States
CitySan Francisco
Period13/05/1917/05/19

Fingerprint

Brain
Information retrieval
Searchlights
Engines
Information retrieval systems
Monitoring
Experiments

Keywords

  • information need
  • prediction
  • fMRI
  • brain signals
  • proactive
  • information retrieval
  • generalised
  • personalised

Cite this

Moshfeghi, Y., Triantafillou, P., & Pollick, F. E. (2019). Towards predicting a realisation of an information need based on brain signals. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 (pp. 1300-1309). New York, NY. https://doi.org/10.1145/3308558.3313671
Moshfeghi, Yashar ; Triantafillou, Peter ; Pollick, Frank E. / Towards predicting a realisation of an information need based on brain signals. The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. New York, NY, 2019. pp. 1300-1309
@inproceedings{43e2c029930148a980843c16591a9f3b,
title = "Towards predicting a realisation of an information need based on brain signals",
abstract = "The goal of Information Retrieval (IR) systems is to satisfy searchers ’Information Need (IN). Our research focuses on next-generation IR engines, which can proactively detect, identify, and serve INs without receiving explicit queries. It is essential, therefore, to be able to detect when INs occur. Previous research has established that a realisation of INs physically manifests itself with specific brain activity. With this work we take the next step, showing that monitoring brain activity can lead to accurate predictions of a realisation of IN occurrence. We have conducted experiments whereby twenty-four participants performed a Q/A Task, while their brain activity was being monitored using functional Magnetic Resonance Imaging (fMRI) technology. The questions were selected and developed from the TREC-8 and TREC 2001 Q/A Tracks. We present two methods for predicting the realisation of an IN, i.e. Generalised method (GM) and Personalised method (PM). GM is based on the collective brain activity of all twenty-four participants in a predetermined set of brain regions known to be involved in representing a realisation of INs. PM is unique to each individual and employs a 'Searchlight' analysis to locate brain regions informative for distinguishing when a {"}specific{"} user realises an information need. The results of our study show that both methods were able to predict a realisation of an IN (statistically) significantly better than chance. Our results also show that PM (statistically) significantly outperformed GM interms of prediction accuracy. These encouraging findings make the first fundamental step towards proactive IR engines based on brain signals.",
keywords = "information need, prediction, fMRI, brain signals, proactive, information retrieval, generalised, personalised",
author = "Yashar Moshfeghi and Peter Triantafillou and Pollick, {Frank E.}",
year = "2019",
month = "5",
day = "13",
doi = "10.1145/3308558.3313671",
language = "English",
isbn = "9781450366748",
pages = "1300--1309",
booktitle = "The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019",

}

Moshfeghi, Y, Triantafillou, P & Pollick, FE 2019, Towards predicting a realisation of an information need based on brain signals. in The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. New York, NY, pp. 1300-1309, The Web Conference 2019, San Francisco , United States, 13/05/19. https://doi.org/10.1145/3308558.3313671

Towards predicting a realisation of an information need based on brain signals. / Moshfeghi, Yashar; Triantafillou, Peter; Pollick, Frank E.

The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. New York, NY, 2019. p. 1300-1309.

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

TY - GEN

T1 - Towards predicting a realisation of an information need based on brain signals

AU - Moshfeghi, Yashar

AU - Triantafillou, Peter

AU - Pollick, Frank E.

PY - 2019/5/13

Y1 - 2019/5/13

N2 - The goal of Information Retrieval (IR) systems is to satisfy searchers ’Information Need (IN). Our research focuses on next-generation IR engines, which can proactively detect, identify, and serve INs without receiving explicit queries. It is essential, therefore, to be able to detect when INs occur. Previous research has established that a realisation of INs physically manifests itself with specific brain activity. With this work we take the next step, showing that monitoring brain activity can lead to accurate predictions of a realisation of IN occurrence. We have conducted experiments whereby twenty-four participants performed a Q/A Task, while their brain activity was being monitored using functional Magnetic Resonance Imaging (fMRI) technology. The questions were selected and developed from the TREC-8 and TREC 2001 Q/A Tracks. We present two methods for predicting the realisation of an IN, i.e. Generalised method (GM) and Personalised method (PM). GM is based on the collective brain activity of all twenty-four participants in a predetermined set of brain regions known to be involved in representing a realisation of INs. PM is unique to each individual and employs a 'Searchlight' analysis to locate brain regions informative for distinguishing when a "specific" user realises an information need. The results of our study show that both methods were able to predict a realisation of an IN (statistically) significantly better than chance. Our results also show that PM (statistically) significantly outperformed GM interms of prediction accuracy. These encouraging findings make the first fundamental step towards proactive IR engines based on brain signals.

AB - The goal of Information Retrieval (IR) systems is to satisfy searchers ’Information Need (IN). Our research focuses on next-generation IR engines, which can proactively detect, identify, and serve INs without receiving explicit queries. It is essential, therefore, to be able to detect when INs occur. Previous research has established that a realisation of INs physically manifests itself with specific brain activity. With this work we take the next step, showing that monitoring brain activity can lead to accurate predictions of a realisation of IN occurrence. We have conducted experiments whereby twenty-four participants performed a Q/A Task, while their brain activity was being monitored using functional Magnetic Resonance Imaging (fMRI) technology. The questions were selected and developed from the TREC-8 and TREC 2001 Q/A Tracks. We present two methods for predicting the realisation of an IN, i.e. Generalised method (GM) and Personalised method (PM). GM is based on the collective brain activity of all twenty-four participants in a predetermined set of brain regions known to be involved in representing a realisation of INs. PM is unique to each individual and employs a 'Searchlight' analysis to locate brain regions informative for distinguishing when a "specific" user realises an information need. The results of our study show that both methods were able to predict a realisation of an IN (statistically) significantly better than chance. Our results also show that PM (statistically) significantly outperformed GM interms of prediction accuracy. These encouraging findings make the first fundamental step towards proactive IR engines based on brain signals.

KW - information need

KW - prediction

KW - fMRI

KW - brain signals

KW - proactive

KW - information retrieval

KW - generalised

KW - personalised

UR - https://www2019.thewebconf.org/

U2 - 10.1145/3308558.3313671

DO - 10.1145/3308558.3313671

M3 - Conference contribution book

SN - 9781450366748

SP - 1300

EP - 1309

BT - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

CY - New York, NY

ER -

Moshfeghi Y, Triantafillou P, Pollick FE. Towards predicting a realisation of an information need based on brain signals. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. New York, NY. 2019. p. 1300-1309 https://doi.org/10.1145/3308558.3313671