Brainsourcing: Crowdsourcing Recognition Tasks via Collaborative Brain-Computer Interfacing

Keith M. Davis; Lauri Kangassalo; Michiel Spapé; Tuukka Ruotsalo

doi:10.1145/3313831.3376288

Brainsourcing: Crowdsourcing Recognition Tasks via Collaborative Brain-Computer Interfacing

Keith M. Davis, Lauri Kangassalo, Michiel Spapé, Tuukka Ruotsalo

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

16 Citations (Scopus)

Abstract

This paper introduces brainsourcing: utilizing brain responses of a group of human contributors each performing a recognition task to determine classes of stimuli. We investigate to what extent it is possible to infer reliable class labels using data collected utilizing electroencephalography (EEG) from participants given a set of common stimuli. An experiment (N=30) measuring EEG responses to visual features of faces (gender, hair color, age, smile) revealed an improved F1 score of 0.94 for a crowd of twelve participants compared to an F1 score of 0.67 derived from individual participants and a random chance of 0.50. Our results demonstrate the methodological and pragmatic feasibility of brainsourcing in labeling tasks and opens avenues for more general applications using brain-computer interfacing in a crowdsourced setting.

Original language	English
Title of host publication	CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
Publisher	Association for Computing Machinery
Publication date	2020
Pages	1-14
DOIs	https://doi.org/10.1145/3313831.3376288
Publication status	Published - 2020
Externally published	Yes

Access to Document

10.1145/3313831.3376288

https://dl.acm.org/doi/10.1145/3313831.3376288

Cite this

Brainsourcing: Crowdsourcing Recognition Tasks via Collaborative Brain-Computer Interfacing. / Davis, Keith M.; Kangassalo, Lauri; Spapé, Michiel; Ruotsalo, Tuukka.

CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2020. p. 1-14.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

@inproceedings{6dd64c927f6b42449365482b53211ee3,

title = "Brainsourcing: Crowdsourcing Recognition Tasks via Collaborative Brain-Computer Interfacing",

abstract = "This paper introduces brainsourcing: utilizing brain responses of a group of human contributors each performing a recognition task to determine classes of stimuli. We investigate to what extent it is possible to infer reliable class labels using data collected utilizing electroencephalography (EEG) from participants given a set of common stimuli. An experiment (N=30) measuring EEG responses to visual features of faces (gender, hair color, age, smile) revealed an improved F1 score of 0.94 for a crowd of twelve participants compared to an F1 score of 0.67 derived from individual participants and a random chance of 0.50. Our results demonstrate the methodological and pragmatic feasibility of brainsourcing in labeling tasks and opens avenues for more general applications using brain-computer interfacing in a crowdsourced setting.",

author = "Davis, {Keith M.} and Lauri Kangassalo and Michiel Spap{\'e} and Tuukka Ruotsalo",

year = "2020",

doi = "10.1145/3313831.3376288",

language = "English",

pages = "1--14",

booktitle = "CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems",

publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Brainsourcing: Crowdsourcing Recognition Tasks via Collaborative Brain-Computer Interfacing

AU - Davis, Keith M.

AU - Kangassalo, Lauri

AU - Spapé, Michiel

AU - Ruotsalo, Tuukka

PY - 2020

Y1 - 2020

N2 - This paper introduces brainsourcing: utilizing brain responses of a group of human contributors each performing a recognition task to determine classes of stimuli. We investigate to what extent it is possible to infer reliable class labels using data collected utilizing electroencephalography (EEG) from participants given a set of common stimuli. An experiment (N=30) measuring EEG responses to visual features of faces (gender, hair color, age, smile) revealed an improved F1 score of 0.94 for a crowd of twelve participants compared to an F1 score of 0.67 derived from individual participants and a random chance of 0.50. Our results demonstrate the methodological and pragmatic feasibility of brainsourcing in labeling tasks and opens avenues for more general applications using brain-computer interfacing in a crowdsourced setting.

AB - This paper introduces brainsourcing: utilizing brain responses of a group of human contributors each performing a recognition task to determine classes of stimuli. We investigate to what extent it is possible to infer reliable class labels using data collected utilizing electroencephalography (EEG) from participants given a set of common stimuli. An experiment (N=30) measuring EEG responses to visual features of faces (gender, hair color, age, smile) revealed an improved F1 score of 0.94 for a crowd of twelve participants compared to an F1 score of 0.67 derived from individual participants and a random chance of 0.50. Our results demonstrate the methodological and pragmatic feasibility of brainsourcing in labeling tasks and opens avenues for more general applications using brain-computer interfacing in a crowdsourced setting.

U2 - 10.1145/3313831.3376288

DO - 10.1145/3313831.3376288

M3 - Article in proceedings

SP - 1

EP - 14

BT - CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

PB - Association for Computing Machinery

ER -