Platform for Evaluation of Readers' Implicit Feedback Using Eye-Tracking

Miroslav Živković; Egon L. van den Broek; Frans van der Sluis

doi:10.1145/3232078.3232099

Platform for Evaluation of Readers' Implicit Feedback Using Eye-Tracking

Miroslav Živković, Egon L. van den Broek, Frans van der Sluis

Abstract

Large amounts of information are nowadays easily obtainable using the Internet, and using implicit feedback whether a reader finds a text interesting is desirable. Eye-tracking technology could be used for such a feedback, and a combination of eye-movement features and a textual complexity measure can be used to predict the user's interest. In this paper we give an overview of a platform developed to evaluate and visualize implicit feedback of a person who reads a text. Based on the eye-movement samples provided, a model is trained that could be used to predict comprehensibility of a user reading a text. This prediction is combined with objective complexity evaluation of the text using data mining methods, and the outcome is used to select a text (from a repository) that a user may find more valuable (interesting). We briefly discuss the requirements, architecture and implementation of this platform.

Original language	English
Title of host publication	ECCE'18: Proceedings of the 36th European Conference on Cognitive Ergonomics
Number of pages	4
Volume	36
Place of Publication	New York, NY, USA
Publisher	Association for Computing Machinery
Publication date	5 Sept 2018
Article number	13
ISBN (Print)	978-1-4503-6449-2
DOIs	https://doi.org/10.1145/3232078.3232099
Publication status	Published - 5 Sept 2018
Event	European Conference on Cognitive Ergonomics - Utrecht, Netherlands Duration: 5 Sept 2018 → 7 Sept 2018 Conference number: 36

Conference

Conference	European Conference on Cognitive Ergonomics
Number	36
Country/Territory	Netherlands
City	Utrecht
Period	05/09/2018 → 07/09/2018

Series	ECCE'18

Access to Document

10.1145/3232078.3232099

http://doi.acm.org/10.1145/3232078.3232099

Cite this

Platform for Evaluation of Readers' Implicit Feedback Using Eye-Tracking. / Živković, Miroslav; van den Broek, Egon L.; van der Sluis, Frans.

ECCE'18: Proceedings of the 36th European Conference on Cognitive Ergonomics. Vol. 36 New York, NY, USA : Association for Computing Machinery, 2018. 13 (ECCE'18).

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

Živković, M, van den Broek, EL & van der Sluis, F 2018, Platform for Evaluation of Readers' Implicit Feedback Using Eye-Tracking. in ECCE'18: Proceedings of the 36th European Conference on Cognitive Ergonomics. vol. 36, 13, Association for Computing Machinery, New York, NY, USA, ECCE'18, European Conference on Cognitive Ergonomics, Utrecht, Netherlands, 05/09/2018. https://doi.org/10.1145/3232078.3232099

@inproceedings{5e8b6ad8b40c4f90a7a07533594eaff8,

title = "Platform for Evaluation of Readers' Implicit Feedback Using Eye-Tracking",

abstract = "Large amounts of information are nowadays easily obtainable using the Internet, and using implicit feedback whether a reader finds a text interesting is desirable. Eye-tracking technology could be used for such a feedback, and a combination of eye-movement features and a textual complexity measure can be used to predict the user's interest. In this paper we give an overview of a platform developed to evaluate and visualize implicit feedback of a person who reads a text. Based on the eye-movement samples provided, a model is trained that could be used to predict comprehensibility of a user reading a text. This prediction is combined with objective complexity evaluation of the text using data mining methods, and the outcome is used to select a text (from a repository) that a user may find more valuable (interesting). We briefly discuss the requirements, architecture and implementation of this platform.",

keywords = "Information experience, Java, WEKA, eye-tracking",

author = "Miroslav {\v Z}ivkovi{\'c} and {van den Broek}, {Egon L.} and {van der Sluis}, Frans",

year = "2018",

month = sep,

day = "5",

doi = "10.1145/3232078.3232099",

language = "English",

isbn = "978-1-4503-6449-2",

volume = "36",

series = "ECCE'18",

publisher = "Association for Computing Machinery",

booktitle = "ECCE'18: Proceedings of the 36th European Conference on Cognitive Ergonomics",

note = "European Conference on Cognitive Ergonomics, ECCE2018 ; Conference date: 05-09-2018 Through 07-09-2018",

}

TY - GEN

T1 - Platform for Evaluation of Readers' Implicit Feedback Using Eye-Tracking

AU - Živković, Miroslav

AU - van den Broek, Egon L.

AU - van der Sluis, Frans

N1 - Conference code: 36

PY - 2018/9/5

Y1 - 2018/9/5

N2 - Large amounts of information are nowadays easily obtainable using the Internet, and using implicit feedback whether a reader finds a text interesting is desirable. Eye-tracking technology could be used for such a feedback, and a combination of eye-movement features and a textual complexity measure can be used to predict the user's interest. In this paper we give an overview of a platform developed to evaluate and visualize implicit feedback of a person who reads a text. Based on the eye-movement samples provided, a model is trained that could be used to predict comprehensibility of a user reading a text. This prediction is combined with objective complexity evaluation of the text using data mining methods, and the outcome is used to select a text (from a repository) that a user may find more valuable (interesting). We briefly discuss the requirements, architecture and implementation of this platform.

AB - Large amounts of information are nowadays easily obtainable using the Internet, and using implicit feedback whether a reader finds a text interesting is desirable. Eye-tracking technology could be used for such a feedback, and a combination of eye-movement features and a textual complexity measure can be used to predict the user's interest. In this paper we give an overview of a platform developed to evaluate and visualize implicit feedback of a person who reads a text. Based on the eye-movement samples provided, a model is trained that could be used to predict comprehensibility of a user reading a text. This prediction is combined with objective complexity evaluation of the text using data mining methods, and the outcome is used to select a text (from a repository) that a user may find more valuable (interesting). We briefly discuss the requirements, architecture and implementation of this platform.

KW - Information experience, Java, WEKA, eye-tracking

U2 - 10.1145/3232078.3232099

DO - 10.1145/3232078.3232099

M3 - Article in proceedings

SN - 978-1-4503-6449-2

VL - 36

T3 - ECCE'18

BT - ECCE'18: Proceedings of the 36th European Conference on Cognitive Ergonomics

PB - Association for Computing Machinery

CY - New York, NY, USA

T2 - European Conference on Cognitive Ergonomics

Y2 - 5 September 2018 through 7 September 2018

ER -

Platform for Evaluation of Readers' Implicit Feedback Using Eye-Tracking

Abstract

Conference

Access to Document

Fingerprint

Cite this