skip to main content
10.1145/2876456.2879481acmconferencesArticle/Chapter ViewAbstractPublication PagesiuiConference Proceedingsconference-collections
poster

Fixation-to-Word Mapping with Classification of Saccades

Published: 07 March 2016 Publication History

Abstract

Eye movement is expected to provide important clues for analyzing the human reading process. However, the noisy tracking environment makes it difficult to map the gaze data captured by eye-trackers to the user's intended word. In this paper, we propose an effective approach for accurately mapping a fixation to a word in the text. Our method regards consecutive horizontally progressive fixations as a sequential reading segment. We first classify transitions between segments according to six classes, and then identify the set of segments associated with each line of the document. Our experiments demonstrate that the proposed method achieves 87% mapping accuracy (15% higher than our previous work) with a classification performance of 84%. We also confirmed that manual annotation time can be reduced by using our approach as a reference. We believe that our method provides sufficiently good accuracy to warrant future analysis.

References

[1]
Ralf Biedert, Jörn Hees, Andreas Dengel, and Georg Buscher. 2012. A Robust Realtime Reading-Skimming Classifier. The Symposium on Eye Tracking Research and Applications (ETRA '12) (2012), 123--130.
[2]
Michael Carl. 2013. Dynamic Programming for Re-mapping Noisy Fixations in Translation Tasks. Journal of Eye Movement Research, Vol. 6, No. 2 (2013), 1--11.
[3]
Kai Kunze, Katsutoshi Masai, Masahiko Inami, Ömer Sacakli, Marcus Liwicki, Andreas Dengel, Shoya Ishimaru, and Koichi Kise. 2015. Quantifying Reading Habits: Counting How Many Words You Read. Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing (2015), 87--96.
[4]
Pascual Martínez-Gómez and Akiko Aizawa. 2014. Recognition of Understanding Level and Language Skill Using Measurements of Reading Behavior. 2014 International Conference on Intelligent User Interfaces (IUI '14) (2014), 95--104.
[5]
Abdrea Mazzei, Shahram Eivazi, Youri Marko, Frederic Laplan, and Pierre Dillenbourg. 2014. 3D Model-Based Gaze Estimation in Natural Reading: a Systematic Error Correction Procedure based on Annotated Texts. The Symposium on Eye Tracking Research and Applications (ETRA '14) (2014), 87--90.
[6]
Abhijit Mishra, Michael Carl, and Pushpak Bhattacharya. 2012. A Heuristic-Based Approach for Systematic Error Correction of Gaze Data for Reading. 24th International Conference on Computational Linguistics (2012), 71--80.
[7]
Keith Rayner. 1998. Eye Movements in Reading and Information Processing: 20 Years of Research. Psychological Bulletin 124.3 (1998), 372--422.
[8]
Akito Yamaya, Goran Topić, Pascual Martínez-Gómez, and Akiko Aizawa. 2015. Dynamic-Programming-Based Method for Fixation-to-Word Mapping. Intelligent Decision Technologies (2015), 649--659.

Cited By

View all
  • (2017)Vertical Error Correction Using Classification of Transitions between Sequential Reading SegmentsJournal of Information Processing10.2197/ipsjjip.25.10025(100-106)Online publication date: 2017

Index Terms

  1. Fixation-to-Word Mapping with Classification of Saccades

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    IUI '16 Companion: Companion Publication of the 21st International Conference on Intelligent User Interfaces
    March 2016
    446 pages
    ISBN:9781450341400
    DOI:10.1145/2876456
    Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 07 March 2016

    Check for updates

    Author Tags

    1. eye-tracking
    2. fixation-to-word mapping
    3. reading

    Qualifiers

    • Poster

    Funding Sources

    • JSPS KAKENHI

    Conference

    IUI'16
    Sponsor:

    Acceptance Rates

    IUI '16 Companion Paper Acceptance Rate 49 of 194 submissions, 25%;
    Overall Acceptance Rate 746 of 2,811 submissions, 27%

    Upcoming Conference

    IUI '25

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)2
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 13 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2017)Vertical Error Correction Using Classification of Transitions between Sequential Reading SegmentsJournal of Information Processing10.2197/ipsjjip.25.10025(100-106)Online publication date: 2017

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media