The Role of Word-Eye-Fixations for Query Term Prediction

Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review

Autoren

  • Masoud Davari
  • Daniel Hienert
  • Dagmar Kern
  • Stefan Dietze

Externe Organisationen

  • GESIS - Leibniz-Institut für Sozialwissenschaften
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des SammelwerksCHIIR 2020
UntertitelProceedings of the 2020 Conference on Human Information Interaction and Retrieval
Seiten422-426
Seitenumfang5
ISBN (elektronisch)9781450368926
PublikationsstatusVeröffentlicht - 14 März 2020
Extern publiziertJa
VeranstaltungCHIIR 2020: ACM SIGIR Conference on Human Information Interaction and Retrieval - Vancouver, Kanada
Dauer: 14 März 2020 → 18 März 2020

Abstract

Throughout the search process, the user's gaze on inspected SERPs and websites can reveal his or her search interests. Gaze behavior can be captured with eye tracking and described with word-eye-fixations. Word-eye-fixations contain the user's accumulated gaze fixation duration on each individual word of a web page. In this work, we analyze the role of word-eye-fixations for predicting query terms. We investigate the relationship between a range of in-session features, in particular, gaze data, with the query terms and train models for predicting query terms. We use a dataset of 50 search sessions obtained through a lab study in the social sciences domain. Using established machine learning models, we can predict query terms with comparably high accuracy, even with only little training data. Feature analysis shows that the categories Fixation, Query Relevance and Session Topic contain the most effective features for our task.

ASJC Scopus Sachgebiete

Zitieren

The Role of Word-Eye-Fixations for Query Term Prediction. / Davari, Masoud; Hienert, Daniel; Kern, Dagmar et al.
CHIIR 2020: Proceedings of the 2020 Conference on Human Information Interaction and Retrieval. 2020. S. 422-426.

Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review

Davari, M, Hienert, D, Kern, D & Dietze, S 2020, The Role of Word-Eye-Fixations for Query Term Prediction. in CHIIR 2020: Proceedings of the 2020 Conference on Human Information Interaction and Retrieval. S. 422-426, CHIIR 2020, Vancouver, Kanada, 14 März 2020. https://doi.org/10.1145/3343413.3378010
Davari, M., Hienert, D., Kern, D., & Dietze, S. (2020). The Role of Word-Eye-Fixations for Query Term Prediction. In CHIIR 2020: Proceedings of the 2020 Conference on Human Information Interaction and Retrieval (S. 422-426) https://doi.org/10.1145/3343413.3378010
Davari M, Hienert D, Kern D, Dietze S. The Role of Word-Eye-Fixations for Query Term Prediction. in CHIIR 2020: Proceedings of the 2020 Conference on Human Information Interaction and Retrieval. 2020. S. 422-426 doi: 10.1145/3343413.3378010
Davari, Masoud ; Hienert, Daniel ; Kern, Dagmar et al. / The Role of Word-Eye-Fixations for Query Term Prediction. CHIIR 2020: Proceedings of the 2020 Conference on Human Information Interaction and Retrieval. 2020. S. 422-426
Download
@inproceedings{ed503928450e451fbbabef1f0500f35f,
title = "The Role of Word-Eye-Fixations for Query Term Prediction",
abstract = "Throughout the search process, the user's gaze on inspected SERPs and websites can reveal his or her search interests. Gaze behavior can be captured with eye tracking and described with word-eye-fixations. Word-eye-fixations contain the user's accumulated gaze fixation duration on each individual word of a web page. In this work, we analyze the role of word-eye-fixations for predicting query terms. We investigate the relationship between a range of in-session features, in particular, gaze data, with the query terms and train models for predicting query terms. We use a dataset of 50 search sessions obtained through a lab study in the social sciences domain. Using established machine learning models, we can predict query terms with comparably high accuracy, even with only little training data. Feature analysis shows that the categories Fixation, Query Relevance and Session Topic contain the most effective features for our task.",
keywords = "Eye tracking, Gaze behavior, Prediction, Query terms",
author = "Masoud Davari and Daniel Hienert and Dagmar Kern and Stefan Dietze",
year = "2020",
month = mar,
day = "14",
doi = "10.1145/3343413.3378010",
language = "English",
pages = "422--426",
booktitle = "CHIIR 2020",
note = "CHIIR 2020 : ACM SIGIR Conference on Human Information Interaction and Retrieval ; Conference date: 14-03-2020 Through 18-03-2020",

}

Download

TY - GEN

T1 - The Role of Word-Eye-Fixations for Query Term Prediction

AU - Davari, Masoud

AU - Hienert, Daniel

AU - Kern, Dagmar

AU - Dietze, Stefan

PY - 2020/3/14

Y1 - 2020/3/14

N2 - Throughout the search process, the user's gaze on inspected SERPs and websites can reveal his or her search interests. Gaze behavior can be captured with eye tracking and described with word-eye-fixations. Word-eye-fixations contain the user's accumulated gaze fixation duration on each individual word of a web page. In this work, we analyze the role of word-eye-fixations for predicting query terms. We investigate the relationship between a range of in-session features, in particular, gaze data, with the query terms and train models for predicting query terms. We use a dataset of 50 search sessions obtained through a lab study in the social sciences domain. Using established machine learning models, we can predict query terms with comparably high accuracy, even with only little training data. Feature analysis shows that the categories Fixation, Query Relevance and Session Topic contain the most effective features for our task.

AB - Throughout the search process, the user's gaze on inspected SERPs and websites can reveal his or her search interests. Gaze behavior can be captured with eye tracking and described with word-eye-fixations. Word-eye-fixations contain the user's accumulated gaze fixation duration on each individual word of a web page. In this work, we analyze the role of word-eye-fixations for predicting query terms. We investigate the relationship between a range of in-session features, in particular, gaze data, with the query terms and train models for predicting query terms. We use a dataset of 50 search sessions obtained through a lab study in the social sciences domain. Using established machine learning models, we can predict query terms with comparably high accuracy, even with only little training data. Feature analysis shows that the categories Fixation, Query Relevance and Session Topic contain the most effective features for our task.

KW - Eye tracking

KW - Gaze behavior

KW - Prediction

KW - Query terms

UR - http://www.scopus.com/inward/record.url?scp=85082443691&partnerID=8YFLogxK

U2 - 10.1145/3343413.3378010

DO - 10.1145/3343413.3378010

M3 - Conference contribution

AN - SCOPUS:85082443691

SP - 422

EP - 426

BT - CHIIR 2020

T2 - CHIIR 2020

Y2 - 14 March 2020 through 18 March 2020

ER -