Focus Paragraph Detection for Online Zero-Effort Queries: Lessons Learned from Eye-Tracking Data

Christin Seifert; Annett Mitschick; Jörg Schlötterer; Raimund Dachselt

doi:10.1145/3020165.3022138

Focus Paragraph Detection for Online Zero-Effort Queries: Lessons Learned from Eye-Tracking Data

Christin Seifert, Annett Mitschick, Jörg Schlötterer, Raimund Dachselt

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

Abstract

In order to realize zero-effort retrieval in a web-context, it is crucial to identify the part of the web page the user is focusing on. In this paper, we investigate the identification of focus paragraphs in web pages. Starting from a naive baseline for paragraph and focus paragraph detection, we conducted an eye-tracking study to evaluate the most promising features. We found that single features (mouse position, paragraph position, mouse activity) are less predictive for gaze which confirms findings from other studies. The results indicate that an algorithm for focus paragraph detection needs to incorporate a weighted combination of those features as well as additional features, e.g. semantic context derived from the user's web history.

Original language	English
Title of host publication	CHIIR'17. Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval
Publisher	ACM Press
Pages	301-304
Number of pages	4
ISBN (Print)	978-1-4503-4677-1
DOIs	https://doi.org/10.1145/3020165.3022138
Publication status	Published - 2017
Event	Conference Human Information Interaction and Retrieval, CHIIR 2017 - Oslo, Norway Duration: 7 Mar 2017 → 11 Mar 2017 http://sigir.org/chiir2017/

Conference

Conference	Conference Human Information Interaction and Retrieval, CHIIR 2017
Abbreviated title	CHIIR 2017
Country	Norway
City	Oslo
Period	7/03/17 → 11/03/17
Internet address	http://sigir.org/chiir2017/

Keywords

eye tracking, focus paragraph detection, zero-effort queries

Access to Document

10.1145/3020165.3022138

Fingerprint Dive into the research topics of 'Focus Paragraph Detection for Online Zero-Effort Queries: Lessons Learned from Eye-Tracking Data'. Together they form a unique fingerprint.

Cite this

@inproceedings{21940b5a996e48d5ac1cdc1a71c04a7b,

title = "Focus Paragraph Detection for Online Zero-Effort Queries: Lessons Learned from Eye-Tracking Data",

abstract = "In order to realize zero-effort retrieval in a web-context, it is crucial to identify the part of the web page the user is focusing on. In this paper, we investigate the identification of focus paragraphs in web pages. Starting from a naive baseline for paragraph and focus paragraph detection, we conducted an eye-tracking study to evaluate the most promising features. We found that single features (mouse position, paragraph position, mouse activity) are less predictive for gaze which confirms findings from other studies. The results indicate that an algorithm for focus paragraph detection needs to incorporate a weighted combination of those features as well as additional features, e.g. semantic context derived from the user's web history.",

keywords = "eye tracking, focus paragraph detection, zero-effort queries",

author = "Christin Seifert and Annett Mitschick and J{\"o}rg Schl{\"o}tterer and Raimund Dachselt",

year = "2017",

doi = "10.1145/3020165.3022138",

language = "English",

isbn = "978-1-4503-4677-1",

pages = "301--304",

booktitle = "CHIIR'17. Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval",

publisher = "ACM Press",

note = "Conference Human Information Interaction and Retrieval, CHIIR 2017, CHIIR 2017 ; Conference date: 07-03-2017 Through 11-03-2017",

url = "http://sigir.org/chiir2017/",

}

Seifert, C, Mitschick, A, Schlötterer, J & Dachselt, R 2017, Focus Paragraph Detection for Online Zero-Effort Queries: Lessons Learned from Eye-Tracking Data. in CHIIR'17. Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval. ACM Press, pp. 301-304, Conference Human Information Interaction and Retrieval, CHIIR 2017, Oslo, Norway, 7/03/17. https://doi.org/10.1145/3020165.3022138

Focus Paragraph Detection for Online Zero-Effort Queries: Lessons Learned from Eye-Tracking Data. / Seifert, Christin; Mitschick, Annett; Schlötterer, Jörg; Dachselt, Raimund.

CHIIR'17. Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval. ACM Press, 2017. p. 301-304.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Focus Paragraph Detection for Online Zero-Effort Queries: Lessons Learned from Eye-Tracking Data

AU - Seifert, Christin

AU - Mitschick, Annett

AU - Schlötterer, Jörg

AU - Dachselt, Raimund

PY - 2017

Y1 - 2017

N2 - In order to realize zero-effort retrieval in a web-context, it is crucial to identify the part of the web page the user is focusing on. In this paper, we investigate the identification of focus paragraphs in web pages. Starting from a naive baseline for paragraph and focus paragraph detection, we conducted an eye-tracking study to evaluate the most promising features. We found that single features (mouse position, paragraph position, mouse activity) are less predictive for gaze which confirms findings from other studies. The results indicate that an algorithm for focus paragraph detection needs to incorporate a weighted combination of those features as well as additional features, e.g. semantic context derived from the user's web history.

AB - In order to realize zero-effort retrieval in a web-context, it is crucial to identify the part of the web page the user is focusing on. In this paper, we investigate the identification of focus paragraphs in web pages. Starting from a naive baseline for paragraph and focus paragraph detection, we conducted an eye-tracking study to evaluate the most promising features. We found that single features (mouse position, paragraph position, mouse activity) are less predictive for gaze which confirms findings from other studies. The results indicate that an algorithm for focus paragraph detection needs to incorporate a weighted combination of those features as well as additional features, e.g. semantic context derived from the user's web history.

KW - eye tracking, focus paragraph detection, zero-effort queries

U2 - 10.1145/3020165.3022138

DO - 10.1145/3020165.3022138

M3 - Conference contribution

SN - 978-1-4503-4677-1

SP - 301

EP - 304

BT - CHIIR'17. Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval

PB - ACM Press

T2 - Conference Human Information Interaction and Retrieval, CHIIR 2017

Y2 - 7 March 2017 through 11 March 2017

ER -