Leveraging Eye-gaze and Time-series Features to Predict User Interests and Build a Recommendation Model for Visual Analysis

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

We developed a new concept to improve the efficiency of visual analysis through visual recommendations. It uses a novel eye-gaze based recommendation model that aids users in identifying interesting time-series patterns. Our model combines time-series features and eye-gaze interests, captured via an eye-tracker. Mouse selections are also considered. The system provides an overlay visualization with recommended patterns, and an eye-history graph, that supports the users in the data exploration process. We conducted an experiment with 5 tasks where 30 participants explored sensor data of a wind turbine. This work presents results on pre-attentive features, and discusses the precision/recall of our model in comparison to final selections made by users. Our model helps users to efficiently identify interesting time-series patterns.

Original languageEnglish
Title of host publicationProceedings - ETRA 2018
Subtitle of host publication2018 ACM Symposium on Eye Tracking Research and Applications
PublisherAssociation of Computing Machinery
ISBN (Electronic)9781450357067
DOIs
Publication statusPublished - 2018
Event10th ACM Symposium on Eye Tracking Research and Applications, ETRA 2018 - Warsaw, Poland
Duration: 14 Jun 201817 Jun 2018

Conference

Conference10th ACM Symposium on Eye Tracking Research and Applications, ETRA 2018
CountryPoland
CityWarsaw
Period14/06/1817/06/18

Fingerprint

Time series
Wind turbines
Visualization
History
Sensors
Experiments

Keywords

  • Evaluation
  • Eye-tracking
  • Model
  • Recommend
  • Similarity
  • Time-series
  • Visual analytics

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Ophthalmology
  • Sensory Systems

Fields of Expertise

  • Information, Communication & Computing

Cite this

Leveraging Eye-gaze and Time-series Features to Predict User Interests and Build a Recommendation Model for Visual Analysis. / Silva, N.; Schreck, T.; Veas, E.; Sabol, V.; Eggeling, E.; Fellner, D.

Proceedings - ETRA 2018: 2018 ACM Symposium on Eye Tracking Research and Applications. Association of Computing Machinery, 2018. a13.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Silva, N, Schreck, T, Veas, E, Sabol, V, Eggeling, E & Fellner, D 2018, Leveraging Eye-gaze and Time-series Features to Predict User Interests and Build a Recommendation Model for Visual Analysis. in Proceedings - ETRA 2018: 2018 ACM Symposium on Eye Tracking Research and Applications., a13, Association of Computing Machinery, 10th ACM Symposium on Eye Tracking Research and Applications, ETRA 2018, Warsaw, Poland, 14/06/18. https://doi.org/10.1145/3204493.3204546
Silva, N. ; Schreck, T. ; Veas, E. ; Sabol, V. ; Eggeling, E. ; Fellner, D. / Leveraging Eye-gaze and Time-series Features to Predict User Interests and Build a Recommendation Model for Visual Analysis. Proceedings - ETRA 2018: 2018 ACM Symposium on Eye Tracking Research and Applications. Association of Computing Machinery, 2018.
@inproceedings{18417a6b299a46a79fa15ff0727c1b4b,
title = "Leveraging Eye-gaze and Time-series Features to Predict User Interests and Build a Recommendation Model for Visual Analysis",
abstract = "We developed a new concept to improve the efficiency of visual analysis through visual recommendations. It uses a novel eye-gaze based recommendation model that aids users in identifying interesting time-series patterns. Our model combines time-series features and eye-gaze interests, captured via an eye-tracker. Mouse selections are also considered. The system provides an overlay visualization with recommended patterns, and an eye-history graph, that supports the users in the data exploration process. We conducted an experiment with 5 tasks where 30 participants explored sensor data of a wind turbine. This work presents results on pre-attentive features, and discusses the precision/recall of our model in comparison to final selections made by users. Our model helps users to efficiently identify interesting time-series patterns.",
keywords = "Evaluation, Eye-tracking, Model, Recommend, Similarity, Time-series, Visual analytics",
author = "N. Silva and T. Schreck and E. Veas and V. Sabol and E. Eggeling and D. Fellner",
year = "2018",
doi = "10.1145/3204493.3204546",
language = "English",
booktitle = "Proceedings - ETRA 2018",
publisher = "Association of Computing Machinery",
address = "United States",

}

TY - GEN

T1 - Leveraging Eye-gaze and Time-series Features to Predict User Interests and Build a Recommendation Model for Visual Analysis

AU - Silva, N.

AU - Schreck, T.

AU - Veas, E.

AU - Sabol, V.

AU - Eggeling, E.

AU - Fellner, D.

PY - 2018

Y1 - 2018

N2 - We developed a new concept to improve the efficiency of visual analysis through visual recommendations. It uses a novel eye-gaze based recommendation model that aids users in identifying interesting time-series patterns. Our model combines time-series features and eye-gaze interests, captured via an eye-tracker. Mouse selections are also considered. The system provides an overlay visualization with recommended patterns, and an eye-history graph, that supports the users in the data exploration process. We conducted an experiment with 5 tasks where 30 participants explored sensor data of a wind turbine. This work presents results on pre-attentive features, and discusses the precision/recall of our model in comparison to final selections made by users. Our model helps users to efficiently identify interesting time-series patterns.

AB - We developed a new concept to improve the efficiency of visual analysis through visual recommendations. It uses a novel eye-gaze based recommendation model that aids users in identifying interesting time-series patterns. Our model combines time-series features and eye-gaze interests, captured via an eye-tracker. Mouse selections are also considered. The system provides an overlay visualization with recommended patterns, and an eye-history graph, that supports the users in the data exploration process. We conducted an experiment with 5 tasks where 30 participants explored sensor data of a wind turbine. This work presents results on pre-attentive features, and discusses the precision/recall of our model in comparison to final selections made by users. Our model helps users to efficiently identify interesting time-series patterns.

KW - Evaluation

KW - Eye-tracking

KW - Model

KW - Recommend

KW - Similarity

KW - Time-series

KW - Visual analytics

UR - http://www.scopus.com/inward/record.url?scp=85049663230&partnerID=8YFLogxK

U2 - 10.1145/3204493.3204546

DO - 10.1145/3204493.3204546

M3 - Conference contribution

BT - Proceedings - ETRA 2018

PB - Association of Computing Machinery

ER -