Gaze-based detection of mind wandering during lecture viewing

Stephen Hutt; Jessica Hardey; Robert Bixler; Angela Stewart; Evan Risko; Sidney K. D’Mello

Gaze-based detection of mind wandering during lecture viewing

Stephen Hutt, Jessica Hardey, Robert Bixler, Angela Stewart, Evan Risko, Sidney K. D’Mello

Research output: Contribution to conference › Paper › peer-review

Abstract

We investigate the use of consumer-grade eye tracking to automatically detect Mind Wandering (MW) during learning from a recorded lecture, a key component of many Massive Open Online Courses (MOOCs). We considered two feature sets: stimulus-independent global gaze features (e.g., number of fixations, fixation duration), and stimulus-dependent local features. We trained Bayesian networks using the aforementioned features and students‟ self-reports of MW and validated them in a manner that generalized to new students. Our results indicated that models built with global features (F₁ MW = 0.47) outperformed those using local features (F₁ MW = 0.34) and a chance-level model (F₁ MW = 0.30). We discuss our results in the context of MOOC development as well as integrating MW detection into attention-aware MOOCs.

Original language	English (US)
Pages	226-231
Number of pages	6
State	Published - 2017
Externally published	Yes
Event	10th International Conference on Educational Data Mining, EDM 2017 - Wuhan, China Duration: Jun 25 2017 → Jun 28 2017

Conference

Conference	10th International Conference on Educational Data Mining, EDM 2017
Country/Territory	China
City	Wuhan
Period	6/25/17 → 6/28/17

Bibliographical note

Publisher Copyright:
© 2017 International Educational Data Mining Society. All rights reserved.

Keywords

Attention-aware learning
Eye-gaze
Intelligent tutoring systems
Lecture viewing
Massive open online courses
Mind wandering

Find It

Find It at U of M Libraries

Cite this

@conference{5c7ba1e3e93a4f39bc10614537a8f146,

title = "Gaze-based detection of mind wandering during lecture viewing",

abstract = "We investigate the use of consumer-grade eye tracking to automatically detect Mind Wandering (MW) during learning from a recorded lecture, a key component of many Massive Open Online Courses (MOOCs). We considered two feature sets: stimulus-independent global gaze features (e.g., number of fixations, fixation duration), and stimulus-dependent local features. We trained Bayesian networks using the aforementioned features and students‟ self-reports of MW and validated them in a manner that generalized to new students. Our results indicated that models built with global features (F1 MW = 0.47) outperformed those using local features (F1 MW = 0.34) and a chance-level model (F1 MW = 0.30). We discuss our results in the context of MOOC development as well as integrating MW detection into attention-aware MOOCs.",

keywords = "Attention-aware learning, Eye-gaze, Intelligent tutoring systems, Lecture viewing, Massive open online courses, Mind wandering",

author = "Stephen Hutt and Jessica Hardey and Robert Bixler and Angela Stewart and Evan Risko and D{\textquoteright}Mello, \{Sidney K.\}",

note = "Publisher Copyright: {\textcopyright} 2017 International Educational Data Mining Society. All rights reserved.; 10th International Conference on Educational Data Mining, EDM 2017 ; Conference date: 25-06-2017 Through 28-06-2017",

year = "2017",

language = "English (US)",

pages = "226--231",

}

TY - CONF

T1 - Gaze-based detection of mind wandering during lecture viewing

AU - Hutt, Stephen

AU - Hardey, Jessica

AU - Bixler, Robert

AU - Stewart, Angela

AU - Risko, Evan

AU - D’Mello, Sidney K.

PY - 2017

Y1 - 2017

N2 - We investigate the use of consumer-grade eye tracking to automatically detect Mind Wandering (MW) during learning from a recorded lecture, a key component of many Massive Open Online Courses (MOOCs). We considered two feature sets: stimulus-independent global gaze features (e.g., number of fixations, fixation duration), and stimulus-dependent local features. We trained Bayesian networks using the aforementioned features and students‟ self-reports of MW and validated them in a manner that generalized to new students. Our results indicated that models built with global features (F1 MW = 0.47) outperformed those using local features (F1 MW = 0.34) and a chance-level model (F1 MW = 0.30). We discuss our results in the context of MOOC development as well as integrating MW detection into attention-aware MOOCs.

AB - We investigate the use of consumer-grade eye tracking to automatically detect Mind Wandering (MW) during learning from a recorded lecture, a key component of many Massive Open Online Courses (MOOCs). We considered two feature sets: stimulus-independent global gaze features (e.g., number of fixations, fixation duration), and stimulus-dependent local features. We trained Bayesian networks using the aforementioned features and students‟ self-reports of MW and validated them in a manner that generalized to new students. Our results indicated that models built with global features (F1 MW = 0.47) outperformed those using local features (F1 MW = 0.34) and a chance-level model (F1 MW = 0.30). We discuss our results in the context of MOOC development as well as integrating MW detection into attention-aware MOOCs.

KW - Attention-aware learning

KW - Eye-gaze

KW - Intelligent tutoring systems

KW - Lecture viewing

KW - Massive open online courses

KW - Mind wandering

UR - https://www.scopus.com/pages/publications/85051749397

UR - https://www.scopus.com/inward/citedby.url?scp=85051749397&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85051749397

SP - 226

EP - 231

T2 - 10th International Conference on Educational Data Mining, EDM 2017

Y2 - 25 June 2017 through 28 June 2017

ER -

Gaze-based detection of mind wandering during lecture viewing

Abstract

Conference

Bibliographical note

Keywords

Find It

Other files and links

Fingerprint

Cite this