Investigating the Utility of Eye-Tracking Information on Affect and Reasoning for User Modeling

Müldner, Kasia; Christopherson, Robert; Atkinson, Robert K.; Burleson, Winslow

doi:10.1007/978-3-642-02247-0_15

Cited by 23 publications

(22 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reuderink et al [22] found that EEG measures are correlated with the valence and arousal dimension when they studied subjects playing computer games and induced emotions through the use of non-responsive controllers. Muldner et al [31] found that the pupil size changes with negative and positive affect when they studied subjects solving exercises in physics and varied the affect. Finally, Drachen et al [32] used a combination of biometric measures while participants played a computer game and found that heart rate and EDA are correlated with self-reported negative/positive affect.…”

Section: A Emotions and Biometricsmentioning

confidence: 99%

See 1 more Smart Citation

Stuck and Frustrated or in Flow and Happy: Sensing Developers' Emotions and Progress

Müller

Fritz

2015

2015 IEEE/ACM 37th IEEE International Conference on Software Engineering

125

136

View full text Add to dashboard Cite

Software developers working on change tasks commonly experience a broad range of emotions, ranging from happiness all the way to frustration and anger. Research, primarily in psychology, has shown that for certain kinds of tasks, emotions correlate with progress and that biometric measures, such as electro-dermal activity and electroencephalography data, might be used to distinguish between emotions. In our research, we are building on this work and investigate developers' emotions, progress and the use of biometric measures to classify them in the context of software change tasks. We conducted a lab study with 17 participants working on two change tasks each. Participants were wearing three biometric sensors and had to periodically assess their emotions and progress. The results show that the wide range of emotions experienced by developers is correlated with their progress on the change tasks. Our analysis also shows that we can build a classifier to distinguish between positive and negative emotions in 71.36% and between low and high progress in 67.70% of all cases. These results open up opportunities for improving a developer's productivity. For instance, one could use such a classifier for providing recommendations at opportune moments when a developer is stuck and making no progress. Abstract-Software developers working on change tasks commonly experience a broad range of emotions, ranging from happiness all the way to frustration and anger. Research, primarily in psychology, has shown that for certain kinds of tasks, emotions correlate with progress and that biometric measures, such as electro-dermal activity and electroencephalography data, might be used to distinguish between emotions. In our research, we are building on this work and investigate developers' emotions, progress and the use of biometric measures to classify them in the context of software change tasks. We conducted a lab study with 17 participants working on two change tasks each. Participants were wearing three biometric sensors and had to periodically assess their emotions and progress. The results show that the wide range of emotions experienced by developers is correlated with their perceived progress on the change tasks. Our analysis also shows that we can build a classifier to distinguish between positive and negative emotions in 71.36% and between low and high progress in 67.70% of all cases. These results open up opportunities for improving a developer's productivity. For instance, one could use such a classifier for providing recommendations at opportune moments when a developer is stuck and making no progress.

show abstract

Section: A Emotions and Biometricsmentioning

confidence: 99%

“…Based on research that has shown that pupil size and fixation duration is affected by positive and negative emotions (e.g. [7], [31], [41]), we extracted various features for fixation duration and pupil size.…”

Section: Biometric Sensors To Determine Developers' Emotions and Pmentioning

confidence: 99%

Stuck and Frustrated or in Flow and Happy: Sensing Developers' Emotions and Progress

Müller

Fritz

2015

2015 IEEE/ACM 37th IEEE International Conference on Software Engineering

125

136

View full text Add to dashboard Cite

show abstract

“…However, most of the existing work has not been formally evaluated in terms of how adaptive edu-game components affect edu-game effectiveness. There has also been rising interest in using eye-tracking to gain insights on the cognitive and affective processes underlying a user's performance with an interactive system [e.g., 6,10,11,12]. In this paper, we extend the use of gaze information to understand if/how users attend to an educational game's adaptive interventions.…”

Section: Related Workmentioning

confidence: 99%

An Analysis of Attention to Student – Adaptive Hints in an Educational Game

Muir

Conati

2012

Intelligent Tutoring Systems

View full text Add to dashboard Cite

Abstract. We present a user study to investigate which factors affect student attention to user-adaptive hints during interaction with an educational computer game. The game is Prime Climb, an educational game designed to provide individualized support for learning number factorization skills in the form of hints based on a model of student learning. We use eye-tracking data to capture user attention patterns on the game adaptive-hints, and present results on how these patterns are impacted by factors related to existing user knowledge, hint timing, and attitude toward getting help in general. We plan to leverage these results in the future for making hint delivery adaptive to these factors. Keywords: Adaptive help, educational games, pedagogical agents, eye-tracking IntroductionThe ability of providing interventions that are adaptive to each student's specific needs is one of the distinguishing features of intelligent tutoring systems (ITS). One of the most widespread forms of adaptive interventions is to provide hints designed to gradually help students through specific educational activities when they have difficulties proceeding on their own [14]. Despite the wide adoption of adaptive hints, there is an increasing body of research showing their possible limitations, going from students gaming the system, i.e., using the hints to get quick answers from the ITS [see 7 for an overview], to help avoidance, i.e. students not using hints altogether [e.g., 8, 9]. In this paper, we are interested in investigating the latter issue. More specifically, we seek to gain a better understanding of which factors may affect a student's tendency to attend to adaptive hints that the student has not explicitly elicited. This research has three main contributions to the ITS field. First, while previous work on help avoidance focused on capturing and responding to a student's tendency to avoid requesting hints [e.g., 8, 9], here we investigate how students react when the hints are provided unsolicited. A second contribution is that we look at attention to adaptive hints during interaction with an educational computer game (edu-game), whereas most previous work on student usage (or misusage) of hints has been in the context of more structured problem solving activities. Providing adaptive hints to support learning during game play is especially challenging because it requires a trade-off between fostering learning and maintaining engagement. We see the results

show abstract

“…However, results from experiments less tightly controlled than traditional psychology ones have been mixed, with many failing to find the anticipated link between pupillary response and state of interest (e.g., [24]). In the past we investigated how only pupillary response distinguishes different types of affect [25], and did not propose a model based on our results. In contrast, here we present a model that relies on a broad range of features across both interaction and sensor data to predict "yes!"…”

Section: Related Work On Detecting Brief Affective Statesmentioning

confidence: 99%

“…moments from a previous user study we conducted [25], which involved students interacting with an intelligent tutoring system (ITS) for introductory Newtonian physics. This ITS, referred to as the Example Analogy (EA)-Coach [29], provides support to students during problem solving in the presence of worked-out examples.…”

Section: Obtaining Data On "Yes!" Momentsmentioning

confidence: 99%

“Yes!”: Using Tutor and Sensor Data to Predict Moments of Delight during Instructional Activities

Müldner

Burleson

VanLehn

2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract.A long standing challenge for intelligent tutoring system (ITS) designers and educators alike is how to encourage students to take pleasure and interest in learning activities. In this paper, we present findings from a user study involving students interacting with an ITS, focusing on when students express excitement, what we dub "yes!" moments. These findings include an empirically-based user model that relies on both interaction and physiological sensor features to predict "yes!" events; here we describe this model, its validation, and initial indicators of its importance for understanding and fostering student interest.

show abstract

Investigating the Utility of Eye-Tracking Information on Affect and Reasoning for User Modeling

Cited by 23 publications

References 17 publications

Stuck and Frustrated or in Flow and Happy: Sensing Developers' Emotions and Progress

Stuck and Frustrated or in Flow and Happy: Sensing Developers' Emotions and Progress

An Analysis of Attention to Student – Adaptive Hints in an Educational Game

“Yes!”: Using Tutor and Sensor Data to Predict Moments of Delight during Instructional Activities

Contact Info

Product

Resources

About