Teaching analytics

Abstract

ABSTRACT'Teaching analytics' is the application of learning analytics techniques to understand teaching and learning processes, and eventually enable supportive interventions. However, in the case of (often, half-improvised) teaching in face-to-face classrooms, such interventions would require first an understanding of what the teacher actually did, as the starting point for teacher reflection and inquiry. Currently, such teacher enactment characterization requires costly manual coding by researchers. This paper presents a case study exploring the potential of machine learning techniques to automatically extract teaching actions during classroom enactment, from five data sources collected using wearable sensors (eye-tracking, EEG, accelerometer, audio and video). Our results highlight the feasibility of this approach, with high levels of accuracy in determining the social plane of interaction (90%, κ=0.8). The reliable detection of concrete teaching activity (e.g., explanation vs. questioning) accurately still remains challenging (67%, κ=0.56), a fact that will prompt further research on multimodal features and models for teaching activity extraction, as well as the collection of a larger multimodal dataset to improve the accuracy and generalizability of these methods.

From signals to knowledge: A conceptual model for multimodal learning analytics

“…Facial expressions are highly investigated in learning for emotion recognition in the affective computing research and have been quite extensively used in multimodal human-computer interaction experiments (e.g., Alyuz et al, 2016;Bosch et al, 2015;Hussain et al, 2012). Eye-tracking is commonly used as an indicator for learners' attention has also been used with multimodal data sets (Edwards et al, 2017;Prieto, Sharma, Dillenbourg, & Rodríguez-Triana, 2016;Raca & Dillenbourg, 2014).…”

“…Finally, an analysis of the speech spans from paralanguage analysis like speaking time, keywords pronounced, or prosodic features like tone and pitch (e.g., Prieto et al, 2016) to actual recognition of spoken words in dialogic settings like student-teacher interactions (D'mello et al, 2015). In theory, speech recognition opens up the possibility to transcribe discourse and use natural language processing to look for deeper level semantic interpretations.…”

“…The most popular approaches to detect brain activity is the electroencephalogram (EEG), which measures the difference of potential inside of the brain. EEG was used by Prieto et al (2016) in combination with eye tracking, from a teacher analytics perspective to predict social plane of interaction and concrete teaching activity. Different techniques can be used to calculate measurements of the heart activity like the heart rate and HRV: the electrocardiogram (ECG) or the photoplethysmography.…”

Read Between the Lines

“…Sensors can monitor both the physical environment where the learner operates and the learner's behaviour including 360-degrees body movements, physiological responses such as heart rate or body temperature, or interpersonal communication, student-teacher or student-peers discussions. In related literature, sensors have been used to track different modalities such as hand gestures [24,40], gross body movements [7], eyetracking [28,29], facial expressions [3,4]. Sensors were also used to monitor physiological signals such as heart rate [1,16], galvanic skin response [14,25], brain waves [1,28].…”

What Constitutes an ‘Actionable Insight’ in Learning Analytics?

“…Already, LA seems either to occupy a place as an umbrella term or to have several siblings working in parallel. As the purpose of this selective review is only to provide an recent speciations of LA that argue for approaches that take didactical and pedagogical concerns much more into consideration, as well as obtain much more fine-grained data on learning situations, e.g., social learning analytics (Ferguson & Buckingham Shum, 2012), learning process analytics (Schneider, Class, Benetos, & Lange, 2012), multimodal learning analytics (Blikstein, 2013), teaching analytics (Prieto, Sharma, Dillenbourg, & Jesús, 2016), insight and action analytics (Miliron, Malcom, & Kil, 2014), and dispositional learning analytics (Tempelaar, Rienties, & Nguyen, 2017). However, as we shall see, many efforts still seem to retain a default view on data and on what constitutes an actionable insight that frames the deliberation of data as a rational decision-making process ultimately focused on increasing retention.…”