A Real-Time Learning Analytics Dashboard for Automatic Detection of Online Learners’ Affective States

Abstract

Students’ affective states describe their engagement, concentration, attitude, motivation, happiness, sadness, frustration, off-task behavior, and confusion level in learning. In online learning, students’ affective states are determinative of the learning quality. However, measuring various affective states and what influences them is exceedingly challenging for the lecturer without having real interaction with the students. Existing studies primarily use self-reported data to understand students’ affective states, while this paper presents a novel learning analytics system called MOEMO (Motion and Emotion) that could measure online learners’ affective states of engagement and concentration using emotion data. Therefore, the novelty of this research is to visualize online learners’ affective states on lecturers’ screens in real-time using an automated emotion detection process. In real-time and offline, the system extracts emotion data by analyzing facial features from the lecture videos captured by the typical built-in web camera of a laptop computer. The system determines online learners’ five types of engagement (“strong engagement”, “high engagement”, “medium engagement”, “low engagement”, and “disengagement”) and two types of concentration levels (“focused” and “distracted”). Furthermore, the dashboard is designed to provide insight into students’ emotional states, the clusters of engaged and disengaged students’, assistance with intervention, create an after-class summary report, and configure the automation parameters to adapt to the study environment.

The impacts of learning motivation, emotional engagement and psychological capital on academic performance in a blended learning university course

“…These findings reveal a noteworthy positive correlation between intrinsic learning motivation and learning outcomes, aligning with prior research (Fredricks and McColskey, 2012;Lazowski and Hulleman, 2016). Similarly, the observed positive impact of emotional engagement on college students' learning outcomes is consistent with earlier conclusions from research (Raver, 2002;Bierman et al, 2008;Liew et al, 2008;Engels et al, 2021;Hasnine et al, 2023). In the blended learning environment, the psychological capital of college students has a significant impact on the learning effect of college students, which is in alignment with previous research conclusions (Jafri, 2013).…”

“…While emotions can be divided into both positive and negative emotions, emotional engagement can also be divided into emotional engagement and disaffection (Skinner et al, 2008;Dixson, 2010;Guthrie et al, 2012). Although the feasibility of using computer vision techniques to measure the emotional engagement by analyzing facial features is being discussed recently (Ashwin and Guddeti, 2020;Mehta et al, 2022;Hasnine et al, 2023), but it is a challenging task, so self-report is relatively mature measures technology (Fredricks and McColskey, 2012).…”

“…Studies have shown that emotional engagement correlated to educational outcomes, or positively related with academic performance and learning satisfaction (Connell et al, 1994;Fredricks et al, 2004;Halverson and Graham, 2019), there are a few studies on the emotional engagement's impact on learning achievement, and some of them find that emotional engagement plays a vital role in predicting academic achievement (Raver, 2002;Bierman et al, 2008;Liew et al, 2008;Engels et al, 2021;Hasnine et al, 2023). Emotional engagement influences academic performance through behavioral shaping as a mediator (Geertshuis, 2019), or effect on learning achievement by the interaction with cognitive engagement (Liu et al, 2022).…”

“…From the perspective of social psychology, learning motivations, emotional engagement, and psychological capital originated from positive psychology, usually considered to impact academic performance positively. Learning motivation, especially intrinsic motivation, is positively correlated with academic outcomes measured by scores or grades (Schunk et al, Liu et al 10.3389/fpsyg.2024.1357936 Frontiers in Psychology 02 frontiersin.org 2008; Lazowski and Hulleman, 2016;Alkış and Taşkaya Temizel, 2018); Emotional engagement is considered to directly affect learning outcomes or indirectly affect by shaping behavioral and cognitive engagement (Raver, 2002;Bierman et al, 2008;Liew et al, 2008;Engels et al, 2021;Hasnine et al, 2023). Psychological capital, as an individual's positive psychological state, leads to positive organizational behavior, and has a positive relationship with academic performance (Jafri, 2013;Khajavy et al, 2019;Carmona-Halty et al, 2021;King and Caleon, 2021;Slåtten et al, 2023).…”

“…In addition, after the sudden outbreak of COVID-19 in 2020, blended learning was accepted more widely, which may prepare students better for future work (Ravat et al, 2021). But the study of blended learning's effect on the academic performance is scarce, while some researches show that blended learning has a more positive impact on academic performance than face-to-face and online learning, because learners hold significantly more positive attitudes toward blended learning (Cirak et al, 2018;Yu et al, 2022), these are determinative of the learning quality (Hasnine et al, 2023), the academic performance is influenced by emotional engagement (Gao et al, 2020). Regardless of gender, academic performance is mainly predicted by satisfaction levels, and the effects of perceived benefit and satisfaction level on academic performance are different between undergraduate students and postgraduate students in the blended context (Kobicheva et al, 2022).…”