Emotion and Learning

Version	Summary	Created by	Modification	Content Size	Created at	Operation
1		Mohammad Nehal Hasnine	--	1113	2023-05-18 02:28:12	\|
2	format correct	Conner Chen	Meta information modification	1113	2023-05-19 02:34:20	\|

This entry is adapted from the peer-reviewed paper 10.3390/s23094243

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.

AI in education affective states detection dashboard

1. Introduction

With the rapid growth of learning technologies, online learning, or virtual education, has become popular. It opened new doors to learners with physical challenges or those who were busy caring for a family that prevented them from learning at school ^[1]. E-learning has become a frontline approach to supporting education during a crisis such as the COVID–19 pandemic. It is because online learning systems are convenient for students, cost-efficient, flexible ways of learning, scalable, allow for better repetition, and have a higher degree of freedom ^[2]. With a compelling e-learning system and a highly motivated student, one can achieve great success in a short period of time ^[2]. On the contrary, online learning environments have several drawbacks, including the fact that they lack the face-to-face interactions that students would receive in traditional classroom settings, and real-time interaction can be frustrating. In addition, it is hard for the lecturer to understand the students’ affective states, such as whether they are feeling confused, motivated to learn, happy with the lesson, taking the lecture with enthusiasm, engaged with the learning materials, or how well the lecture is delivered.

In online learning, the problem of student disengagement and poor concentration is gaining attention. In the classroom, students’ engagements consist of their behavioral, cognitive, and emotional elements ^[3]. For example, student academic effort, persistence, attention, concentration, and a lack of conduct problems are associated with behavioral engagement; thoughtfulness and willingness to make the efforts necessary to understand complex ideas and master difficult skills are related to cognitive engagement; and the presence of interest, enthusiasm, the absence of anger, anxiety, and boredom are connected with emotional engagement ^[3]. It is also evident that students’ engagement is directly proportional to their achievement ^[4]. Due to poor concentration and a low level of engagement during the lecture, many students fail to achieve the learning goal. This also raises the concern of not receiving a high-quality education. This is because it is challenging for an instructor to keep a close eye on the entire class and regulate teaching. Therefore, for an educational system, it is essential to monitor students’ engagement and concentration frequently, as learning occurs when the students are meaningfully involved in the learning environment.

2. Emotion and Learning: Why Emotions Are Important in Education?

Kop et al. ^[5] stated that emotions are conceptual entities that arise from brain-to-body-to-environment interactions. Emotions are inherently linked to and influence cognitive skills such as attention, memory, executive function, decision-making, critical thinking, problem-solving, and regulation, all of which play a crucial role in learning ^[6]. Generally speaking, we have positive emotions and negative emotions that play powerful roles in learning. Positive emotions such as curiosity, passion, interest, wonder, creativity, and joy make our learning experience more desirable and aid in enhancing our focus and attention. These types of emotions enable learners to broaden their perspective and respond effectively to critical situations. On the other hand, negative emotions including sadness, disinterest, disengagement, anxiety, stress, worry, and fear can slow learning processes. These types of emotions negatively impact a learner’s learning experience. While positive emotions help learners stay engaged for longer, negative emotions could be disturbing. Yet negative emotions are not always bad for learning. For example, negative emotions such as confusion can increase students’ interest levels. Additionally, negative emotions are important for learning complex concepts. Therefore, emotions, either positive or negative, are important factors that influence our learning process. Emotions influence our memory, reasoning capability, perception, and logical thinking, and therefore, in education, emotion is essential as it is highly associated with students’ attention ^[7].

3. Theories Associated with Emotion and Learning

In order to find the relation between emotion and learning, psychologists and neurologists have evaluated many theories. For example, one study ^[8] evaluated a model in terms of how emotions influence students’ learning and achievement. According to the findings of this study, the influence of emotions can be mediated by several mechanisms with cumulative or contradictory effects on predicting overall effects on performance. The second example is Pekrun’s control-value theory of emotions ^[9]. The findings of this study indicated that the influence of emotions can be mediated by a few mechanisms with cumulative or contradictory effects for predicting overall effects on performance.

In addition, affective models are proposed that aim to establish a link between academic emotions and engagement levels. For example, an affective model to identify the level of student engagement depending on their emotions is proposed by Khawlah Altuwairqi ^[10]. This study conducted a series of experiments to find the relation between engagement levels and their emotions. A study conducted by CR Seal ^[11] proposed social and emotional development (SED). SED is the integration of theory, emotional intelligence, and competence development applied to educational practice. This study suggests that sustainable enhancement of personal capacity to utilize emotional information, behaviors, and traits could facilitate social outcomes.

Following these theories, in academics, understanding students’ emotional states is crucial to understanding the learning process. However, despite the importance of recognizing learners’ emotions in e-learning platforms, only a few platforms that recognize learners’ emotions could be found. Hence, new frameworks need to be developed to uncover the unsolved learning problems.

4. Measurements of Emotion in E-Learing

Online learning has become the core of research and practices in learning analytics, educational data mining, artificial intelligence in education, intelligent tutoring systems, and educational recommendation systems. The research and practices of learning analytics (LA) are defined as “the measurement, collection, analysis, and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and the environments in which it occurs” by the Society for Learning Analytics Research (SOLAR). Multimodal learning analytics (MMLA), a subbranch of learning analytics, is focusing research on how critical aspects of the learning process could be revealed using multimodal data such as facial, emotional, gesture, and cognitive data ^[12].

With the help of LA and MMLA, many complex issues, including disengagement in online learning, are explored. Disengagement is regarded as one of the main challenges in online learning. Due to disengagement and poor concentration, many learners fail to achieve their learning goals. To understand more about why disengagement and poor concentration happen, LA and MMLA approaches measure the student’s work context, actions, utterances, facial expressions, body language, and interactions with teachers or fellow students. As of now, many machine learning models, learning analytics systems, and learning analytics dashboards are being developed to regulate learning and teaching. However, measuring emotions and affective states during the class has been a challenge for teachers without LA or MMLA technologies.

References

Wang, Y.; Liu, Q.; Stein, D.; Xia, Q. Measuring students affective states through online learning logs—an application of learning analytics. Int. J. Inf. Educ. Technol. 2019, 9, 356–361.
Guragain, N. E-learning benefits and applications. Psychol. 2016. Available online: https://urn.fi/URN:NBN:fi:amk-201602122192 (accessed on 19 April 2022).
Silvola, A.; Näykki, P.; Kaveri, A.; Muukkonen, H. Expectations for supporting student engagement with learning analytics: An academic path perspective. Comput. Educ. 2021, 168, 104192.
Skinner, E.A.; Zimmer-Gembeck, M.J.; Connell, J.P.; Eccles, J.S.; Wellborn, J.G. Individual Differences and the Development of Perceived Control. Monogr. Soc. Res. Child Dev. 1998, 63, i-231.
Kop, R.; Fournier, H.; Durand, G. A Critical Perspective on Learning Analytics and Educational Data Mining; Society for Learning Analytics Research Publishing: Canada, 2017.
Immordino-Yang, M.H.; Damasio, A. We Feel, Therefore We Learn: The Relevance of Affective and Social Neuroscience to Education. Mind Brain Educ. 2007, 1, 3–10.
Hasnine, M.N.; Bui, H.T.; Tran, T.T.T.; Nguyen, H.T.; Akçapınar, G.; Ueda, H. Students’ emotion extraction and visualization for engagement detection in online learning. Procedia Comput. Sci. 2021, 192, 3423–3431.
Pekrun, R. The Impact of Emotions on Learning and Achievement: Towards a Theory of Cognitive/Motivational Mediators. Appl. Psychol. 1992, 41, 359–376.
Ranelluci, J.; Hall, N.C.; Goetz, T. Achievement goals, emotions, learning, and performance: A process model. Motiv. Sci. 2015, 1, 98–120.
Altuwairqi, K.; Jarraya, S.; Allinjawi, A.; Hammami, M. A new emotion–based affective model to detect student’s engagement. J. King Saud Univ. Comput. Inf. Sci. 2018, 33, 99–109.
Seal, C.R.; Naumann, S.E.; Scott, A.N.; Royce-Davis, J. Social emotional development: A new model of student learning in higher education. Res. High. Educ. J. 2011, 10, 114–115.
SOLAR. What Is Learning Analytics. Available online: https://www.solaresearch.org/about/what-is-learning-analytics/ (accessed on 19 April 2022).

© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.

Upload a video for this entry

Information

Subjects: Education & Educational Research

Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to https://encyclopedia.pub/register :

Mohammad Nehal Hasnine

Ho Tan Nguyen

Thuy Thi Thu Tran

Huyen T. T. Bui

Gökhan Akçapınar

Hiroshi Ueda

View Times: 236

Update Date: 19 May 2023

Table of Contents

Video Upload Options

Confirm