Emorec: a new approach for detecting and improving the emotional state of learners in an e-learning environment

ABSTRACT

In e-learning environments, several activities are offered to learners, including learning and assessment activities. During these activities, the learner may encounter difficulties, such as blocking situations or lack of motivation. This paper presents a new approach to detect these difficulties based on the learner’s emotional states and recommends solutions to motivate him/her. Our first contribution is recognizing the learner’s emotional state using two modules: facial expression recognition using a Gabor filter bank and vocal emotion recognition using MFCC features. Concerning the recommendations in these cases of difficulties, a psychological and/or pedagogical recommendation generator is proposed in this study; it is our second contribution. Three experiments to validate our approach were conducted on two groups of students: test and control. The results indicate that the proposed method improves the learner’s emotional state, motivation, and engagement time in the system.

KEYWORDS:

• E-learning
• learner
• emotions
• facial expressions
• speech emotions
• recommendations/solutions

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Med Nadjib Kouahla

Med Nadjib Kouahla received the engineer degree in computer science from Guelma University in 2006 and the Master degree in instrumentation and image computing from Burgundy university, Dijon, France in June 2007. He received his PhD in Computer Science with distinction in 2010 from the University of Franche-Comte, Besancon, France. He is currently associate professor of department of computer science and a member of LabSTIC laboratory, Guelma University, Algeria. His research interests include image processing, machine learning, and pattern recognition.

Adil Boughida

Adil Boughida is a five-year Ph.D. student in computer science at LabSTIC laboratory, university of Guelma, Algeria studying under Professor Kouahla Med. Nadjib. He is preparing his thesis on emotion-based adaptation in collaborative social learning environments. His research focuses on emotion and its impact on the learner’s learning process. He also works on Machine Learning and image processing in the same context of emotion, where he published an article entitled “A novel approach for facial expression recognition based on Gabor filters and genetic algorithm” in Evolving systems journal.

Imed Chebata

Imed Chebata is a former master’s student at the University of Guelma, Algeria. He prepared his master’s thesis on difficulty detection based on the emotional state of a learner in a computer environment for human learning, studying under Professor Kouahla Med. Nadjib.

Zohra Mehenaoui

Zohra Mehenaoui is currently working as a senior lecturer of Computing at the Computer Science Department of Guelma University, Algeria and she is a researcher at the LabSTIC laboratory. She holds an MS in Computer Science from Annaba University and Phd in 2018 at Annaba University. Her research fields include e-learning, collaborative learning, recommender systems, social networks and learning analytics.

Yacine Lafifi

Yacine Lafifi is currently working as a Full Professor at the Computer Science Department of Guelma University, Algeria. Also, he is a senior researcher at LabSTIC laboratory (Guelma University, Algeria). He works in e-learning research field since 1997. He received his PhD in computer science from the University of Annaba (Algeria) in 2007. He has several published papers in conferences and journals. Furthermore, he is an editorial board member of many international journals. Currently, he works on e-tutoring environments, e-Learning, CSCL, recommender systems, MOOC and human tutoring systems.