Detection of Student Engagement in e-Learning Systems Based on Semantic Analysis and Machine Learning

Identifying pedagogical intervention in MOOCs learning processes: a conversational agent proposal

“…Otherwise, research systematically explores technology-enhanced learning solutions to increase students' engagement and avoid school dropout. Considering the research areas on which this paper draws, we selected articles addressing the automatic categorization of student forum posts [Capuano and Caballé 2019, Agrawal et al 2015, Bóbó et al 2019, autonomous agents applied to pedagogical interventions [Toti et al 2020, Demetriadis et al 2018, and agents associated with recommendation systems [Harrathi et al 2017, Brigui-Chtioui et al 2017, Bóbó et al 2019].…”

“…The work developed in [Toti et al 2020] aims to detect and analyze the involvement of course participants in the context of online education, obtaining relevant information related to aspects that indicate student engagement, such as sentiment, urgency, confusion, and the probability of student drop-out. Students' posts and comments are considered to accomplish this task, using classification algorithms based on machine learning.…”

“…As in [Toti et al 2020, Bóbó et al 2019 works, our research explores technologies such as knowledge representation, artificial intelligence, computational linguistic, among others, to increase students' engagement and avoid school dropout. As [Demetriadis et al 2018], we also define conversational agents as software programs engaging learners in a conversation through natural language, hoping to impact group learning outcomes.…”

“…With that, we believe that assisted education may contribute to the automatization process of students tutoring. In this context, the greatest challenge is not only sending students recommendations and academic topics but also predicting learning issues and sending notifications [Toti et al 2020].…”

Wearables for Engagement Detection in Learning Environments: A Review

“…Other works centered around student emotional state detection analyze and process signals from Electroencephalogram (EEG), Electromyogram (EMG), Electrocardiography (ECG), Electrodermal activity (EDA), heart rate variability, skin temperature, blood volume pulse, respiration, or Electrodermography (EDG)/galvanic skin response (GSR) [ 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 ]. Researchers [ 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 ] report the use of deep learning and machine learning (ML) techniques for emotion classification. Finally, other techniques rely on emotion recognition via computer vision [ 22 , 41 , 48 , 49 , 50 ], linguistic semantic approaches [ 51 ], and biological features [ 52 ].…”