Personality is considered as the internal factor that defines a person’s behavior. Therefore, providing adaptive features and personalized support in online learning by considering learners’ personalities can improve their learning experiences and outcomes. In this context, several research studies have investigated the impact of personality differences in online learning. However, little is known about how personality differences affect learners’ behavior while learning. To fill this gap, this study applies a lag sequential analysis (LSA) approach to understand learners’ navigational behavior patterns in an online three-months course of 65 learners based on their personalities. In this context, the five factor model (FFM) model was used to identify learners’ personalities. The findings revealed that learners with different personalities use different strategies to learn and navigate within the course. For instance, learners high in extraversion tend to be extrinsically motivated. They therefore significantly navigated between viewing the course module and their personal achievements. The findings of this study can contribute to the adaptive learning field by providing insights about which personalization features can help learners with different personalities. The findings can also contribute to the field of automatic modeling of personality by providing information about differences in navigational behavior based on learners’ personalities.

School engagement has assumed an important place in current developmental psychology and educational research due to its potential to address students’ low achievement, high dropout rates, and misbehavior. Although much has been written about the antecedents and outcomes of student engagement, literature on how students’ level of engagement differs in response to different teaching styles was missing on a large scale. Understanding the patterns and risks linked with student engagement provides opportunities for targeted intervention. This study explored primary school students’ engagement and burnout profiles and how different profiles interacted with perceived classroom teaching styles (i.e., autonomy-supportive & autonomy suppressive). Latent profile analysis resulted in four student engagement subgroups: moderately engaged, engaged, moderately burned out, and burned out. Students clustered into engagement groups were likely to report higher autonomy support from teachers. In contrast, burned-out groups were more likely to rate teachers’ teaching styles as suppressive (i.e., autonomy suppressive). Collectively, the study indicated that autonomy-supportive teaching behaviors are pivotal in understanding student engagement and school burnout. Thus, tailored teacher-focused intervention programs that enhance teachers’ awareness of autonomy-supportive teaching is important. The significance of the findings with the demand-resource model (in the education context) was discussed.

The emotional variation can reflect shifts in mental and emotional states. It plays an important role in the field of intelligent education. Emotion recognition can be used as cues for teachers to evaluate the learning state, analyze learning motivation, interest, and efficiency. Although research on emotion recognition has been ongoing for a long time, there has been a restricted emphasis on analyzing the credibility of the recognized emotions. In this paper, the origin, development, and application of emotion recognition were introduced. Then, multiple signals captured from video that could reflect emotion changes were described in detail and their advantages and disadvantages were discussed. Moreover, a comprehensive summary of the pertinent applications and research endeavors of emotion recognition technology in the field of education was provided. Last, the trend of emotion recognition in the field of education was given.