Thousands of learners are taking massive Open Online courses (MOOCs) in search of self-improvement opportunities. However, the learning process often involves a struggle with confusion, which can adversely affect the course participation experience, leading to dropout halfway through. At the same time, it is impossible for the instructors to recognize and respond “confusion” posts accurately and timely, due to the large volume of registrants. This study aims to develop a robust and interpretable NLP model to identify "confusion" posts that require instructors' immediate attention and to dig deeper into the origin causes of confusion posts according to the type of confusion. We find that posts identified as “confusion” are manifestations of different learner affects pertaining to their informational needs–primarily related to cognitive and social processes. Furthermore, we evaluated the model with a 13% improvement in F1 value compared to previous studies and successfully applied it across unseen domains.

Autonomy support is an interpersonal tone of support and understanding. Teachers' instructional behaviors with autonomy support facilitate students' inner motivational resources and enhance their engagement in learning activities. Identifying these behaviors is vital in terms of teaching effects on students' academic performance and behaviors. However, existing methods heavily rely on psychological questionnaires or observers, which are time consuming and difficult to apply in large scale teaching scenarios. In this work, we combine deep neural networks with psychology to achieve automatically identifying the behaviors. To this end, we create the first Chinese instructional behavior dataset for deep learning, and then construct a BERT-based network for modeling psychological features and identifying behaviors. Since frequencies of different behaviors are highly imbalanced, we further design a novel loss function to adaptively optimize training weights for each behavior. Extensive experiments verify the effectiveness of our method and explain how the behaviors are identified.

Learning motivation plays a crucial role in student’s daily study life since it greatly affects academic performance and engagement. Perceived relatedness, based on self-determined theory, is an important predictor of learning motivation. Today, assessment for both of them still relies on subjective evaluations and self-reports, which is time-consuming and onerous. Hence, we propose a novel approach blended with mobile sensing by simultaneously collecting psychological measurements and objective mobile sensing data from N=58 undergraduates to explore new methods of assessing learning motivation and perceived relatedness. We identify a variety of social behavioral patterns from mobile sensing data, and investigate associations between psychological measures and these patterns. Our study helps enlighten what the new forms of assessing learning motivation and perceived relatedness in education could be, and paves the way for personalizing intervention in future research.

Self-regulated learning influences students' learning behaviors and is a significant academic performance factor. Resource management strategy based on self-regulated learning theory is an important indicator for students to demonstrate Self-regulated learning. However, current self-regulated learning and resource management strategy assessments still rely on subjective evaluations and self-assessments, which are time-consuming and laborious. Therefore, we propose a novel method combined with mobile sensing by collecting detailed learning strategy subscales and objective mobile sensing data from 211 college students to explore a new approach to assessing self-regulated learning and resource management strategy. We are the first to propose a mobile sensing approach for assessing self-regulated learning and learning strategies. The method studies the associations between the learning strategy subscales and these daily behavior patterns and presents features for behavior patterns from mobile sensing data. Our study helps to reveal new forms of assessing self-regulated learning and opens the way for personalized interventions.

Assessing the levels of motivation in the learning process are pivotal in the daily life of college students, for the learning motivation profoundly impacts their overall academic performance. Yet, the prevailing methods to measure learning motivation levels still predominantly depend on expert evaluation and self-report, advancements in passive smartphone sensing have not been fully utilized in measuring motivation levels in learning process. In this study, we investigate and analyze behaviors and behavioral changes associated with their levels of learning motivation of N=118 undergraduate college students integrating passive smartphone sensing with self-report survey. We collect a dataset regarding the students' daily behaviors and self-report responses using a mobile application and questionnaire. Subsequently, we identify a variety of behaviors based on behavioral features captured from passive sensing data, followed by an exploration of the correlations between levels of learning motivation and the identified behaviors. Moreover, we analyze differences in behavioral changes among groups characterized by varying levels of learning motivation. Our study contributes to enhancing psychological assessment approaches by introducing a novel integrated method for more quantified and multidimensional measurement of learning motivation, providing valuable perspectives for assessing and intervening learning motivation in future research endeavors.