Explore the vast range of titles available.

Previous studies have shown that encouraging students to use self-explanation strategies has proven effective in text-focused learning contexts. However, no study to date has focused on how students' strategy preference moderates the effect of self-explanation strategies on learning from video lectures. The current study investigated how students' self-explanation strategy preference impacts their learning from video lectures by using prompts with a between-within-subjects design strategy preference (i.e., strategy preference vs. no strategy preference; between subject) and with prompt type (i.e., focused vs. open; within-subject), assessing learning performance, cognitive load, attention allocation, quantity and quality of explanation, and behavioral patterns. Study results showed that, compared to students using open prompts and with no self-explanation preference, providing focused prompts improved their learning performance and explanation quality, lowering their cognitive load and enabling them to search for information more accurately. Meanwhile, for students with a self-explanation preference, the two types of prompts used in this study had a similar positive impact on their learning performance and their quality of explanation.

With the increasing bandwidth, videos have been gradually used as submissions for online peer assessment activities. However, their transient nature imposes a high cognitive load on students, particularly low-ability students. Therefore, reviewers' ability is a key factor that may affect the reviewing process and performance in an online video peer assessment activity. This study examined how reviewers' ability affected the comments they provided and their reviewing behaviors and performance. Thirty-eight first-year undergraduate students participated in an online video peer assessment activity for 3 weeks. This study analyzed data collected from the teacher's and peer reviewers' ratings, comments provided by peer reviewers, and system logs. Several findings are significant. First, low-ability reviewers preferred to rate higher scores than high-ability reviewers did. Second, low-ability reviewers had higher review errors than high-ability reviewers. Third, high-ability reviewers provided more high-level comments, while low-ability reviewers provided more low-level comments. Finally, low- and high-ability reviewers showed different behavior patterns when reviewing peers' videos. In particular, low-ability reviewers invested more time and effort in understanding video content, while high-ability reviewers invested more time and effort in detecting and diagnosing problems. These findings are discussed, and several suggestions for improving the instructional and system design of online video peer assessment activities are provided.

Learning programming has become increasingly popular, with learners from diverse backgrounds and experiences requiring different support. Programming-process analysis helps to identify solver types and needs for assistance. The study examined students’ behavior patterns in programming among beginners and non-beginners to identify solver types, assess midterm exam scores’ differences, and evaluate the types’ persistence. Data from Thonny logs were collected during introductory programming exams in 2022, with sample sizes of 301 and 275. Cluster analysis revealed four solver types: many runs and errors, a large proportion of syntax errors, balance in all features, and a late start with executions. Significant score differences were found in the second midterm exam. The late start of executions characterizes one group with lower performance, and types are impersistent during the first programming course. The findings underscore the importance of teaching debugging early and the need to teach how to program using regular executions.

Wheel-spinning is unproductive persistence without the mastery of skills. Understanding wheel-spinning during the use of intelligent tutoring systems (ITSs) is crucial to help improve productivity and learning. In this study, following Beck and Gong (2013), we defined wheel-spinning students (unsuccessful students in ITSs) as those who practiced the same skill set over 10 times but failed to submit correct answers three times in a row. The t-SNE and K-means clustering algorithms were used to probe wheel-spinning learning patterns. Our results showed three types of wheel-spinning patterns when using ASSISTments, an online mathematics tutoring system. The findings indicate that a lack of motivation, math knowledge, or metacognitive ability can cause the failure to learn math with ITSs, which provides us with a deeper understanding of students' failure in ITSs and clues about how we can help these unsuccessful students in ITSs.

Massive Open Online Courses (MOOCs) have gradually become a dominant trend in education. Since 2014, the Ministry of Education in Taiwan has been promoting MOOC programs, with successful results. The ability of students to work at their own pace, however, is associated with low MOOC completion rates and has recently become a focus. The development of a mechanism to effectively improve course completion rates continues to be of great interest to both teachers and researchers. This study established a series of learning behaviors using the video clickstream records of students, through a MOOC platform, to identify seven types of cognitive participation models of learners. We subsequently built practical machine learning models by using K-nearest neighbor (KNN), support vector machines (SVM), and artificial neural network (ANN) algorithms to predict students’ learning outcomes via their learning behaviors. The ANN machine learning method had the highest prediction accuracy. Based on the prediction results, we saw a correlation between video viewing behavior and learning outcomes. This could allow teachers to help students needing extra support successfully pass the course. To further improve our method, we classified the course videos based on their content. There were three video categories: theoretical, experimental, and analytic. Different prediction models were built for each of these three video types and their combinations. We performed the accuracy verification; our experimental results showed that we could use only theoretical and experimental video data, instead of all three types of data, to generate prediction models without significant differences in prediction accuracy. In addition to data reduction in model generation, this could help teachers evaluate the effectiveness of course videos.

The aim of the study was to investigate how psychosocial problems in childhood and adolescence associate with an unhealthy health behavior pattern among adolescents in Northern Finland. The study population consisted of 4350 participants, drawn from the Northern Finland Birth Cohort 1986 Study. Health behavior patterns were assessed in adolescence and psychosocial problems in childhood and adolescence. Logistic regression analyses were performed to determine the associations. Several psychosocial problems predicted greater likelihood of engaging in unhealthy health behavior pattern. Externalizing problems in childhood predicted greater likelihood of engaging in unhealthy behavior patterns for girls. For both genders, externalizing problems and inattention in adolescence were associated with unhealthy health behavior patterns. Boys and girls with externalizing problems both in childhood and adolescence had an increased risk of unhealthy patterns. Psychosocial problems contribute to unhealthy lifestyles and should therefore be acknowledged when designing and targeting health promotion strategies aimed at adolescents.

To model students' behavior and describe their behavior characteristics accurately and comprehensively, a framework for predicting students' learning performance based on behavioral model is proposed, which extracts features from multiple perspectives to describe behaviors more comprehensively, including statistical features and association features. In addition, a multi-task model is designed for fine-grained prediction of students' learning performance in the curriculum. A framework for predicting mastery based on online learning behavior is also put forward. Additional context information is added to the collaborative filtering algorithm, including student-knowledge-point mastery and class-knowledge-point, and students' mastery is predicted according to the learning path excavated. Considering the time-varying of mastery, the approximate curve of students' mastery of knowledge points is fitted according to the Ebinhaus forgetting curve. The experiments show that the proposed framework has a high recall rate for the prediction of learning performance, and also shows a certain practicability for early warning. Further, based on the model, the correlation between student behavior patterns and learning performance is discussed. The addition of additional information has improved the prediction efficiency, especially the operational efficiency. At the same time, the proposed framework can not only dynamically assess students' master of knowledge, but also facilitate the system to review feedback or adjust the learning order, and provide personalized learning services.

Educational data mining and learning analytics have become a very important topic in the field of education technology. Many frameworks have been proposed for learning analytics which make it possible to identify learning behavior patterns or strategies. However, it is difficult to understand the reason why behavior patterns occur and why certain strategies are used. In other words, all of the existing frameworks lack an important step, that is, result confirmation. In this paper, we propose a Result Confirmation-based Learning Behavior Analysis (ReCoLBA) framework, which adds a result confirmation step for exploring the hidden reasons underlying the learning patterns and strategies. Using this ReCoLBA framework, a case study was conducted which analyzed e-book reading data. In the case study, we found that the students had a tendency to delete markers after adding them. Through an investigation, we found that the students did this because they could not grasp the learning emphasis. To apply this finding, we proposed a learning strategy whereby the teacher highlights the learning emphasis before students read the learning materials. An experiment was conducted to examine the effectiveness of this strategy, and we found that it could indeed help students achieve better results, reduce repetitive behaviors and save time. The framework was therefore shown to be effective.

The objective of this experiment was to evaluate the effects of corn processing and protein level on the feeding, lying, and post milking standing (PMS) behavior in high producing cows. Eight Holstein cows were randomly assigned to diets containing either finely ground (FGC) or steam flaked (SFC) corn based on either low (LP) or high (HP) protein content. Cows receiving LP had lower milk yield than cows receiving HP with similar DMI. Moreover, FGC-fed cows had higher DMI than SFC-fed cows with similar milk yields. Eating and rumination time tended to be lower and chewing time was lower in HP-fed cows than LP-fed cows. Cows fed SFC tended to have higher laying rumination interval and lower lying rumination bouts than cows fed FGC. Total and average PMS were lower in cows fed HP than LP. Cows fed LP had higher chewing activity in the daytime than cows fed HP. Our results suggested that the protein level and corn processing affect the standing and lying behavior of high producing dairy cows, although, this effect is marginal. Results also indicated that probably any change in the diet that increases the rumination and eating times could also improve the PMSThe objective of this experiment was to evaluate the effects of corn processing and protein level on the feeding, lying, and post milking standing (PMS) behavior in high producing cows. Eight Holstein cows were randomly assigned to diets containing either finely ground (FGC) or steam flaked (SFC) corn based on either low (LP) or high (HP) protein content. Cows receiving LP had lower milk yield than cows receiving HP with similar DMI. Moreover, FGC-fed cows had higher DMI than SFC-fed cows with similar milk yields. Eating and rumination time tended to be lower and chewing time was lower in HP-fed cows than LP-fed cows. Cows fed SFC tended to have higher laying rumination interval and lower lying rumination bouts than cows fed FGC. Total and average PMS were lower in cows fed HP than LP. Cows fed LP had higher chewing activity in the daytime than cows fed HP. Our results suggested that the protein level and corn processing affect the standing and lying behavior of high producing dairy cows, although, this effect is marginal. Results also indicated that probably any change in the diet that increases the rumination and eating times could also improve the PMS

The learning style of a learner is an important parameter in his learning process. Therefore, learning styles should be considered in the design, development, and implementation of e-learning environments to increase learners’ performance. Thus, it is important to be able to automatically determine learning styles of learners in an e-learning environment. In this paper, we propose a sequential pattern mining approach to extract frequent sequential behavior patterns, which can separate learners with different learning styles. In this research, in order to recognize learners’ learning styles, system uses the Myers-Briggs Type Indicator’s (MBTI). The approach has been implemented and tested in an e-learning environment and the results show that learning styles of learners can be predicted with high accuracy. We show that learners with similar learning styles have similar sequential behavior patterns in interaction with an e-learning environment. A lot of frequent sequential behavior patterns were extracted which some of them have a meaningful relation with MBTI dimensions.