Design of a Personalized Recommendation System for Learning Resources based on Collaborative Filtering

At present, personalized recommendation system has become an indispensable technology in the fields of e-commerce, social network and news recommendation. However, the development of personalized recommendation system in the field of education and teaching is relatively slow with lack of corresponding application.In the era of Internet Plus, many colleges have adopted online learning platforms amidst the coronavirus (COVID-19) epidemic. Overwhelmed with online learning tasks, many college students are overload by learning resources and unable to keep orientation in learning. It is difficult for them to access interested learning resources accurately and efficiently. Therefore, the personalized recommendation of learning resources has become a research hotspot. This paper focuses on how to develop an effective personalized recommendation system for teaching resources and improve the accuracy of recommendation. Based on the data on learning behaviors of the online learning platform of our university, the authors explored the classic cold start problem of the popular collaborative filtering algorithm, and improved the algorithm based on the data features of the platform. Specifically, the data on learning behaviors were extracted and screened by knowledge graph. The screened data were combined with the collaborative filtering algorithm to recommend learning resources. Experimental results show that the improved algorithm effectively solved the loss of orientation in learning, and the similarity and accuracy of recommended learning resources surpassed 90%. Our algorithm can fully satisfy the personalized needs of students, and provide a reference solution to the personalized education service of intelligent online learning platforms.

Exploring jump back behavior patterns and reasons in e-book system

With the increasing use of digital learning materials in higher education, the accumulated operational log data provide a unique opportunity to analyzing student learning behaviors and their effects on student learning performance to understand how students learn with e-books. Among the students’ reading behaviors interacting with e-book systems, we find that jump-back is a frequent and informative behavior type. In this paper, we aim to understand the student’s intention for a jump-back using user learning log data on the e-book materials of a course in our university. We at first formally define the “jump-back” behaviors that can be detected from the click event stream of slide reading and then systematically study the behaviors from different perspectives on the e-book event stream data. Finally, by sampling 22 learning materials, we identify six reading activity patterns that can explain jump backs. Our analysis provides an approach to enriching the understanding of e-book learning behaviors and informs design implications for e-book systems.

Self-Reported Perceptions of Online Learning and Observed Online Learning Behaviors: To What Extent Are They Consistent?

This study investigates to what extent there is an association between students’ self-reported perceptions of online learning and observed online learning behaviors recorded by the learning analytic data. The participants were 319 undergraduates studying an engineering course in an Australian university. Data analyses were conducted using cluster analyses, Hidden Markov Model, one-way ANOVAs, and a cross-tabulation. The relations between students’ self-reported perceptions and their academic learning outcome show that those with positive perceptions tended to have higher scores. The relations between observational online learning behaviors and their academic learning outcome demonstrate that students with most learning sessions achieved more highly. The cross-tabulation finds a significant association between the cluster membership generated by by the self-reported perceptions and observational online learning behaviors. Amongst students who had most study sessions characterized by high percentages of reading and formative states and low percentage of summative states, the proportion of those with positive perceptions (40.2%) was significantly higher than those with negative perceptions (20.0%). Of students who had the least study sessions represented by moderate reading and summative states, and low formative states, the proportion of students with positive perceptions (3.0%) was significantly lower than the proportion of students having negative perceptions (8.7%).

Informal learning behaviors, interaction and workplace autonomy and readiness to learn

Purpose This paper aims to find a measurement model with better evidence of validity, with data extracted from the Program for the International Assessment of Adult Competencies (PIAAC). To test a parsimonious model in which dispositional and workplace context characteristics are predictors of informal learning behaviors (ILBs). Design/methodology/approach The authors performed exploratory and confirmatory factor analyses to improve the fit of the PIAAC data measurement model. Multiple linear regression was used to examine the prediction of ILBs by one dispositional variable (Readiness to Learn) and two workplace context variables (Autonomy and Interaction in the Workplace). Findings A measurement model emerged with 18 items divided into four factors. The three antecedent variables predicted ILBs. Interaction in the workplace resulted in higher scores, and workplace autonomy resulted in lower scores. Research limitations/implications The small number of items for ILBs prevented a more detailed exploration of predictors of different types of these behaviors. ILBs can be stimulated by policies that promote readiness to learn and that encourage the design of environments that require worker interactions and autonomy. Originality/value Few studies on ILBs in the workplace have investigated the prediction of dispositional and contextual antecedents based on a theoretical model. The findings herein were obtained using a diverse sample of countries, occupations and generations, allowing better generalization. The importance of interpersonal relationships in the workplace for predicting ILBs was emphasized.

Research on the differences of students’ learning styles and knowledge integration in SPOC learning: a case study of course “Basic Portuguese”

Problem and goal. With the advent of the information age, Internet-based online learning has also become one of the learning methods chosen by many learners. They can use these online learning platforms to complete knowledge construction while learning offline. Methodology. Most studies of learning behaviors focus on the discovery of the best learning model and disregard the possible impact of different learning behaviors on knowledge construction. Therefore, based on the Felder - Silverman learning style model, this article uses the Solomon learning style scale to improve the design of the questionnaire and collect four-dimensional differential learning behaviors data. In order to further understand the influence of learning styles on the effectiveness of online learning, we also use online learning data on the Small Private Online Course platform and general cognitive intelligence knowledge integration theory to clarify the relation between learning modes and individuals differences. Results. This study observes and analyzes the learning behavior data of 46 students of Nankai University in the SPOC learning platform, also analyzes the differences in learning styles and knowledge construction of students in the SPOC environment. Compared with the traditional Basic Portuguese teaching method, the blended teaching model based on the Chaoxing Learning platform has unparalleled advantages. Interactions inside and outside the classroom, improving student participation and promoting teaching diagnosis. Conclusion. Through a comprehensive analysis of questionnaire data and online data, we found that some learning styles have different effects on the effectiveness of online learning, ignoring the individual differences of learners will still cause problems in knowledge construction.

Learning Motivations and Learning Behaviors of Sports Majors Based on Big Data

The subjective factors of sports majors play a critical role in the improvement of their cultural quality. Based on data mining, the valuable information about learning motivation and learning behavior can be obtained from the massive data. Therefore, this paper explores the learning motivations and learning behaviors of sports majors based on big data. Firstly, this paper analyzed the features of the learning behaviors of sports majors, and measured the complexity of their learning behaviors with information entropy, approximate entropy, and change-complexity function. Next, a dataset was established based on the students’ use of campus access network and online learning platforms. After that, a time domain convolutional capsule network model of multiple semantic features was established to recognize and classify the learning motivations of sports majors. The proposed model was proved effective through experiments.

Genome-wide analysis of DNA methylation reveals selection signatures of the grass carp during domestication

With the rapid development of aquaculture, many fish species are domesticated and brought into cultivation. In the process of domestication, the domesticated fish undergone intense selection pressures and develop some adaptations and phenotypic traits, namely selection signatures, such as growth and metabolism, immunity, foraging and learning behaviors. However, how this selection signatures emerges is still not clear and the knowledge of molecular epigenetic mechanisms underlying selection signatures in fish is still in its infancy. Thus, we used a farmed fish, grass carp (Ctenopharyngodon idellus), as model species to detect these selection signatures and identify the candidate differentially methylated genes that are closely associated with these selection signatures at the level of whole genome, investigating the role of DNA methylation in the emergence of selection signatures during domestication. Our results showed that domesticated grass carp demonstrated four selection signatures, including growth and metabolism, immunity, foraging and learning behaviors, and 38 candidate genes were found associated with these traits. 16 genes are significant candidate genes which play major roles in the growth and metabolism, such as IGF-1 , GK , GYS1, etc. 11 genes are related to immunity, including . The GRM1, TAS1R1 and TAS1R3 genes are essential for the adaptation of domesticated grass carp to commercial feed in artificial rearing condition. The C-FOS, POMC and CBP genes may be responsible for the acquisition of novel feeding habits and contribute to faster growth indirectly by enhancing food intake. The findings here in will provide new insights to expand our understanding about the role of epigenetic modifications in shaping physiological phenotypes in this and other teleost models, which can contribute to efficient breeding of aquaculture stocks and restocking programmes.