Online Learning Behavior Analysis Based on Image Emotion Recognition

As a brand-new learning strategy, cooperative learning can greatly improve the quality of classroom teaching and the teamwork and learning efficiency of students. The conventional student grouping models for cooperative learning take less consideration of the complementarity of students’ knowledge structures and learning interests, so they are not quite suitable for online teaching, which is provided for a huge number of students and has a large scale of learning resources and great freedom of choice. To this end, this paper studies the student grouping method for massive online collaborative learning. Firstly, the problem of identifying the student’s knowledge state was described and characterized, and a diagnosis model of students’ knowledge state simulating the cooperative learning process was constructed based on the gated recurrent neural network. The creation of an online collaborative learning scenario that considers both the knowledge state and interests of students was regarded as an NP-hard problem, and then, the enhanced particle swarm optimization algorithm was adopted to realize the grouping of students for massive online collaborative learning. The experimental results verified the effectiveness of the model constructed in this paper.

Section: Introductionmentioning

confidence: 99%

A Student Grouping Method for Massive Online Collaborative Learning

Wang¹,

Qi²

2022

“…Newly emerged technologies such as Internet+ and cloud computing are changing people's every life aspect subtly, in terms of education, they have greatly promoted the development of smart education and online education [1][2][3][4][5][6]. However, the existing learning resource search engines provided by current smart education platforms couldn't meet students' needs of retrieving personalized learning resources based on fuzzy learning objectives, as a result, personalized teaching and accurate application of the competency-based instructing system couldn't be realized, especially for students with large structural differences in their professional knowledge cognition level and knowledge system, more attention needs to be paid to their learning preferences and personality traits when recommending personalized learning resources for them [7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Retrieval and Recommendation of English Learning Resources Based on Knowledge Correlation

Li¹

2022

The design of retrieval and recommendation method of personalized learning resources based on students’ cognition level of professional knowledge and the correlation degree of the knowledge is of certain practical significance. In reality, students’ learning preferences and needs will change with the passing of time and the upgrading of learning stages, so giving learning resource recommendations without considering the time series features of students’ needs for learning resources cannot guarantee students' learning efficiency or the effect of personal knowledge system perfection. To solve this problem, this paper took online English learning as an example to study the retrieval and recommendation of English learning resources based on knowledge correlation. At first, the paper gave the relationship between the knowledge points of English learning resources, and gave judgements on students’ mastery degree of knowledge points. Then, the influence of the semantics and relationships of knowledge points involved in English learning was fully considered, and the closeness degree of the correlation of learning resources was calculated. At last, this paper introduced a hybrid attention mechanism into the learning resource recommendation model, and gave the process for calculating the weight of hybrid attention. The effectiveness of the constructed model was verified by the experimental results.

“…In this context, how to scientifically and properly organize and guide learners to learn actively and efficiently has become a research subject for domestic and foreign scholars [7][8][9][10][11][12]. To achieve this goal, it is particularly important to analyze and study the features and patterns of learners' learning behaviours [13][14][15][16][17][18]. The analysis of learning behaviour features includes two parts -group feature analysis and individual feature analysis.…”

Section: Introductionmentioning

confidence: 99%

Features of Group Online Learning Behaviours Based on Data Mining

Zhu¹,

Wang²,

Wang³

2022

With the development of information technology, how to scientifically and properly organizing and guiding learners to learn actively and efficiently has become a research subject for domestic and foreign scholars. However, existing research on online learning behaviours studied little about learning attitudes, learning preferences, student-student interaction, teacher-student interaction and so on. To this end, this paper studies the features of group online learning behaviours based on data mining. In this paper, a K-means-based group online learning behaviour feature selection model and an AdaBoost-based group online learning behaviour classification model were constructed, and the processing methods, execution processes and algorithm functions of the two models were described in detail. Finally, the effectiveness of the constructed models was verified through an experiment.