Learning Behavior Data Research Articles

Exploring an online learning burnout assessment model based on learning behavior data

Exploring an online learning burnout assessment model based on learning behavior data

Analysis of Factors Influencing Online Learning Using the Decision Tree Method

Objective: With the continuous development of online learning, the analysis of students' online learning has become increasingly important. Understanding which factors can influence students' engagement in online learning plays a crucial role in improving their learning performance. Methods: By utilizing web crawling techniques, students' online learning behavior data was collected from the Chinese University’s massive open online courses (MOOC) platform. To address the imbalance in the dataset, a synthetic minority oversampling technique (SMOTE) was used. Course progress was used to reflect students' online learning status, which was categorized into interruptions and completions. Furthermore, to tackle the issue of low computational efficiency in the C4.5 decision tree algorithm, its calculation formula was improved to develop an improved version of C4.5. Findings: Of the several factors analyzed, the number of course chapters had the greatest impact on students' online learning, followed by the number of course evaluations and overall course scores. The classification of students’ online learning situations based on an improved C4.5 algorithm revealed that the improved method achieved the highest accuracy rate of 0.942 and the shortest classification time of 0.165 s compared to methods such as the naive Bayesian and random forest algorithms. Novelty: This study designed an improved version of C4.5 to analyze the influencing factors in online learning, and its reliability was demonstrated through experiments, providing a new effective method for data analysis in online learning. Doi: 10.28991/HIJ-2024-05-02-018 Full Text: PDF

Simulation of E-learning in English personalized learning recommendation system based on Markov chain algorithm and adaptive learning algorithm

The research topic of this article is the English personalized learning recommendation module based on Markov chain algorithm and adaptive learning algorithm. Personalized learning recommendation systems have been widely applied in the field of education. Firstly, this article uses Markov chain algorithm to analyze user learning behavior data, abstract user learning behavior as a process of state transition, predict their future behavior based on their past behavior, better understand their learning needs and interests, and provide more personalized learning recommendations for them. Subsequently, combined with adaptive learning algorithms, recommendation strategies and content are dynamically adjusted based on the user's learning goals and level, providing more accurate and effective learning recommendations according to their personalized needs and learning progress. By comparing with traditional recommendation systems, evaluate the accuracy and personalization of the recommendation module to better meet the learning needs of users.

Study of The Technical Index of Online Learning Behavior Analysis of Nursing Majors on The Superstar Platform Based on The Kirkpatrick Evaluation Model

Objective: To analyze the technical indexes of students’ online learning behavior analysis based on Kirkman’s evaluation model, sort out the basic indexes of online learning behavior, and extract scientific and efficient evaluation indexes of online learning effect through statistical analysis. Methods: The online learning behavior data of Physiology of nursing students from 2021–2023 and the first semester of 22 nursing classes (3 and 4) were collected and analyzed. The preset learning behavior indexes were analyzed by multi-dimensional analysis and a correlation analysis was conducted between the indexes and the final examination scores to screen for the dominant important indexes for online learning effect evaluation. Results: The study found that the demand for online learning of nursing students from 2021–2023 increased and the effect was statistically significant. Compared with the stage assessment results, the online learning effect was statistically significant. Conclusion: The main indicators for evaluating and classifying online learning behaviors were summarized. These two indicators can help teachers predict which part of students need learning intervention, optimize the teaching process, and help students improve their learning behavior and academic performance.

Multidimensional clustering analysis of mathematical knowledge difficulty based on Gspan

In addition to providing learners with a large amount of teaching resources, online teaching platforms can also provide learning resources and channels such as video courseware, Q&A tutoring groups, and forums. However, currently, there are still shortcomings in depth and dimensionality in mining student learning behavior data on the platform. In view of this situation, based on the learning interaction behavior, this study established the difficulty similarity model of knowledge points, and used spectral clustering to classify their difficulty. In addition, the study intended to use the maximum frequent subgraph under the Gspan framework to characterize learners’ implicit learning patterns. The outcomes expressed that the algorithm put forward in the study achieved the highest accuracy index of 98.8%, which was 1.4%, 4.0%, and 8.6% higher than Apriori-based graph mining algorithms, K-means, and frequent subgraph discovery algorithms. In terms of F1 index, the convergence value of the algorithm proposed in the study was 95.5%, which was about 2.5% higher than the last three algorithms. In addition, learners of all three cognitive levels had the highest maximum number of frequent subgraphs with sizes above 100 when the minSup value was 60%. And when the number of clusters was 3, the clustering accuracy of the three learners was the highest. In similarity calculation, the calculation method used in the study was at the minimum in terms of root mean square error and absolute error average index, which were 0.048% and 0.01% respectively. This indicated that the model proposed by the research had better classification effect on the difficulty of knowledge points for learners of different cognitive levels, and had certain application potential.

Overview of Online Learning Behavior Analysis in the Context of Big Data

Under the Internet era, various technologies such as big data and cloud computing are becoming more and more a hot issue of concern. Big data provides a large number of network resources with great economic as well as social value, which has a certain impact on various fields in society, and its use in education has received more attention from scholars. After the outbreak of the new crown epidemic, online learning has become a normalized way of learning, online learning platform records a large number of learners' learning data, through the processing and analysis of these massive data, not only is conducive to the realization of students' personalized learning, but also helps teachers to understand and master the current situation of students' learning, and then adjust their teaching. In order to have a clear understanding of the current research status of online learning behavior analysis in the context of big data, the article uses the visual analysis software CiteSpace to analyze the literature selected from the China Knowledge Network (CKN), from which the current status of the research, research hotspots, and future research trends in this field are obtained. The analysis results show that the number of publications has gradually decreased in the past two years, and there is less cooperation and communication between the core publication authors as well as the publication institutions; the analysis of learning behavior data on MOOC platforms has become a research hotspot at this stage, and in-depth learning, multi-scenario, and focusing on the students' learning experience are the future research trends.

Online course evaluation model based on graph auto-encoder

In the post-epidemic era, online learning has gained increasing attention due to the advancements in information and big data technology, leading to large-scale online course data with various student behaviors. Online data mining has become a popular and important way of extracting valuable insights from large amounts of data. However, previous online course analysis methods often focused on individual aspects of the data and neglected the correlation among the large-scale learning behavior data, which can lead to an incomplete understanding of the overall learning behavior and patterns within the online course. To solve the problems, this paper proposes an online course evaluation model based on a graph auto-encoder. In our method, the features of collected online course data are used to construct K-Nearest Neighbor(KNN) graphs to represent the association among the courses. Then the variational graph auto-encoder(VGAE) is introduced to learn the useful implicit features. Finally, we feed the learned implicit features into unsupervised and semi-supervised downstream tasks for online course evaluation, respectively. We conduct experiments on two datasets. In the clustering task, our method showed a more than tenfold increase in the Calinski-Harabasz index compared to unoptimized features, demonstrating significant structural distinction and group coherence. In the classification task, compared to traditional methods, our model exhibited an overall performance improvement of about 10%, indicating its effectiveness in handling complex network data.

Research on Evaluation of Online Education Effectiveness Based on AI Teaching Aid System

Abstract In the age of technology, the application of intelligent assistive systems in teaching is getting more and more attention. After systematically describing the framework of the AI teaching assistance system and the process of online education effect evaluation, the study selects the course of an AI teaching assistance platform as a research case, collects the students’ learning behavior data, and applies the K-means-based clustering algorithm to divide them into clusters to obtain the learner portrait. The association rule algorithm based on Apriori is used to initially mine the connection between online learning behavior and educational effects. Furthermore, the multivariate linear regression method is applied to determine specific associations between online learning behaviors and educational effects to complete the assessment of online educational effects. Through the analysis, four types of learners were summarized: general (37.89%), negative (6.84%), interactive (9.48%), and positive (45.79%). Significant correlations between students’ online learning behaviors and educational outcomes were obtained, with regression equations between them. The effectiveness of online education is greatly influenced by students’ time commitment and learning motivation. Subsequent teaching can start from these two aspects to promote the improvement of the quality of teaching in online education.

Research on Computer-aided Innovation and Entrepreneurship Education Model and Algorithm

Abstract With the rapid development of science and technology, computer-aided technology has been widely used in the field of education, but in the field of innovation and entrepreneurship education (Hereinafter referred to as IEE), there are still problems such as uneven distribution of resources and the disconnection between teaching content and actual needs. This paper puts forward a new model framework of computer-aided IEE, which is student-centered and practice-oriented. Through clear teaching objectives, rich course content, diverse teaching methods, and a scientific evaluation system, students’ innovative consciousness and entrepreneurial ability are comprehensively improved. The course covers innovative thinking, business models, market research, and other theoretical knowledge, and introduces virtual reality (VR) and augmented reality (AR) technologies to simulate the real entrepreneurial process and provide a practical platform. In the aspect of algorithm application, the research combines the content recommendation algorithm and collaborative filtering recommendation algorithm, constructs accurate user portraits by analyzing students’ learning behavior data, and matches them according to the characteristics of learning resources to recommend personalized learning resources for students. At the same time, the learning path optimization algorithm is developed, and the personalized and efficient learning path is planned by using the shortest path algorithm in graph theory to ensure that students can master the required knowledge in the shortest time. The experimental part designed a one-semester teaching experiment, and compared the differences between the experimental group and the control group in academic performance, learning participation, and satisfaction. The results show that the computer-aided IEE model significantly improves students’ academic performance, learning participation, and satisfaction, which verifies the effectiveness of the model. The research on the model and algorithm of computer-aided IEE proposed in this paper provides new ideas and methods for IEE, and helps to cultivate more high-quality talents with innovative thinking and entrepreneurial ability.

A Study of Accounting Teaching Feature Selection and Importance Assessment Based on Random Forest Algorithm

Abstract With the steady progress of China’s education information technology, learners generate massive learning behavior data during classroom interactions, and behind these data lie learners’ implicit behavioral characteristics. In this paper, we use accounting teaching as an example to deeply mine learners’ behavioral data, from which we extract behavioral features related to learning effects to create an experimental dataset. The Random Forest Important Feature Selection Algorithm uses the Gini index to filter out the learning behavior categories with higher importance among the learning behavior feature items. We extensively mine the learning behavior data to construct learning effect prediction models, establish feedback mechanisms, and intervene in the learning process in real time. The learning effect prediction model, which utilizes the Random Forest important feature selection algorithm, increases model prediction accuracy to 85.35% after cross-validation, as shown in the results. The increased accuracy allows for more accurate prediction of students’ learning effects in future periods, effective identification of student problems, and provision of targeted guidance to different student categories. At the same time, teachers can understand students’ learning status in various classes, make timely adjustments to accounting teaching content, and improve the teaching process. Ultimately, accurate education achieves the goal of teaching students according to their abilities.

A 21st century-oriented model for the integration of foreign rule of law personnel and higher education in emerging technologies

Abstract Foreign-related rule-of-law personnel are an indispensable strategic resource for maintaining and expanding national interests, participating in the change of the international governance system, and providing important legal support for promoting the construction of a community of human destiny. This paper begins by outlining the objectives and strategies of training the foreign rule of law talents, describing the specific qualities of these talents, and establishing a “three-inone” foreign rule of law talents training model that integrates emerging information technology. The online learning big data platform for foreign rule of law talents provides the learning behavior data, which we weigh, process, and combine with the SHAP interpretable model to extract the learning behavior features. We used SMOTE to process data sampling imbalances and established a model for predicting student learning performance in combination with the XGBoost model. Additionally, we designed a comparative teaching experiment to analyze the teaching effect using the talent cultivation model. The SMOTE-XGBoost-SBD model yielded a coefficient of determination of 0.487, demonstrated a strong correlation between the predicted and actual performance, and yielded a SHAP value of 1.492 for the knowledge point mastery (C) characteristics of the foreign rule of law students. At the end of the teaching experiment, the mean value of the student’s performance in class A was 10.29 points higher than that in class B, and the average value of the student’s performance in class B was 10.29 points higher. The teaching experiment resulted in a mean score of 10.29 points higher for students in class A than for students in class B. 74.5% 7 of the students agreed with the “Trinity” foreign rule of law talent cultivation model. Using emerging information technology can foster the overall development of foreign rule-oflaw talents by integrating domestic and foreign legal resources.

Online and offline mixed teaching quality assessment method for physical education class based on value assignment method

Abstract The blended teaching mode combines the advantages of online and offline teaching, which can improve the effect of university physical education teaching. The article takes the acquisition path of students’ multidimensional learning behavior data as the entry point, introduces the data preprocessing method after acquiring online learning behavior, and then establishes the online-offline blended teaching quality evaluation index system for physical education classes based on the CIPP model. The subjective and objective weights of the evaluation indexes are solved by using the AHP method and the improved pull-apart grade method, and the comprehensive, integrated assignment method is introduced to weigh the subjective and objective weights in order to obtain the comprehensive weights. Based on the weights of the indicators obtained by AHP-ISD, a teaching quality assessment model for physical education courses was established by combining the SVM model, and the SMO algorithm was selected to optimize the training of the model. To assess the application effectiveness of the model, a comprehensive assessment of its teaching quality was carried out, and the teaching effect of the blended teaching mode was also explored. The weight of the learning outcome evaluation index is 0.438 at most, the accuracy of the SMO algorithm training model is up to 99.99%, and the range of error scores between the model evaluation value and the actual value is between [0.01,0.03] points. The teaching quality assessment model based on the assignment method can obtain more accurate teaching quality assessment results for physical education courses and provide a new direction for optimizing the hybrid teaching assessment method of physical education courses.

Design and Implementation of the Reliable Learning Style Recognition Mechanism Based on Fusion Labels and Ensemble Classification

Learning style recognition is an indispensable part of achieving personalized learning in online learning systems. The traditional inventory method for learning style identification faces the limitations such as subject and static characteristics. Therefore, an automatic and reliable learning style recognition mechanism is designed in this paper. Firstly, a learning style labeling framework (LSDFA) based on multi-label fusion is proposed, which can obtain learning style labels by mining the potential information of two sets of inventories. Furthermore, a two-layer ensemble model (SRGSML) based on learners' online learning behaviors data to recognize learners' learning styles is proposed, which combines the resampling technology (SMOTE) to solve the unreliable prediction problem caused by class imbalance. The superiority of the proposed mechanism is verified on learning behavior data of 2,056 learners during the online teaching period of Shanghai Normal University. Experimental results show that the recognition accuracy of SRGSML achieves to 0.977, as well as prove the effectiveness of the LSDFA for labeling learning style.

Modern Transformation of Ancient Chinese Philosophical Thought in Ideological And Political Education in Colleges and Universities Based on Multiple Learning Styles Adaptation

Abstract Ancient Chinese philosophical thinking, as an important part of Chinese civilization, has influenced thousands of years of Chinese history and also had a profound impact on the Ideological and Political Education in modern colleges and universities. Based on the philosophical nature of Ideological and Political Education, the article analyzes the learning styles of different categories and establishes a blended-tiered teaching model for Ideological and Political Education with the aid of digital technology. Based on students’ online Ideological and Political education learning behavior data, a Bayesian discriminant analysis algorithm is used to identify students’ learning styles. Then, the GRU neural network model is introduced to define the diagnosis of the knowledge level of Ideological and Political Education, and the Ideological and Political Knowledge Level Diagnosis Model is established. An example analysis was conducted to assess the learning style, cognitive level, and relevance of Ideological and Political Education. The study shows that when carrying out the identification of students’ learning styles, the Bayesian discrimination improves by 10.98% compared with the results of the style clustering algorithm, and the average absolute error of the diagnosis of students’ Civics knowledge level minimizes only 0.128. The scores for various learning styles are highly variable, and the extreme differences are all over 24 points. The standardized regression coefficients of learning interest in Ideological and Political courses and literacy learning styles are between 0.072 and 0.163, with a very significant correlation. Incorporating ancient Chinese philosophical ideas into ideological and political education is conducive to satisfying students’ multiple learning styles and also contributes to modernizing and preserving ancient philosophical ideas.

Deep mining method of online learning behavior data based on big data analysis

Deep mining method of online learning behavior data based on big data analysis

Prediction method of College Students' Achievements Based on Learning Behavior Data Mining

Prediction method of College Students' Achievements Based on Learning Behavior Data Mining

Design of Customized Teaching Strategies Based on User Behavior Analysis in the Digital Transformation of Health Education

Abstract With the greater popularity of the Internet, on the one hand, online education platforms have flourished and education informatization has entered a new era, with massive learning behavior data generated by learners in different learning platforms. This paper constructs a portrait of student learning behavior based on the characteristics of their learning behavior in the health education class. Based on the clustering analysis method in the big data mining algorithm, the user’s behavioral characteristics are analyzed. On this basis, the algorithm is improved by using collaborative filtering personalized recommendation and introducing the LDA model, and a customized teaching model is constructed in the context of health education, and its application effect is explored. From the four dimensions of “course completion characteristics”, “teaching interaction characteristics”, “learning input characteristics,” and “learning achievement characteristics”, we analyzed different groups of students and investigated the effect of its application. “The behavioral characteristics of different groups of students were analyzed, and it was concluded that Group A and Group B performed better, but Group C accounted for a higher percentage of 24%. Finally, according to the collaborative filtering-based digital customized teaching on the students’ health education test scores for the pre and post-test, it was concluded that the average scores of the experimental subjects increased after the post-test. The mean scores for the third post-test were 4.27, 4.44, and 4.35, respectively. It can be concluded that the customized teaching model has a significant improvement in the students’ classroom teaching effectiveness.

Exploring the Path of Civic-Constitutional Construction of Civil Aviation Professional English Courses in the Information Age

Abstract The form of online teaching in the information age has become the mainstream of the construction of civil aviation professional English courses in Civics. In this paper, the digital resource module for the English course Civics for Civil Aviation Professionals is screened out by combining it with the teaching design of the Civics course for civil aviation English courses. With the help of the subtitle text selection method and the semi-supervised model of S4VM to label the teaching resources of the English course Civics, the CUMPF model is used to recommend the teaching resources of the English course Civics. Collecting and organizing the online learning behavior data of flipped classrooms to explore the influence of long and short-acting course resource design factors on the continuity of online learning, and recommending teaching resources based on the analysis results. The results of the effectiveness of the construction of the civil aviation professional English course’s Civic and political construction are analyzed from the degree of integration of the course’s Civic and political elements as well as from the four dimensions of course background, course guarantee, course implementation, and course effect, respectively. The integration degree of English course Civics resources for civil aviation majors is the best, which can reach up to 3.9315. The overall construction scores of the English course Civics are 0.907, 0.809, 0.744, and 0.768. The construction of the course implementation dimension needs to be improved, and the teaching materials of the English course Civics need to be improved in terms of writing and design. Civil aviation majors can benefit from the study’s ability to check and fill in the gaps in the Civics and Politics of English course construction.

Research on Management Path and Operation Mechanism Construction of Civic Education in Colleges and Universities in the Era of Artificial Intelligence

Abstract Under the background of the artificial intelligence era, the education management style of colleges and universities is moving towards a more intelligent direction. This paper combines the F-S learning style model and the environmental characteristics of online learning to construct an index system of online learning behavioral characteristics for Civic and Political Education in colleges and universities. On this basis, the traditional K-means clustering algorithm is improved based on three-branch decision-making and is used to cluster and divide the learning behaviors of students in the Civic and Political Education courses. At the same time, the degree of interest is introduced to optimize the Apriori algorithm, and the association rules of students’ learning behavior and performance are mined. Then, taking the student learning behavior data of the online course of X Civic and Political Education in colleges and universities as a research sample, TK-means, and Apriori algorithm are used to explore the management path and operation mechanism of Civic and Political Education in colleges and universities. The study shows that among the students in the four clusters, the students with higher task point completion, chapter completion number, and check-in number are the most, accounting for 32%, and the students with a higher course video completion progress, task completion number, and document completion are the least, accounting for 19%. The probability of receiving an ‘Excellent’ grade was 93.9% when students were classified as ‘Visual-Active-High-Commitment’. When students were of the ‘Verbal - Active - passive - High Engagement’ type, there was a 91.3% probability of getting a ‘Medium’ grade. The effectiveness of civics education can be improved by enriching curriculum resources and improving assessment methods.

Exploring the Microteaching model of English courses in the digital era

Abstract The application of microteaching in English teaching can not only create a good atmosphere for learning English but also deepen the change of teaching mode and promote English teaching to deep development. In this paper, the output-oriented model is combined with microclasses to establish a blended teaching model for English. For students’ online learning behavior, the K-means clustering algorithm is used to classify them, and the GBDT algorithm and integrated learning Stacking algorithm are combined to predict their performance. Taking the online learning behavior data under the blended teaching mode as an example, a practical analysis was carried out in three aspects: the classification of students’ English online learning behavior, the prediction of academic performance, and the satisfaction of the blended teaching mode. The results show that the number of clusters of English online learning behavior is 5, and the comprehensive score of cluster 1 reaches 91.52. When the progress of blended teaching in the English course developed from 10% to 100%, the accuracy of students’ learning performance prediction increased by 20.97 percentage points. Students’ satisfaction with the “output-oriented method + micro-teaching” blended teaching mode reached 86.34% with grade B and above. The blended teaching mode of combining microteaching and English courses in the digital era can improve students’ independent learning ability and enhance their English application ability.