Student Behavior Data Research Articles

A Student Education Data Mining Method based on Student Sequential Behaviors and Hybrid Recurrent Neural Network

This research aims to propose a student education data mining method based on a hybrid recurrent neural network and improved support vector machine-decision tree algorithm through in-depth analysis of student behavior sequences. The method combines the feature extraction capability of a hybrid recurrent neural network and the nonlinear mining efficiency of support vector machine-decision tree algorithm to achieve efficient prediction of students’ learning behavior and performance. Experimental results have shown that the designed method completed an APA of 91.3% and 89.2% for the HR-SDT model on the Student_1 and Student_2 datasets, respectively. The F1 score average values of the HR-SDT model reached 86.7% and 81.9%, respectively. The results indicate that the student behavior data mining method based on hybrid recurrent neural networks can accurately predict the learning behavior and performance of students, providing valuable insights and decision support for educators.

Data Mining Technology for Smart Campus in Behavior Association Analysis of College Students

The data in smart campuses is complex and massive, with insufficient utilization, and existing data processing methods have many limitations. Therefore, in order to improve the efficiency of data processing in universities and assist in student management, a data processing method integrating cluster analysis and association rule mining is proposed. The proposed method is divided into two parts. Firstly, an improved K-Means model based on information entropy and density optimization is constructed for clustering analysis of student consumption, learning, and other data; Secondly, use the improved Mapping Apriori to obtain the correlation between student grades, consumption records, and learning behavior. The clustering results on student consumption data show that the average accuracy of ED-K-Means clustering is 97.41%, which is 12.8%, 8.5% and 4.0% higher than the comparison algorithm. The result of the correlation between consumption level and achievement shows that when the amount of consumption is less than 1500 yuan, the student’s achievement is directly proportional to the amount of consumption. Therefore, the proposed method can effectively mine and analyze student behavior data, which has important practical significance for intelligent management in universities.

Visual analysis and interactive interface design of students' abnormal behavior introducing clustering algorithm.

Traditional methods have the limitations of low accuracy and inconvenient operation in analyzing students' abnormal behavior. Hence, a more intuitive, flexible, and user-friendly visualization tool is needed to help better understand students' behavior data. In this study a visual analysis and interactive interface of students' abnormal behavior based on a clustering algorithm were examined and designed. Firstly, this paper discusses the development of traditional methods for analyzing students' abnormal behavior and visualization technology and discusses its limitations. Then, the K-means clustering algorithm is selected as the solution to find potential abnormal patterns and groups from students' behaviors. By collecting a large number of students' behavior data and preprocessing them to extract relevant features, a K-means clustering algorithm is applied to cluster the data and obtain the clustering results of students' abnormal behaviors. To visually display the clustering results and help users analyze students' abnormal behaviors, a visual analysis method and an interactive interface are designed to present the clustering results to users. The interactive functions are provided, such as screening, zooming in and out, and correlation analysis, to support users' in-depth exploration and analysis of data. Finally, the experimental evaluation is carried out, and the effectiveness and practicability of the proposed method are verified by using big data to obtain real student behavior data. The experimental results show that this method can accurately detect and visualize students' abnormal behaviors and provide intuitive analysis results. This paper makes full use of the advantages of big data to understand students' behavior patterns more comprehensively and provides a new solution for students' management and behavior analysis in the field of education. Future research can further expand and improve this method to adapt to more complex students' behavior data and needs.

Predicting classroom activity index through multi-scale head posture classification network

The quantification of the interplay between student behavior data and classroom teaching effectiveness using quantitative metrics has perennially posed a challenge in the evaluation of classroom instruction. Classroom activity serves as a reflection of student engagement, emotional ambiance, and other pertinent aspects during the pedagogical process. This article presents a methodology for quantifying student head posture during classroom instruction utilizing AI-driven video analysis technology, notably the Classroom Activity Index (CAI). A Classroom Activity Analysis System (CAAS) was designed and developed, integrating a multi-scale classification network based on ECA-ResNet50 and ECA-ResNet18. This network discerns and categorizes various head regions of students situated in both the frontal and real rows of a lecture-style classroom, irrespective of their dimensions. The classification network attains exceptional performance, boasting F1 score of 0.91 and 0.92 for student head-up and head-nodding. Drawing on the live classroom instruction at a higher vocational college in Wuhan, Hubei Province, China, a comparative experiment was executed. The findings revealed that three factors: teacher-student verbal interaction, teacher body language, and utilization of digital resource, all exert an influence on CAI. Simultaneously, the degree of classroom activity as gauged by FIAS and manual analysis fundamentally aligns with the CAI indicators quantified by CAAS, validating the efficacy of CAI in the quantification of classroom activity. Consequently, the incorporation of CAAS in teaching, research, and oversight scenarios can augment the precision and scientific rigor of classroom teaching assessment.

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.

Blockchain Enhanced Student Physical Performance Analysis using Machine Learning-IoT and Apriori Algorithm in Physical Education Network Teaching

In the digital era, particularly with the rise of online teaching, traditional approaches to college physical education face challenges in adequately monitoring and enhancing students’ physical fitness. This study introduces a novel approach that integrates blockchain technology with a Machine Learning-IoT framework to evaluate and improve students' physical performance. Utilizing the Apriori algorithm, enhanced with particle swarm optimization and an improved K-means methodology, this system offers a robust tool for correlating student behavior with sports performance in a secure and decentralized manner. The proposed system uses blockchain for safe data management and IoT for real-time data collection, ensuring privacy as well as efficiency. The algorithm's accuracy, recall, and F1 values on the Iris dataset are 0.947, 0.931, and 0.928, respectively, with a considerable Calinski Harabasz score of more than 240. When applied to university student behavior data, the blockchain-enhanced system successfully mined association rules with a maximum confidence level of 0.923.

Analysis of English Classroom Interaction in Colleges and Universities Based on Student Behavioral Data

Abstract With the advancement of the information age, the traditional teacher-led English classroom interaction in colleges and universities has made it challenging to meet the individualized needs of different students. Therefore, this paper takes the current classroom behavior data of college students as the basis, uses the K-means clustering algorithm and I-divergence measure to categorize, analyze, and study the student behavior data, and digs out the correlation between students’ classroom behavior data and teaching interaction. This paper takes all the teachers and students of English majors in college M as the research samples. It conducts experimental research in terms of teachers’ and students’ classroom speech rates, teachers’ and students’ questioning rates, and teachers’ and students’ use of instructional technology, etc. The 10 classes of English majors in college M do not have more than 50% of the students’ speech rate, except for class 2. Class 2 has the highest speech rate (61.64%) among students, while class 5 has the lowest rate (7.5%). From the point of view of active questioning rate, 10 classes had very low SQ ≤ 0.02, and even in classes 1, 3, 4, 5, and 6, there was a situation where students’ active questioning rate was zero. After analyzing the student behavior data in some classes, it was found that the mean score of English test students in the experimental group before and after the test increased by 4.687, corresponding to a significance Sig value of 0.000<0.05, which reaches the level of significance. The analysis of classroom behavior data reveals that enhancing the ratio of teacher-student interaction activities can improve students’ English scores.

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.

RETRACTION: Improving College English Reading Teaching Efficiency Based on Student Behavior Data Mining and Mobile Edge Computing

RETRACTION: Improving College English Reading Teaching Efficiency Based on Student Behavior Data Mining and Mobile Edge Computing

Construction of Cloud Computing Resource Allocation and Ideological and Political Education Platform Based on the Theme of Party History and Party Building

Abstract Party history and party-building education is an important carrier of party-building work in colleges and universities, and it is also an important content of cultivating and promoting socialist core values while party-building work is an effective way and the main hand of ideological and political work of students in colleges and universities. This paper takes the large amount of data generated in the process of ideological and political education resource allocation on the theme of party history and party building as the research object and builds a mapping relationship between tasks and ideological and political education resources according to certain strategies based on cloud computing resource allocation. A platform for allocating resources for ideological and political education has been designed and developed, which is based on a time series clustering algorithm and constructs resource overviews, sequence collections, and clustering modules. The functions of student behavior data collection and overview, feature calculation and selection, behavior time series clustering, and group feature analysis are realized, which enhances the efficiency of the ideological and political education resource platform. Functional and performance tests of the platform were completed, and the average system response times of the three modules were 75.05, 80.39, and 69.95ms, which were able to meet the actual application standards. With the help of the platform, the behavioral record data of 6,927 platform users were evaluated and practiced, and the user group classification and group characterization were carried out according to the output of the platform, which provided scientific suggestions for the distribution of ideological and political teaching resource services.

Using learning analytics to understand the learning design patterns of K12 synchronous language teaching

ABSTRACT The global expansion of online language courses is on the rise, offering greater flexibility in the approaches to learning design. This study delves into the exploration of the fundamental learning design patterns within a K-12 synchronous language course. Leveraging a rich array of textual data, including syllabi, textbooks, course outlines, student behavior data, and recorded online instructional videos, network analysis and discourse analysis were employed. Results spotlighted the pivotal role of “dialogue” in connecting various learning activities. Furthermore, the study underscores the significance of language usage over strict adherence to grammatical rules and phonetic pronunciation. Additionally, technology has transcended its conventional role as a mere tool for reinforcing teacher authority, but it has evolved into an environment where instructors regain face-to-face authority, thereby influencing semi-recursive interactions among learners throughout the course. These findings highlight the importance of dialogue and language use in online language instruction, as well as emphasize the transformative potential of technology in reshaping teacher-student interactions.

An English course practice evaluation system based on multi-source mobile information and IoT technology

With the increased use of online English courses, the quality of the course directly determines its efficacy. Recently, various industries have continuously employed Internet of Things (IoT) technology, which has considerable scene adaptability. To better supervise the specific content of English courses, we discuss how to apply multi-source mobile Internet of Things information technology to the practical evaluation system of English courses to boost the performance of English learning evaluation. Therefore, by analyzing the problems of existing English course evaluation and the characteristics of multi-source mobile Internet of Things information technology, this article designs an English course practical evaluation system based on multi-source data collection, processing, and analysis. The system can collect real-time student voices, behavior, and other data through mobile devices. Then, analyze the data using cloud computing and data mining technology and provide real-time learning progress and feedback. We can demonstrate that the accuracy of the evaluation system can reach 80.23%, which can effectively improve the efficiency of English learning evaluation, provide a new method for English teaching evaluation, and further improve and optimize the English education teaching content to meet the needs of the actual teaching environment.

Research on the development of digitalization of art education in the era of big data technology

Abstract Exploring the digital development of art education can effectively enhance students’ creativity in art design. This paper constructs a digital teaching platform for art education based on big data technology and analyzes student learning behavior data in the teaching platform. For student learning behavior with a new Hawkes process for data extraction, the decomposition of the student learning effect is realized by data encoder, event-level decoder and course-level decoder. Performance tests and art teaching effect analysis were conducted for the platform built in this paper. From the performance test, the throughput of the test interface is 580 when the server CPU is maintained at about 26%, memory is maintained at about 48.62%, and load is maintained at about 4.7. From the teaching effect, the four dimensions of students’ creativity changes had significant differences; namely, the p-values of adventurousness, curiosity, imagination, and challenge were 0.189, 0.247, 0.076, and 0.425, respectively. This indicates that the digital teaching platform for art education built by using big data technology can effectively enhance students’ creativity and also provide a new direction for the digital development of art education.

Research on the innovation of ideological and political education for college students based on the Civic and Political Science Cloud Education Platform

Abstract Innovative ideological and political education for college students is to help better students improve their ideological quality and political literacy. In this paper, under the background of big data, the Civic and Political Cloud Education Platform is constructed using big data technology, which is mainly composed of four main parts: model layer, view layer, control layer, and basic services. Student behavior data is collected and analyzed through a collaborative filtering recommendation algorithm under big data collection and analysis technology, and performance simulation analysis is conducted for the Civic and Political Science Cloud Education Platform. From the performance analysis, when the number of concurrent users of the Civic Education Cloud Platform is 80-120, the average transaction processing per second is stable at 10.5 s. From the practicality, the Civic Education Cloud Platform built by big data can effectively explore the value of Civic Education teaching resources. This shows that the Civic and Political Science cloud education platform is an effective way to innovate and develop the ideological and political education of college students, and through this platform, the ideological quality and political literacy of college students can be effectively improved.

A Model to Predict and Analyze Students' Learning Preferences and their Cognitive Development through Educational Big Data

Underpinned by the accelerated progression of information technology, the role of educational big data in information gathering and analysis has been underscored, particularly so in finance, a discipline embedded in logic and analysis. Patterns in student learning and behavioral data, when examined, can afford educators invaluable insights to shape efficacious teaching strategies. Contemporary research probing into the dynamics of student learning preference evolution and cognitive advancement appears to over-depend on static data, often falling short of effectively addressing the intricate data structures in educational big data. In this light, it becomes imperative to delve into the temporal shifts in student learning preferences and their link to cognitive advancement. In this context, a novel dynamic trustaware preference evolution model is brought to the fore, with the potential to precisely track variations in learning preferences of finance students and elucidate their correlation with cognitive advancement. A correlation model is erected, laying bare the reciprocal interaction between the metamorphosis of student learning preferences and cognitive progression. This pioneering approach eclipses the constraints inherent in extant research methodologies, rendering deeper comprehension to educators. Findings from regression analysis divulge the association between the transformative journey of learning preferences and cognitive advancement, holding far-reaching implications for educational practices. These revelations can capacitate educators to fine-tune their teaching approaches in line with student development, fostering personalized learning ecosystems. This research further holds significant merits for addressing complexities within finance education, aiding in the cultivation of adept professionals capable of navigating the fluid landscape of modern finance.

Analysis of educational data enabled by deep learning to increase student success

A key component of improving educational quality is identifying pupils who are at a high risk of doing poorly academically as early as feasible. To accomplish this, most studies now in existence have used conventional Deep learning (DL) algorithms to forecast students' academic progress based on their behavior data, from which behavior elements are manually identified owing to the professional expertise and knowledge. Nevertheless, it has become increasingly difficult to recognize finely constructed handcrafted traits as a result of a rise in the types and quantities of behavioral data. The Enriched Plant Growth Optimized Artificial Neural Network (EPGO-ANN) technique enabled data analysis of educational data which is a viable tactic that may be used to improve student accomplishment in educational settings as we suggested in this research. The optimization predicts the academic success by autonomously extracting characteristics from student behavior data from several heterogeneous sources. This model's novelty employs recording the in-built time-series data for each kind of activity and uses EPGO-ANN to extract correlation features between various behaviors. The results of the experiments show that the suggested deep model approach outperforms several DL methods. The results of experiments show that the EPGO-ANN technique is superior to other DL methods.

Theory of physical education ecosystem based on SFIC model

Abstract Through comparison and logical analysis, the author expounds the basic concepts and components of the physical education ecosystem are expounded, the SFIC physical education ecosystem model is established, and a student sports performance warning method based on machine learning is proposed. In view of the heterogeneous student behavior data, data preprocessing technology is adopted to preprocess sample data, and data characteristics are extracted based on knowledge points and item types. A sports achievement warning model (K-DNN) based on knowledge points and item types is established, and the students’ sports achievement warning model is designed and implemented. The experimental results show that, compared with DNN algorithm, Adaboost and ridgeregregression, K-DNN algorithm has the highest accuracy in predicting Ac and the lowest mean square error in predicting MS, indicating that K-DNN model has higher accuracy and better motion prediction effect.

Retracted: The Role of Mastering Musical Instrument Playing Skills Combined with Student Behavior Data Mining and Analysis in the Digital Campus Environment to Improve Students' Comprehensive Quality.

[This retracts the article DOI: 10.1155/2022/7724675.].

Analysis and Prediction of Student Performance Based on Moodle Log Data using Machine Learning Techniques

During the COVID-19 Pandemic, many universities in Thailand were mostly locked down and classrooms were also transformed into a fully online format. It was challenging for teachers to manage online learning and especially to track student behavior since the teacher could not observe and notify students. To alleviate this problem, one solution that has become increasingly important is the prediction of student performance based on their log data. This study, therefore, aims to analyze student behavior data by applying Predictive Analytics through Moodle Log for approximately 54,803 events. Six Machine Learning Classifiers (Neural Network, Random Forest, Decision Tree, Logistic Regression, Linear Regression, and Support Vector Machine) were applied to predict student performance. Further, we attained a comparison of the effectiveness of early prediction for four stages at 25%, 50%, 75%, and 100% of the course. The prediction models could guide future studies, motivate self-preparation and reduce dropout rates. In the experiment, the model with 5-fold cross-validation was evaluated. Results indicated that the Decision Tree performed best at 81.10% upon course completion. Meanwhile, the SVM had the best result at 86.90% at the first stage, at 25% of the course, and Linear Regression performed with the best efficiency at the middle stages at 70.80%, and 80.20% respectively. The results could be applied to other courses and on a larger e-learning systems log that has similar student activity conditions and this could contribute to more accurate student performance prediction.

Construction of College Students’ Management Informatization Ecosystem Based on Data Analysis Technology

College students’ management informatization ecosystem can help college students better manage information and resources, thus improving learning and life efficiency. It’s important to introduce data technology into the college student management informatization ecosystem, which can better realize the extraction of student behavior fluctuation information and achieve more targeted student management decisions. The current research lacks consideration of its future development trend, such as the impact of the application of technologies, including artificial intelligence, big data Fenix, and the Internet of Things. This paper studies the construction of college students’ management informatization ecosystem based on data analysis technology. Firstly, the design of the data fusion scheme applied to the college students’ management informatization ecosystem is carried out, and the idea of the scheme is given. Aiming at the big data of students’ learning and living behaviors, this paper digs deep into the value of data information, and extract historical student behavior characteristics, providing a basis for short-term student behavior prediction and management decision-making planning and implementation for the college students’ management informatization ecosystem. Based on historical student behavior data and its characteristic data, the XGboost algorithm is used to quantify and extract the importance of each influencing factor on student behavior fluctuations. Experimental results verify the effectiveness of the method proposed in this paper.