International Journal of Continuing Engineering Education and Life-Long Learning (24 papers in press)

Special Issue on: OA Adaptive E Learning Technologies and Experiences

• Open Access

  Construction of intelligent student management evaluation information system based on clustering algorithm ( Free Full-text Access )

  by Hongyuan Ma, Yin Chen, Yujia Song 
  Abstract: For a long time, the management evaluation information work of students has relied on the subjective evaluation of people. Such evaluation is not highly professional and scientific, and the evaluation experience is not easy to be inherited and preserved. This paper selected the K-means clustering algorithm to build an intelligent learning management evaluation information system, because it can better reflect the actual needs and solve the application requirements according to the actual needs. This paper uses the grades of 20 college students as data samples and applies the K-means clustering algorithm to the intelligent student management and evaluation information system. The management and processing mechanism of students in colleges and universities had been improved to improve the speed of data analysis, so that the outstanding rate of students had increased by about 20% compared with the original. This could help the decision-making of colleges and universities to be more professional. Through mobile communication intelligent decision support system, the construction of the student management evaluation information system was realised.
  Keywords: k-means clustering algorithm; information evaluation system; performance analysis; clustering algorithm; student performance.
  DOI: 10.1504/IJCEELL.2025.10074391
   
  

• Open Access

  Study on fuzzy comprehensive evaluation of English teaching quality based on artificial neural network ( Free Full-text Access )

  by Lingyan Mao, Yuting Yan, Aihua Shen 
  Abstract: In order to improve the coverage and accuracy of evaluation indicators, a fuzzy comprehensive evaluation method for English teaching quality based on artificial neural networks is proposed. Firstly, association rules and rough set techniques are used to collect and analyse English teaching data, and a fuzzy comprehensive evaluation index system for English teaching quality is constructed. Secondly, a multi-layer fuzzy comprehensive evaluation model is constructed, and sample data of English teaching quality is obtained by the expert scoring method. The data are used for subsequent artificial neural network learning and prediction. Finally, a fuzzy comprehensive evaluation model for English teaching quality is constructed using BP neural network. By training and learning the internal data association pattern of the network, English teaching quality evaluation is achieved. The experimental results show that the indicator coverage of the proposed method remains stable between 94.6% and 95.4%, and the highest evaluation accuracy reaches 98%.
  Keywords: artificial neural network; English teaching quality; fuzzy comprehensive evaluation; evaluation index system.
  DOI: 10.1504/IJCEELL.2025.10074954
   
  

• Open Access

  The application effect of MOOC videos in English audio-visual teaching ( Free Full-text Access )

  by Yansong Zhang 
  Abstract: In order to improve the completeness and accuracy of evaluation indicators for the analysis of the effectiveness of English audio-visual teaching, a method for analysing the application effect of massive open online course (MOOC) videos in English audio-visual teaching is proposed. The factor analysis method is adopted to screen evaluation indicators for the application effect of MOOC videos in English audio-visual teaching, and the balanced iterative reducing and clustering using hierarchies (BIRCHs) algorithm is utilised to cluster the evaluation indicator data. Using the clustered indicator data as input variables and the application effect evaluation values as output variables, an adaptive BP neural network model is constructed to achieve accurate analysis of the application effect of MOOC videos in English audio-visual teaching. The experimental results show that the proposed method achieves a maximum recall rate of 98.56% in evaluating English audio-visual teaching effectiveness, and the evaluation accuracy varies between 94.76% and 97.82%.
  Keywords: MOOC videos; English; audio-visual teaching; application effect; BIRCH algorithm; adaptive BP neural network model.
  DOI: 10.1504/IJCEELL.2025.10075085
   
  

• Open Access

  Cloud-based user behaviour analysis and personalised recommendation of sports teaching system based on big data analysis ( Free Full-text Access )

  by Guohua Li 
  Abstract: The fragmentation and dynamic changes of user behaviour data in the current cloud basketball teaching system lead to delayed recommendation content and low matching degree. This paper proposes a personalised recommendation method based on big data analysis and deep learning. It combines the long short-term memory (LSTM) network to extract training time series features, and integrates the collaborative filtering algorithm to optimise personalised recommendations to accurately identify users’ training rhythm and technical shortcomings. Experiments show that after 50 training cycles, the model’s root mean square error (RMSE) reached 0.36 and the mean absolute error (MAE) was 0.33. After the personalised recommendation system, the user training completion rate was improved, ranging from 20% to 30%. This method can effectively improve the intelligence level of basketball teaching system and promote the realisation of personalised learning.
  Keywords: physical education system; personalised recommendations; big data analysis; long short-term memory network; LSTM; collaborative filtering; mean absolute error; MAE.
  DOI: 10.1504/IJCEELL.2025.10075329
   
  

• Open Access

  An evaluation of online English teaching learning effectiveness based on decision tree classification algorithm ( Free Full-text Access )

  by Yingying Qi 
  Abstract: To enhance the accuracy and real-time performance in evaluating online English teaching effectiveness, this study proposes an evaluation model based on the decision tree classification algorithm. First, an evaluation index system is established, and principal component analysis (PCA) is employed to screen the most relevant indicators. The filtered data is then pre-processed for analysis. Given that online English teaching data is typically a hybrid data type, the classification and regression trees (CART) algorithm is utilised for the evaluation task. Furthermore, to mitigate model overfitting, an improved algorithm that incorporates decision tree depth as a pruning weight is introduced. Experimental results demonstrate that the proposed method achieves a maximum R² value of 0.974, a maximum inconsistency index of only 0.29, and a maximum evaluation time of 5.80 seconds. These findings indicate that the method possesses high evaluation accuracy and promising real-time performance.
  Keywords: online English teaching; assessment of learning outcomes; decision tree classification algorithm; tree depth.
  DOI: 10.1504/IJCEELL.2026.10076032
   
  

• Open Access

  The strategy of empowering education development with artificial intelligence in the digital age ( Free Full-text Access )

  by Mingyue Sun 
  Abstract: To solve the limitations of traditional education development strategies, including low achievement of learning objectives, low utilisation of teaching resources, and low academic performance, a strategy of empowering education development with artificial intelligence (AI) in the digital age is proposed. An education quality evaluation system is built. Education quality evaluation data is collected through knowledge graph, and input into RBF neural network to obtain the education quality evaluation results. Based on the evaluation results of education quality, strategies of empowering education development with AI in the digital age are proposed from the aspects of building a smart education ecosystem, promoting personalised teaching, improving teacher teaching efficiency and quality, and promoting educational innovation and international cooperation. Case test results show that the proposed method achieves a maximum teaching objective achievement rate of 98.47%, a maximum teaching resource utilisation rate of 97.96%, and a maximum learning performance of 94.15%.
  Keywords: digital age; artificial intelligence; empowering education development; knowledge graph; RBF neural network.
  DOI: 10.1504/IJCEELL.2026.10076033
   
  

Special Issue on: OA Smart and Continuing Education and Life Long Learning

• Open Access

  Design and implementation of a real-time intelligent translation system for network language based on incremental learning ( Free Full-text Access )

  by Ying Liu 
  Abstract: This paper proposes a real-time intelligent system based on incremental learning for translating network language, in order to solve the problem of traditional translation systems being unable to cope with language changes, resulting in insufficient translation accuracy and adaptability. This paper adopts a converter model to construct a translation architecture, which effectively processes complex language structures using its self-attention mechanism while receiving and processing network language data in real-time, ensuring the efficiency of data flow. The introduction of incremental learning mechanism enables the model to dynamically absorb new language features, and in the process of continuously inputting new data, the translation results can be continuously optimised. The experimental results show that the incremental learning model outperforms the traditional model in bilingual evaluation understudy (BLEU) score and accuracy, and significantly outperforms the traditional model in training time (5 hours) and average translation time (0.4 seconds).
  Keywords: incremental learning; network language; transformer model; real-time translation; intelligent translation system; system design; implementation.
  DOI: 10.1504/IJCEELL.2025.10075328
   
  

Special Issue on: OA Adaptive E-Learning Technologies and Experiences

• Open Access

  Analysis of factors influencing student learning experience in the blended online-offline smart education model ( Free Full-text Access )

  by Yuan Fang, Juan Hu 
  Abstract: Research on the influencing factors of students' learning experience in the blended online-offline smart education model is significant for optimising the allocation of educational resources and improving teaching effectiveness. In this study, first, 14 key factors were identified across five dimensions, including course environment, platform, and course design. Through expert inquiry, logical connections between factors were analysed, and an adjacency matrix was established. Next, the reachable matrix was calculated to reveal the hierarchical structure, defining the reachable set and antecedent set to extract factors hierarchically. Finally, an interpretive structural model was constructed to demonstrate the hierarchy and interactions among factors. Test results indicate that the proposed method maintains over 95% accuracy in analysing learning experience factors, with a factor weight stability index ranging between 0.97 and 0.99 and a fluctuation amplitude of only 0.02.
  Keywords: blended online and offline; smart education model; learning experience; analysis of influencing factors.
  DOI: 10.1504/IJCEELL.2025.10074576
   
  

Special Issue on: OA Smart and Continuing Education and Life-Long Learning

• Open Access

  Design of distance English translation teaching system based on digital multimedia intelligent equipment ( Free Full-text Access )

  by Fali Liang 
  Abstract: With the development of science and technology and network technology, the application of artificial intelligence technology, and the advent of the internet era, computer multimedia-assisted foreign language teaching technology has been continuously innovated and improved. First, suitable digital multimedia equipment, including large database software, mobile multimedia intelligent servers, and equipment that supports voice recognition and machine translation, are selected. The system realises interaction and resource sharing between students and teachers through computer networks and database management functions. At the same time, multi-language recognition technology, voice synchronisation translation equipment, and multimedia teaching software are used to support cross-border translation and remote video conferencing interfaces, realising flexible and traceable remote teaching. The results of this experiment show that in the post-test scores of the experimental group (Group M) and the control group (Group N), the average score of group M is 9.708, and the average score of group N is 8.74.
  Keywords: English translation teaching; digital multimedia; distance teaching; intelligent assistance; teaching and training.
  DOI: 10.1504/IJCEELL.2025.10074868
   
  

Special Issue on: Smart Education in the Digital Society

• A fuzzy evaluation of information resource management performance in higher education from the perspective of knowledge management  
  by Zhimin Zhao, Pei Niu 
  Abstract: In order to help universities better manage information resources and improve the quality of teaching and research, this paper conducts a fuzzy evaluation of the performance of educational information resource management in universities from the perspective of knowledge management. Firstly, analyse the knowledge transformation mode and design a performance evaluation index system; Secondly, Cronbach's Alpha was used to calculate the reliability of the indicators. Then, calculate the weight of the indicators and multiply the weight vector with the fuzzy relationship matrix to obtain the fuzzy evaluation result. The results show that the comprehensive evaluation values of educational information resource management performance in the three universities are 83.2691, 78.9212, and 82.3145, respectively, with evaluation levels of "excellent", "good", and "good", which is consistent with the evaluation of them by various sectors of society. This provides a reference for the development of educational information resource management in local universities.
  Keywords: Cronbach's alpha; fuzzy relation matrix; weight vector; fuzzy evaluation.
  DOI: 10.1504/IJCEELL.2025.10074086
   
  
• Evaluation system for the effectiveness of college English curriculum teaching reform based on DPSIR model  
  by Wei Lin 
  Abstract: In order to improve the effectiveness of college English curriculum teaching reform and ensure the scientific and objective nature of teaching evaluation, this paper proposes an evaluation system for the effectiveness of college English curriculum teaching reform based on the Driving Force Pressure State Impact Response (DPSIR) model. Principles for selecting evaluation indicators for the effectiveness of college English course teaching reform, constructing a preliminary evaluation system, and conducting reasonable assignment and quantitative analysis of expert questionnaires. Introduce the DPSIR model to classify indicators, determine indicator weights based on these criteria layers, use the TOPSIS model to calculate closeness, obtain the reform effectiveness rating standard, and evaluate the reform effectiveness indicators based on this. The experimental results show that the utilization efficiency of English teaching resources in this method is 99.8%, the highest evaluation accuracy can reach 99.5%, and the evaluation time varies from 1.5s to 6.2s, indicating that this method can improve the effectiveness evaluation of college English course teaching reform.
  Keywords: driving force pressure state impact response; DPSIR model;TOPSIS model; CIPP evaluation model; weight assignment.
  DOI: 10.1504/IJCEELL.2025.10074088
   
  
• Interactive physical education teaching and learning environment based on immersive VR Immersive VR  
  by Xiaoai Gao 
  Abstract: This study explores the development of an interactive physical education teaching and learning environment utilising immersive virtual reality (VR) technology. Firstly, the characteristics of an interactive physical education teaching environment under immersive VR are analysed. Secondly, by integrating the mathematical models of the high-pass acceleration channel, tilt coordination channel, and high-speed angular velocity channel, high-intensity acceleration, body tilt, and angular velocity changes are accurately simulated. Finally, with the support of immersive VR technology, real-time interaction between students and virtual scenes is achieved through layout calculation, lighting simulation, motion sensing interaction capture, pose tracking, collision detection, and viewpoint transformation. The test results show that the method proposed in this article can significantly increase the student interaction frequency, reaching up to 17 times per hour, and exhibits a significant advantage in the utilisation rate of teaching equipment.
  Keywords: immersive VR; interactive learning; physical education teaching;learning environment.
  DOI: 10.1504/IJCEELL.2025.10074089
   
  
• A method for detecting students concentration in online Chinese course learning based on deep learning  
  by Hang Liu 
  Abstract: There is a problem of poor detection effect in detecting student concentration during online Chinese course learning. Therefore, a deep learning-based method for detecting student concentration in online Chinese courses is designed in this paper. Firstly, the facial expression feature attributes of Chinese online learning students are determined, and the Gabor + LBP method is used to extract their facial expression features. Then, the AlphaPose algorithm is used to obtain the joint coordinates of Chinese online learning students and extract specific action detail features. Finally, convolutional blocks are introduced for student focus feature vector classification, and a deep learning-based focus detection model is constructed to output the detection results. The experimental results show that this proposed approach improves the accuracy of identifying students’ attentiveness in remote Mandarin learning. This method helps to more accurately grasp students’ learning status, thus providing strong support for optimising online Chinese course teaching strategies and improving teaching quality.
  Keywords: deep learning; Chinese courses; online learning; student focus; testing; spatial attention; fully connected layer.
  DOI: 10.1504/IJCEELL.2025.10074091
   
  
• Study on resource allocation of English multimedia network teaching for digital education reform  
  by Fan Yang, Luping Zhang 
  Abstract: This study developed an innovative method for allocating English multimedia network teaching resources to overcome limitations in traditional approaches, including poor validity, low matching accuracy, and process inefficiency. The proposed solution involved three key phases. First, teaching resources were collected and processed using Kalman filtering for noise reduction; subsequently, comprehensive feature extraction was performed through multi-task width learning; finally, user preferences were calculated via an interest model while resource matching was optimised using graph planning algorithms. The allocation model incorporated Pearson correlation coefficients to enhance precision. Experimental results demonstrated exceptional performance metrics: allocation validity approaching 100%, absolute matching error consistently below 0.2%, and allocation efficiency reaching 99%. These outcomes confirmed the methods significant improvement over conventional techniques, particularly in digital education reform. The systems robust performance stemmed from its integrated approach combining advanced filtering, comprehensive feature analysis, and intelligent matching algorithms, establishing a new performance benchmark for educational resource allocation systems in both accuracy and operational efficiency.
  Keywords: Kalman filter algorithm; allocation of teaching resources; width learning; user interest model; K-means algorithm.
  DOI: 10.1504/IJCEELL.2025.10074516
   
  
• Fuzzy comprehensive evaluation of MOOC English teaching quality based on improved entropy method  
  by Yifan Liang 
  Abstract: In the practical application of MOOC English teaching quality evaluation, the entropy method exhibits high sensitivity to the degree of data dispersion. Once the sample data presents a local concentration trend or is disturbed by extreme values, it will cause an imbalance in the allocation of indicator weights, ultimately undermining the evaluation accuracy. Therefore, a research on fuzzy comprehensive evaluation of MOOC English teaching quality based on improved entropy method is proposed. In this method, an evaluation index system is constructed for MOOC English teaching quality, and grey relational analysis is conducted to screen indicators. Then indicator data is collected, and outlier cleaning is performed to ensure data quality. Subsequently, with processed indicator data as input, the entropy method is used to determine indicator weights, and fuzzy comprehensive evaluation method is applied to improve indicator weights. Based on the determined indicator weights, the fuzzy comprehensive evaluation of MOOC English teaching quality is completed. The results show that this method can effectively determine key evaluation indicators, with a high sensitivity coefficient of 1.97, the highest evaluation accuracy of 0.98, and the highest evaluation time of 3.792 seconds, demonstrating a good evaluation performance.
  Keywords: MOOC English teaching; teaching quality evaluation; grey correlation analysis; entropy method; fuzzy comprehensive evaluation method.
  DOI: 10.1504/IJCEELL.2026.10074951
   
  
• Fuzzy evaluation of digital teaching quality of theoretical courses in application-oriented universities under AI empowerment  
  by Jian Xie, Dan Chu 
  Abstract: In order to overcome the limitations of low indicator precision, high weight calculation error rate, and low evaluation accuracy in traditional evaluation methods, a fuzzy evaluation method of digital teaching quality of theoretical courses in application-oriented universities under AI empowerment is proposed. This method involves the use of factor analysis to screen fuzzy evaluation indicators for teaching quality, construction of a fuzzy evaluation indicator system for teaching quality under AI empowerment, and application of the random forest algorithm to calculate indicator weights. The fuzzy evaluation results of the digital teaching quality of theoretical courses in application-oriented universities are obtained by integrating indicator weights and fuzzy comprehensive evaluation methods. The experimental results show that the proposed method achieves a minimum precision of 96.17% for teaching quality evaluation index, a minimum error rate of 3.15% for evaluation index weight calculation, and a quality evaluation accuracy above 93.3%, indicating high evaluation performance.
  Keywords: AI empowerment; application-oriented universities; theoretical courses; digitisation; teaching quality; fuzzy evaluation; random forest algorithm; fuzzy comprehensive evaluation.
  DOI: 10.1504/IJCEELL.2026.10075012
   
  
• The characteristics of MOOC learners online learning behaviour and learning performance evaluation  
  by Shan Li 
  Abstract: To accurately analyse and evaluate the online learning situation of MOOC learners, this article focuses on MOOC learners and proposes innovative evaluation methods. First, using techniques such as association feature extraction and adaptive mining, the online learning behaviour data of MOOC learners are collected. Second, by analysing in detail the behavioural data of course access, video learning, homework submission, and daily grades, the external performance characteristics of MOOC learners online learning behaviour can be quantitatively analysed. Finally, a multi-level fuzzy comprehensive evaluation method is used to construct a learning performance evaluation system, which quantitatively evaluates learning performance by setting evaluation factor sets, weight allocation, and comment sets. The test results show that the proposed method exhibits the highest feature analysis accuracy of 98% and performance evaluation accuracy of 95%.
  Keywords: MOOC learners; online learning behaviour; characteristic analysis; learning performance evaluation.
  DOI: 10.1504/IJCEELL.2026.10074952
   
  
• Evaluation of classroom teaching effectiveness empowered by AI teachers based on bat algorithm random forest classification  
  by Qingmei Lu, Junli Li, Yuan Gao 
  Abstract: The large amount and complex types of data empowered by AI teachers in classroom teaching result in evaluation outcomes that fail to accurately reflect teaching effectiveness. To address this, research is conducted on evaluating the effectiveness of AI teacher-empowered classroom teaching based on bat algorithm-optimised random forest classification. First, an evaluation index system for AI teacher-empowered classroom teaching effectiveness is constructed, covering multiple dimensions. Second, variance inflation factor and principal component analysis are employed to screen indicators, ensuring efficiency. Finally, a bat algorithm-optimised random forest classification model processes complex data to build an accurate and highly generalisable evaluation model for teaching effectiveness. Results indicate that the method achieves a mean square error below 0.2, a Spearman rank correlation coefficient exceeding 0.95, and an evaluation time of up to 3.75 seconds.
  Keywords: AI teacher empowering classroom; teaching effectiveness evaluation; random forest classification algorithm; bat algorithm.
  DOI: 10.1504/IJCEELL.2026.10074953
   
  
• Comprehensive management strategies of educational knowledge from the perspective of digital humanities  
  by Jianlei Zhang 
  Abstract: In order to overcome the limitations of low knowledge recommendation accuracy, low knowledge utilisation rate of, and high total management cost in traditional methods of comprehensive management of educational knowledge, a comprehensive management strategies method of educational knowledge from the perspective of digital humanities is proposed. Educational knowledge data are collected through web crawling technology, annotated using the GPT model, and then integrated with TransE model and collaborative filtering algorithm to achieve knowledge recommendation. After determining the recommended content of educational knowledge, comprehensive management strategies are designed for educational knowledge from multiple aspects such as constructing a comprehensive educational knowledge graph, strengthening knowledge sharing and communication, and promoting knowledge innovation and application. The case test results show that the accuracy of the proposed method for educational knowledge recommendation varies between 93.9% and 97.1%, with a maximum utilisation rate of 75.9%, and the total management cost is 2,163,100 yuan.
  Keywords: perspective of digital humanities; educational knowledge; comprehensive management strategies; GPT model; TransE model; collaborative filtering algorithm.
  DOI: 10.1504/IJCEELL.2026.10076067
   
  
• A quantitative evaluation of teaching quality in higher education institutions assisted by artificial intelligence  
  by Fanqi Meng 
  Abstract: A quantitative evaluation method for teaching quality in universities with the assistance of artificial intelligence is proposed to address the problems of large average absolute error and low accuracy of evaluation results in existing methods. Firstly, collect teaching data, including teacher basic information, course information, teaching arrangements, and student feedback, and perform data preprocessing. Extract data features from processed data and reduce the number of features through dimensionality reduction techniques. Secondly, construct a neural network evaluation model, determine the number of nodes in the input layer, hidden layer, and output layer, and select a linear function as the activation function. Finally, the learning rate and loss function of the model are dynamically adjusted, and the optimised neural network model is used to quantitatively evaluate the teaching quality of universities. The experimental results show that the evaluation results of this method are more accurate and reliable.
  Keywords: artificial intelligence; university teaching; quality evaluation; neural network; feature dimensionality reduction; L1 regularisation.
  DOI: 10.1504/IJCEELL.2026.10076068
   
  
• Analysis for the influencing factors of college students' mobile learning willingness in the context of English curriculum reform  
  by Lingyan Mao, Yuting Yan, Lin Luo 
  Abstract: In order to address the limitations of traditional analysis methods, including low coverage of influencing factors, low Cronbach’s alpha reliability, and long screening time, a method for analysing the influencing factors of college students’ mobile learning willingness in the context of English curriculum reform is proposed. Using the TPB model as a framework, the influencing factors of college students’ mobile learning willingness are screened from five perspectives: behavioural attitude, subjective norm, perceived behavioural control, behavioural intention, and actual behaviour. A multi-level linear model is used to comprehensively analyse the complex interaction relationships between these influencing factors, and the results indicates a significant positive correlation between these influencing factors and college students mobile learning willingness. The experimental results show that this method achieves as an influencing factor coverage rate of 92.3%94.6%, a Cronbach’s alpha reliability between 0.987 and 0.996, and a screening time always below 0.5 s.
  Keywords: English curriculum reform; mobile learning; TPB model; learning willingness; interaction relationships; analysis for the influencing factors.
  DOI: 10.1504/IJCEELL.2026.10076069
   
  
• A study on the impact of online peer evaluation on learners’ critical thinking  
  by Xuejiao Huang 
  Abstract: Critical thinking is one of the essential higher-order thinking skills for learners in higher education, and online peer assessment has been shown to effectively promote its development. However, the question of which mode of online peer assessment is most effective in fostering critical thinking remains unresolved. To address this gap, this study employed a quasi-experimental approach in the ‘Research Methods in Educational Technology’ course to examine the impact of different online peer assessment methods on learners’ critical thinking. Results indicate that, compared to real-name assessment, anonymous assessment contributes more to the development of learners’ critical thinking dispositions and skills. This improvement is specifically manifested in three implementation pathways: questioning and disagreeing, arguing and decision-making, and integrating and suggesting.
  Keywords: online learning; peer assessment; critical thinking; anonymous evaluation.
  DOI: 10.1504/IJCEELL.2026.10076070
   
  
• An evaluation method of ChatGPT intervention in online course teaching effectiveness based on principal component regression analysis  
  by Hui Wang, Haibin Wang, Shaomei Li 
  Abstract: In order to overcome the limitations of low recall rate and low accuracy of evaluation indicators in traditional online course teaching effectiveness evaluation methods, a new evaluation method of ChatGPT intervention in online course teaching effectiveness using principal component regression analysis is proposed. Principal component regression analysis is adopted to screen evaluation indicators to establish an evaluation index system for ChatGPT intervention in online course teaching effectiveness. The evaluation index data is clustered using Gaussian mixture model, and then input into RBF neural network to obtain the evaluation results of ChatGPT intervention in online course teaching effectiveness. The experimental results show that the proposed method achieves a maximum recall rate of 98.74% in evaluation indicates, a minimum screening time of 1.28 seconds, and evaluation accuracy ranging from 63.8% to 85.8%.
  Keywords: principal component regression analysis; ChatGPT intervention; online course; teaching effectiveness evaluation; Gaussian mixture model; GMM; RBF neural network.
  DOI: 10.1504/IJCEELL.2026.10076071
   
  
• Empirical study on learning behaviour intention under college curriculum reform based on technology acceptance model  
  by Shudong He, Baole Huang, Long Li 
  Abstract: To address the issues of low accuracy and poor compatibility in empirical research on learning behaviour intention under curriculum reform, a method for empirical research on learning behaviour intention is designed based on the technology acceptance model (TAM). Firstly, the TAM theoretical framework was constructed to clarify the key elements in the model. Then, a questionnaire was designed to measure the actual performance of research variables among learners and research hypotheses were proposed accordingly. Finally, a reliability and validity analysis was conducted on the questionnaire, and Pearson correlation coefficient and regression analysis were used to verify the research hypothesis, thus clarifying the causal and quantitative relationship between the independent variable and the dependent variable (learning behaviour intention). Experimental results demonstrate that the accuracy and compatibility of TAM-based model proposed in this study consistently remain above 90% in empirical study of learning behavioural intentions under curriculum reform. Empirical research reveals high accuracy and compatibility, along with good efficiency in studying learning behaviour willingness.
  Keywords: curriculum reform; technology acceptance model; TAM; learning behaviour intention; regression analysis.
  DOI: 10.1504/IJCEELL.2026.10076072