Learner Model Research Articles

Factors Influencing the Satisfaction of Second Language Learners of Chinese in Online Courses.

The study aims to investigate the relationship among the key factors affecting second language learners' satisfaction with online Chinese courses and their willingness to continue utilizing them by constructing a Model of Chinese Learners' Satisfaction in Online Courses. Additionally, the influence of participants' individual differences was also explored. A total of 203 second language learners of Chinese participated in the questionnaire survey, with 5 learners further participating in interviews. Learner expectations, learner perceived quality, and learner perceived value were identified as important factors influencing learner satisfaction and willingness to continue using the online course. The results of the questionnaire survey showed that (1) learner individual differences, such as age, Chinese proficiency, weekly study duration, and offline Chinese course experience, significantly influence learner satisfaction. (2) Learner expectations have a significant positive impact on perceived quality, while perceived quality positively affects perceived value. (3) Learner satisfaction significantly influences the willingness to continue using online courses. (4) The results of the interview revealed that most learners still prefer traditional offline courses, indicating that online teaching has several shortcomings and deficiencies. Overall, this study provides some scientific and reasonable decision-making references for improving online teaching methods, aiming to enhance learner satisfaction and promote the development of online education.

Enhancing the exploitation of natural resources for green energy: An application of LSTM-based meta-model for aluminum prices forecasting

Efficient resource allocation for electric car production can be achieved by anticipating aluminum future pricing. For the electric car sector to maintain a steady supply chain, efficient production, and long-term growth, accurate forecasts are essential for policymakers to plan resource policies. The accuracy of ensemble learning models in predicting Aluminum prices was analyzed using Gene Expression programming and long short-term memory (LSTM) method. The analysis was based on monthly frequency spot settlement price data of Aluminum, copper, silver, and crude oil prices, as well as currency inflation rates of USA, China, and Peru. The study period spanned from January 1, 1994 to December 31, 2022, and also included the gross domestic product (GDP) of USA, China, and other metal minerals. Initially, we assess the level of multicollinearity between each chosen input parameter and Aluminum price volatility using Variance inflation factor-based multicollinearity. The primary innovation of this study lies in the creation of a highly precise model that utilizes the LSTM algorithm to estimate monthly Aluminum prices. This model serves as a revolutionary forecasting method. An extensive evaluation of various ensemble learning models reveals that XGBoost is the optimal model for accurately forecasting monthly Aluminum prices. The LSTM-based recurrent neural network model exhibited the lowest error, with a Mean Relative Error (MRE) ranging from 0.001 to 0.008, RMSE ranging from 54.527 to 136.044, and R2 ranging from 0.95 to 0.983. The findings demonstrated that the LSTM-based super learner models had superior performance compared to the CatBoost, LightBoost, Random Forest, XGBoost, and AdaBoost models, as evidenced by higher values of the determination coefficient (R2), value account for (VAF), and other 10 error analysis evaluators. Therefore, the utilization of an LSTM-based super learner model can serve as a dependable approach for forecasting future monthly Aluminum prices. In addition, this study introduces a logical mathematical model utilizing gene expression programming (GEP) to anticipate future Aluminum prices, which can be utilized by other researchers. Thus, we conclude that both the GEP and ensemble learning models, particularly the LSTM-based Super learner model, are appropriate for precise metal price predictions, which can benefit policymakers and assist in resource policy planning.

Environmental risk score of multiple pollutants for kidney damage among residents in vulnerable areas by occupational chemical exposure in Korea

This study aimed to develop an environmental risk score (ERS) of multiple pollutants (MP) causing kidney damage (KD) in Korean residents near abandoned metal mines or smelters and evaluate the association between ERS and KD by a history of occupational chemical exposure (OCE). Exposure to MP, consisting of nine metals, four polycyclic aromatic hydrocarbons, and four volatile organic compounds, was measured as urinary metabolites. The study participants were recruited from the Forensic Research via Omics Markers (FROM) study (n = 256). Beta-2-microglobulin (β2-MG), N-acetyl-β-D-glucosaminidase (NAG), and estimated glomerular filtration rate (eGFR) were used as biomarkers of KD. Bayesian kernel machine regression (BKMR) was selected as the optimal ERS model with the best performance and stability of the predicted effect size among the elastic net, adaptive elastic net, weighted quantile sum regression, BKMR, Bayesian additive regression tree, and super learner model. Variable importance was estimated to evaluate the effects of metabolites on KD. When stratified with the history of OCE after adjusting for several confounding factors, the risks for KD were higher in the OCE group than those in the non-OCE group; the odds ratio (OR; 95% CI) for ERS in non-OCE and OCE groups were 2.97 (2.19, 4.02) and 6.43 (2.85, 14.5) for β2-MG, 1.37 (1.01, 1.86) and 4.16 (1.85, 9.39) for NAG, and 4.57 (3.37, 6.19) and 6.44 (2.85, 14.5) for eGFR, respectively. We found that the ERS stratified history of OCE was the most suitable for evaluating the association between MP and KD, and the risks were higher in the OCE group than those in the non-OCE group.

Design of Personalized Recommendation System for College Education Based on Multivariate Hybrid Criteria Fuzzy Algorithm

The learner model's design is a most important aspect of a personalized college student education recommendation system. Currently, most learner models need more scientific focus, relying on a single method to collect dimensions and feature attributes with low computing costs. Hence, this paper introduced a Multivariate Hybrid Criteria Fuzzy Algorithm (MHCFA) for personalized college education recommendation. The MHCFA is trained by Social Feedback Artificial Tree (SFAT), where SFAT is the combination of Social Optimization Algorithm (SOA) and Feedback Artificial Tree (FAT). In addition, Deep Fuzzy Clustering (DFC) is utilized to group college education content. The RV-Coefficient is employed to select the best content. Moreover, the feature is extracted by All Caps and numerical for further personalized recommendations. In addition, the test results show that SFAT_MHCFA performs better in Precision, Recall, and F-Measure where the values gained 0.989, 0.878, and 0.859, respectively.

Enhancing Diabetes Prediction Accuracy through Hybrid Machine Learning Models: A Comparative Study

This study investigates the effectiveness of various machine learning (ML) models in predicting the onset of diabetes, emphasizing the superior performance of hybrid models over single learner models. Employing a dataset comprising 10,000 individuals with features like Glucose level, BMI, Insulin, and more, we meticulously processed and engineered the data to optimize it for ML applications. We developed several models, including Decision Trees, Random Forest, KNN, and XGBoost, and then advanced to hybrid models using ensemble techniques like stacking and soft voting classifiers. Our findings indicate that hybrid models significantly outperform single learner models. These models achieved remarkable accuracy (98.11%), precision (97.31%), and ROC AUC (99.82%), highlighting their potential in clinical settings. The study underscores the value of hybrid ML models in enhancing predictive accuracy and reliability in diabetes diagnostics.

Research on the Construction and Application of an Intelligent Education Learner Model Based on the UTAUT Theory

With the rapid development of computer technology, a new educational model, the innovative education learner model, has emerged as a product of the deep integration of technology and education. In this paper, we will begin by organizing the theories and models related to technology acceptance. We will select the UTAUT model, known for its high explanatory power, as the theoretical framework. Subsequently, we will comprehensively analyze the dataset and conduct in-depth habit mining. The effectiveness of applying K-means concepts to address the classification of clusters of learners’ learning habits is confirmed. The feasibility of the LSTM algorithm in predicting learners for exercise responses is also demonstrated. Next, a learning cluster construction method based on intelligent learner clustering is proposed. The methods of MDS+K-means and spectral clustering are selected for clustering. Learning clusters are constructed, and the performance of the two types of algorithms is compared and analyzed. Finally, the enhanced text feature extraction algorithm is utilized to design and implement the corresponding system for the practical application of the innovative educational learner model. The final experiment proves that the text features extracted by the model are effective, with an error rate of only about 2.8%, thus demonstrating that the intelligent educational learning model in this paper is reasonable.

A Theoretical Foundation to Inform the Implementation of Precision Education and Assessment.

Precision education (PE) uses personalized educational interventions to empower trainees and improve learning outcomes. While PE has the potential to represent a paradigm shift in medical education, a theoretical foundation to guide the effective implementation of PE strategies has not yet been described. Here, the authors introduce a theoretical foundation for the implementation of PE, integrating key learning theories with the digital tools that allow them to be operationalized. Specifically, the authors describe how the master adaptive learner (MAL) model, transformative learning theory, and self-determination theory can be harnessed in conjunction with nudge strategies and audit and feedback dashboards to drive learning and meaningful behavior change. The authors also provide practical examples of these theories and tools in action by describing precision interventions already in use at one academic medical center, concretizing PE's potential in the current clinical environment. These examples illustrate how a firm theoretical grounding allows educators to most effectively tailor PE interventions to fit individual learners' needs and goals, facilitating efficient learning and ultimately improving patient and health system outcomes.

A Toolbox for Modelling Engagement with Educational Videos

With the advancement and utility of Artificial Intelligence (AI), personalising education to a global population could be a cornerstone of new educational systems in the future. This work presents the PEEKC dataset and the TrueLearn Python library, which contains a dataset and a series of online learner state models that are essential to facilitate research on learner engagement modelling. TrueLearn family of models was designed following the "open learner" concept, using humanly-intuitive user representations. This family of scalable, online models also help end-users visualise the learner models, which may in the future facilitate user interaction with their models/recommenders. The extensive documentation and coding examples make the library highly accessible to both machine learning developers and educational data mining and learning analytics practitioners. The experiments show the utility of both the dataset and the library with predictive performance significantly exceeding comparative baseline models. The dataset contains a large amount of AI-related educational videos, which are of interest for building and validating AI-specific educational recommenders.

Stochastic configuration networks with CPU-GPU implementation for large-scale data analytics

Stochastic configuration networks (SCNs) are a class of randomized learner models that have garnered increasing attention in data analytics. In the original implementation of SCN, the pseudo-inverse of the hidden layer output matrix is used to evaluate output weights. However, it is quite challenging to compute the pseudo-inverse of the hidden layer output matrices for large-scale datasets with high complexity, which occurs in many real-world applications. This paper aims to accelerate the learning process of SCNs by employing the well-known alternating direction method of multipliers (ADMM) solver and CPU-GPU heterogeneous computing technique. Empirical results on two benchmark datasets demonstrate the efficiency and effectiveness of the proposed method for large-scale data analytics.

Performance comparison of machine learning models used for predicting subclinical mastitis in dairy cows: Bagging, boosting, stacking, and super-learner ensembles versus single machine learning models

Mastitis has a substantial impact on the dairy industry across the world, causing dairy producers to suffer losses due to the reduced quality and quantity of produced milk. A further problem, related to this issue, is the excessive use of antibiotics that leads to the development of resistance in different bacterial strains. The growing consumer awareness oriented toward food safety and rational use of antibiotics has promoted the search for new methods of early identification of cows that may be at risk of developing the disease. Subclinical mastitis does not cause any visible changes to the udder or milk, and therefore it is more difficult to detect than clinical mastitis. The collection of large amounts of data related to milk performance of cows allows using machine learning (ML) methods to build models that could be used for classifying cows into healthy and at risk of subclinical mastitis. The data used for the purpose of this study included information from routine milk recording procedures. The data set consisted of 19,856 records of 2,227 Polish Holstein-Friesian cows from 3 herds. The authors decided to use the approach of building ensemble ML models, in particular bagging, boosting, stacking and super learner models, and comparing them for accuracy of identification of disease-affected cows against single ML models based on the Support Vector Machines, Logistic Regression, Gaussian Naïve Bayes, k-Nearest Neighbors and Decision Tree algorithms. The models were trained and evaluated based on the information recorded for herd 1 and using an 80:20 train-test split ratio according to animal ID (to avoid data leakage). The information recorded for herds 2 and 3 was only used to evaluate on unseen data models developed using the herd 1 data set. Among the single ML models, the Support Vector Machines model was found to be the most accurate in predicting subclinical mastitis at subsequent test-day when used both for the training set (mean F1-score of 0.760) and the testing sets containing data for herds 1, 2 and 3 (F1-score of 0.778, 0.790 and 0.741 respectively). The Gradient Boosting model was found to be the best performing model among the ensemble ML models (F1-score of 0.762, 0.779, 0.791 and 0.723 for the training set and the testing sets respectively). The super learner model, featuring the most advanced design and Logistic Regression in the meta layer, achieved the highest mean F1-score of 0.775 during the cross-validation, however, it was characterized by a slightly worse prediction accuracy of the testing sets (mean F1-score of 0.768, 0.790 and 0.693 for herds 1, 2 and 3 respectively). The study findings confirm the promising role of ensemble ML methods that were found to be slightly superior with respect to most of the single ML models.

What the experts see: A qualitative analysis of the behaviors of master adaptive learners in emergency medicine.

The Master Adaptive Learner (MAL) model postulates that learners develop adaptive expertise through cycles of self-regulated learning. Despite a robust theoretical basis, the actual observable behaviors of MALs are not well characterized. We sought to define behaviors that characterize MALs within emergency medicine (EM) training. Using a constructivist grounded theory approach, we analyzed semistructured interviews with expert EM educators. These experts reflected on observable behaviors as well as factors in the clinical learning environment that may modulate these behaviors. We recruited using purposive sampling until thematic saturation. We identified four overall themes, of which three described groups of learner behaviors and a fourth described modifiers of these behaviors. Learner behaviors include: (1) critical interrogation of practice, (2) intellectual risk-taking, and (3) intentional curation of a learning network. Critical interrogation of practice encompasses several observable behaviors including learner-driven feedback conversations, independent synthesis of clinical information, appropriate deviation from algorithms based on their conceptual understanding of core principles, intentional use of case variation and hypothetical questioning, and continuous refinement of decisions. MALs also engage in intellectual risk-taking for their development by communicating clinical decision-making processes even at the risk of being wrong, openly addressing errors and gaps, and intentionally seeking out uncomfortable experiences. Intentional curation of a learning network is the deliberate development of a consortium of trusted individuals who serve as mentors and sounding boards. We also identified a fourth theme related to the expression of learner behaviors: learning environment modulates behaviors. Active promotion of psychological safety is necessary for learners to express these behaviors. This safety is mediated through trusting relationships and expert supervisors who serve as colearners and role models. We present several behaviors that allow identification of MALs among EM trainees. These data expand our understanding of MALs and the critical influence of the learning environment. Identification of these behaviors may allow for more precise categorization of targeted curricular interventions and meaningful learning outcomes.

Collaborative Optimization of Learning Team Formation Based on Multidimensional Characteristics and Constraints Modeling: A Team Leader-Centered Approach via E-CARGO

With the massive popularization of e-learning, collaborative learning via learning teams has become indispensable to enhancing the learning efficiency and learning quality of overall learners. The team leader usually plays a key role in collaborative learning. However, the existing research ignores the key characteristics of learners and constraints relevant to e-learners when identifying appropriate team leaders and compatible members. A novel collaborative optimization approach to learning team formation is proposed based on a refined learner model and the environments—classes, agents, roles, groups, and objects (E-CARGO) model. With the proposed approach, a learner is modeled by combining 5-D characteristics (i.e., cognitive ability, leadership, sociability, learning style, and personality) and three types of constraints (e.g., conflicts, genders, and the number of members), and an assessment mechanism is designed to measure the comprehensive abilities of learners for identifying an ideal team leader and selecting the team members for a team. By innovatively introducing the role-based collaboration theory and E-CARGO model, the leader-centered learning team formation problem is formalized as a collaborative optimization problem. The mathematical model and the constraint relations are established for this problem, which is solved based on the IBM CPLEX package. Finally, a case study and experiments demonstrate that the proposed approach is efficient and feasible, in favor of improving the satisfaction degree of learners.

Biogas Production Prediction Based on Feature Selection and Ensemble Learning

The allocation of biogas between power generation and heat supply in traditional kitchen waste power generation system is unreasonable; for this reason, a biogas prediction method based on feature selection and heterogeneous model integration learning is proposed for biogas production predictions. Firstly, the working principle of the biogas generation system based on kitchen waste is analyzed, the relationship between system features and biogas production is mined, and the important features are extracted. Secondly, the prediction performance of different individual learner models is comprehensively analyzed, and the training set is divided to reduce the risk of overfitting by combining K-fold cross-validation. Finally, different primary learners and meta learners are selected according to the prediction error and diversity index, and different learners are fused to construct the stacking ensemble learning model with a two-layer structure. The experimental results show that the research method has a higher prediction accuracy in predicting biogas production, which provides supporting data for the economic planning of kitchen waste power generation systems.

A Novel Personalized Learning Path Mining Based on Steiner Tree and Knowledge Graph

Modern society has accumulated great amounts of knowledge since human start learning and communicating. With knowledge’s continuously thriving and getting refined, knowledge itself has developed into a complex system with a huge number of content and structure features. Together with the development of science and technology, the ways of people learning have been changed greatly. Under the pressure of high-paced life and workplace competition, more and more people are in demand of personalized learning paths, in order to achieve their learning target as fast as possible. A personized and scientific learning path is the key to effective learning grogram. However, studies on algorithms of optimal learning path discovery are not comprehensively developed, especially on its performance and application. Therefore, in this article, we propose a new algorithm, Portfolio ST, which is improved from Steiner Tree, for personalized and optimal learning path mining. At first, this paper constructs the knowledge graph of finance, then builds learner models by profiling learners’ owned and aimed knowledge based on the knowledge network. At last, according to the knowledge structure of a person’s learner model, the most personized and shortest learning path is calculated by the Portfolio ST. After the experiment compared with two baseline algorithms, the Portfolio ST algorithm is proved to have the best performance and scalability, by changing owned/aimed/overall knowledge respectively, which is also the best algorithm of learning path mining that can achieve the global optimal among these three algorithms.

Research on individualized Chinese teaching based on adaptive learning system

Language teaching in the smart education environment pays more attention to the personalised needs of learners, and adaptive learning systems can provide technical support to meet students’ learning needs and realise personalised learning. Based on the principle of teaching according to the student’s ability, this paper conducts research on adaptive learning systems, describes the construction ideas and practical application methods of the four panel models (i.e., domain model, learner model, cognitive diagnosis, and adaptive model) in adaptive learning systems in language teaching, and puts forward relevant suggestions on language teaching strategies against the background of the current language teaching and educational needs.

The Application of Multiple Music Cultures in College Music Teaching in the Background of Internet

Abstract In advancing quality education, there is a pressing necessity to equip students in higher education with global perspectives and skills in intercultural communication. This study leverages the TSPCK knowledge transformation model to deliver an extensive exploration and application in the realms of goal orientation, content structuring, foundational learning, strategy deployment, and the execution of assessments within the framework of multicultural music education. The adaptive learning system’s learner model is meticulously crafted by assessing learners’ preliminary knowledge, evaluating their challenges with music knowledge, and estimating their overall knowledge proficiency, with validation conducted across six distinct datasets. Multicultural elements in college music education are strategically utilized to investigate their influence on students’ aesthetic interests and musical literacy. Empirical results indicate a residual mean score of 2.0501 for music aesthetic literacy within a multicultural context, suggesting that exposure to multicultural music education broadens students’ perspectives significantly. Furthermore, this educational approach encourages students to cultivate a deeper appreciation and respect for the nuances and commonalities across various cultures. Enhancing the quality of music education in tertiary institutions and promoting a profound understanding and proficiency in diverse music cultures are identified as pivotal elements in achieving these educational outcomes.

Factors influencing global citizenship competencies: A structural equation model of adult learners in Taiwan

Compared to formal education, adult education is one of the most crucial systems for social education and lifelong learning. This paper examines learners' global citizenship competencies and analyzes the influence of demographic variables. Moreover, this article employs structural equation modeling by developing a survey instrument to measure global citizenship competence. The researchers sampled learners from community colleges in Taiwan, distributing 1,400 paper questionnaires, and receiving 1,280 responses. Research findings are: (1) Adult learners' performance in global citizenship competencies is uneven. Participation in multiculturalism, economic phenomena, and political organizations needs to be more advanced. (2) Adult learners' global citizenship competencies were significantly affected by demographic variables such as educational attainment, occupation, monthly personal income, and in an urban or rural area. (3) Results showed that the structural equation modeling is appropriate and has good explanatory power. Implications and suggestions are given at the end.

Research on the Language Acquisition Model of Non-Native English Learners Based on Artificial Intelligence

Abstract The widest application field of intelligent teaching supported by artificial intelligence technology is language learning, and enhancing learners’ language acquisition ability is the top priority. On the basis of analyzing the guidelines for the construction of a language acquisition model for non-native English learners, this paper combs through the main advantages of intelligent technology-assisted English teaching and establishes an intelligent language acquisition model based on artificial intelligence. Fuzzy cognitive diagnosis of the language acquisition level of non-native English learners is carried out using the Fuzzy-CDF model, the language acquisition ability of learners is modeled, and the regression model is constructed by combining with artificial intelligence technology so as to realize the bidirectional assessment of language acquisition level of learners. When the Fuzzy-CDF model is utilized for the learner’s language acquisition level, its MAE value is the lowest at 0.1385, and the influence coefficient of the teacher’s teaching method on the learner’s language acquisition ability is the largest at 23.506. The difference between the learner’s language acquisition response time at different levels on the experimental example sentences and the native learners is small, and close to 90% of the students indicated that they were more satisfied with the intelligent language acquisition model. Relying on artificial intelligence technology to construct intelligent language acquisition models can help non-native English learners improve their language acquisition ability.

A study on the application of quantum computing in improving the efficiency of English language learning

Abstract The rapid development of information technology has brought new opportunities to the field of language learning and formed new learning methods. In this paper, a content-based quantum recommendation algorithm is first proposed to calculate the preference attributes of English learners using the Hamming distance and then combined with the constructed dynamic interest model of learners to complete the personalized recommendation of English language learning resources. The algorithm is employed to build an English-language customized learning system that incorporates learning, resource management, and proficiency assessment functions, and performance testing is carried out simultaneously. Furthermore, the study utilizes the system to conduct application experiments to evaluate its improvement in English language learning efficiency. The results showed that the mean value of perceived satisfaction with the improvement of English language efficiency in classes using the system was 7.48, and the ANOVA results (F=3.88, p<0.5) indicated a significant difference from the traditional method. Among them, the performance enhancement rates of superior and intermediate students were more than 45% and 62%, respectively, which effectively enhanced the efficiency of English language learning. After this study, it can provide a high reference value for the application of quantum machine algorithms in the field of education.

Applying artificial intelligence in teaching music for primary education students at Tan Trao University

Artificial Intelligence (AI) is driving broader and deeper changes in higher education. The application of AI in university teaching includes learner data collection, building learner models, constructing domain knowledge models, and developing teaching models. However, there are still some challenges in applying AI in teaching higher education, primarily concerning the understanding of the relationship between AI and humans, establishing educational goals in AI applications, and ensuring data safety and risks. The article is based on the theory of music teaching and the results of applying AI in teaching to highlight the current situation of music education for primary education students at Tan Trao University. Through an analysis of the current situation, we propose five solutions to apply AI in music education and organize pedagogical experiments to verify feasibility, with the aim of innovating teaching methods and enhancing teaching quality.