Personalized Resource Research Articles

Students’ Perceptions and Use of AI in MLIS Courses

Artificial intelligence (AI) has been a buzzword on the Internet due to the development of ChatGPT. AI, especially generative AI, can create original text, audio, and images in response to users’ questions and needs. These programs have the potential to enhance students’ learning and creativity if used ethically. Especially for graduate students in the library and information science (LIS), AI can be used to help students outline essays or produce creative content (e.g., videos, slides, visual presentations) that mimic human intelligence and creativity. However, considering this is yet new technology, research needs to be done to understand how students perceive and use AI ethically in their coursework and research in higher education settings. Specifically, this study aims to explore students’ views on the ethical implications of AI in LIS research and class assignments in a course in the Master of Library and Information Studies (MLIS) program at a university and gather students’ perspectives on its responsible or irresponsible utilization. Content analysis of students’ online discussions revealed that students perceived that AI could enhance educational efficiency, foster creativity, and provide technical support. Students found AI helpful in personalized learning experiences, resource access, streamlining tasks, and critical thinking and problem-solving. However, they had concerns about incorrect citation, copyright, plagiarism, bias, misinformation, privacy, and the risk of diminished creativity. This inquiry will contribute to gaining insights into how to help MLIS students prepare with ethical understanding and use of AI for their professional activities.

Leveraging ICT and Generative AI in Higher Education for Sustainable Development: The Case of a Lebanese Private University

This study investigates the interaction of information and communication technology (ICT) and higher education in driving sustainable development, with a special emphasis on the rising significance of generative AI tools such as ChatGPT. This quantitative study, conducted in a Lebanese private university, looks into the impact of ICT, specifically generative AI, on promoting sustainability in higher education. A questionnaire was distributed to university instructors to determine how these technologies contribute to sustainable practices in academic environments. The results, which were evaluated using descriptive statistics and correlation analysis, show that ICT tools, professional instructor development, and the upkeep of educational infrastructure all contribute considerably to Lebanon’s sustainable development. Furthermore, integrating generative AI into educational processes has the potential to improve personalized learning, resource efficiency, and content production, all of which contribute to sustainability goals. The study concludes by exploring the findings’ broader implications, acknowledging their shortcomings, and suggesting future research possibilities.

Re-Evaluating Components of Classical Educational Theories in AI-Enhanced Learning: An Empirical Study on Student Engagement

The primary goal of this research was to empirically identify and validate the factors influencing student engagement in a learning environment where AI-based chat tools, such as ChatGPT or other large language models (LLMs), are intensively integrated into the curriculum and teaching–learning process. Traditional educational theories provide a robust framework for understanding diverse dimensions of student engagement, but the integration of AI-based tools offers new personalized learning experiences, immediate feedback, and resource accessibility that necessitate a contemporary exploration of these foundational concepts. Exploratory Factor Analysis (EFA) was utilized to uncover the underlying factor structure within a large set of variables, and Confirmatory Factor Analysis (CFA) was employed to verify the factor structure identified by EFA. Four new factors have been identified: “Academic Self-Efficacy and Preparedness”, “Autonomy and Resource Utilization”, “Interest and Engagement”, and “Self-Regulation and Goal Setting.” Based on these factors, a new engagement measuring scale has been developed to comprehensively assess student engagement in AI-enhanced learning environments.

A knowledge graph algorithm enabled deep recommendation system.

Personalized learning resource recommendations may help resolve the difficulties of online education that include learning mazes and information overload. However, existing personalized learning resource recommendation algorithms have shortcomings such as low accuracy and low efficiency. This study proposes a deep recommendation system algorithm based on a knowledge graph (D-KGR) that includes four data processing units. These units are the recommendation unit (RS unit), the knowledge graph feature representation unit (KGE unit), the cross compression unit (CC unit), and the feature extraction unit (FE unit). This model integrates technologies including the knowledge graph, deep learning, neural network, and data mining. It introduces cross compression in the feature learning process of the knowledge graph and predicts user attributes. Multimodal technology is used to optimize the process of project attribute processing; text type attributes, multivalued type attributes, and other type attributes are processed separately to reconstruct the knowledge graph. A convolutional neural network algorithm is introduced in the reconstruction process to optimize the data feature qualities. Experimental analysis was conducted from two aspects of algorithm efficiency and accuracy, and the particle swarm optimization, neural network, and knowledge graph algorithms were compared. Several tests showed that the deep recommendation system algorithm had obvious advantages when the number of learning resources and users exceeded 1,000. It has the ability to integrate systems such as the particle swarm optimization iterative classification, neural network intelligent simulation, and low resource consumption. It can quickly process massive amounts of information data, reduce algorithm complexity and requires less time and had lower costs. Our algorithm also has better efficiency and accuracy.

Precision medicine for papillary thyroid carcinoma (PTC) variants: A machine learning approach to prognosis and treatment guidance.

e18072 Background: PTC is a common endocrine cancer with a good prognosis, but aggressive subtypes, such as Hürthle cell (HCC) and columnar cell variants (CCV), pose challenges due to their higher recurrence and metastasis rates. To provide personalized care, we applied machine learning to evaluate the treatment effectiveness and develop precise prognostic models for PTC variants. Methods: The Surveillance, Epidemiology, and End Results (SEER) database provided the data used for this study’s analysis (2000–2019). Patients who met any of the following criteria were excluded: diagnosis not confirmed by histology, previous history of cancer or with other concurrent malignancies, and unknown data. To identify prognostic variables, we conducted Cox regression analysis and constructed prognostic models using machine learning (ML) algorithms to predict the 5-year survival. Patient records were randomly divided into training (70 %) and validation (30 %) sets. A validation method incorporating the area under the curve (AUC) of the receiver operating characteristic curve was used to validate the accuracy and reliability of the ML models. Results: The study population comprised 3690 patients. Among them 3180 patients with CCV and 510 patients with HCC, respectively. Most patients (62.8%) were 45 years or older, with a median age of 52 years. A total of 56.9% of patients had a tumor size greater than 2 cm, with a median tumor size of 3.1 cm. The largest racial group was white, comprising 83.8% of the cases, and 11.8% of the cases were Asian. Most cases were regional (53.4%, n=1969), followed by localized (38.3%, n= 1413). Multivariate Cox regression analysis revealed that N1 negatively affected the survival of HCC patients. CCV has a favorable prognosis after surgery, radiotherapy, or total thyroidectomy. Poor prognosis in CCV is associated with black race, large tumor size, and T4 stage. Improved survival in the localized/regional stage and decreased survival with male sex, older age, distant metastasis, and advanced AJCC stage in both PTC subtypes. ML models revealed that the random forest classifier (RFC) and K-Nearest Neighbors (KNN) accurately predicted outcomes, followed by Logistic Regression (LR) models. The highest contributing factors were AJCC staging, tumor size, and T aspect of TNM staging. Conclusions: Our study offers a method for evaluating and treating patients with PTC variants. The machine learning model that we created serves as a useful and personalized resource to aid in clinical decision-making processes.[Table: see text]

Application Analysis of English Personalized Learning Based on Large-scale Open Network Courses

In the context of Big data, large-scale open online courses increase learning paths for learners, but in the face of countless high-quality curriculum resources, it is easy for derivative learners to face the dilemma of rich curriculum resources but difficult to choose resources, which leads to information maze for learners. How to help learners quickly and accurately find their own learning resources in the explosive growth of MOOC resources is an urgent problem in the field of education Big data. However, the traditional Collaborative filtering recommendation technology does not perform well when dealing with sparse data and cold start. The recommendation content is repeated and can not effectively deal with high-dimensional and nonlinear data of online learning users, resulting in low efficiency of resource recommendation. Therefore, the study adopts a deep belief network (DBN) to construct a personalized resource recommendation model. The model combines the learner behavior characteristics with the curriculum resource content attribute characteristics to form the learner feature vector. The parameters of the model are adjusted according to the characteristics of learners. Through experiments, the proposed model has shown good performance. The experiment explored the effects of training set size, learner characteristics, and GPU on model performance. The experimental results show that when the training set proportion is 100%, the RMSE, Accuracy, Recall, and F1 values of the model are 0.76, 0.946, 0.957, and 0.951, respectively. When the model is trained using a training set containing learner features, the RMSE, Accuracy, Recall, and F1 values of the model are 0.75, 0.962, 0.908, and 0.958, respectively. After using GPU to accelerate the model, the running time of the model decreased from 360 minutes to 90 minutes. The results indicate that the model cannot effectively mine data information when the degree of correlation between sample information is low. The richer the relationships between samples, the better the performance of the model. Simultaneously learning hunger feature vectors and learner behavior feature vectors for training can significantly improve the recommendation accuracy of the model. The main contribution of this study is to propose a recommendation method based on DBN classification to replace traditional similarity calculation methods, using DBN's efficient feature abstraction and feature extraction capabilities to fully explore learners' interest and preference for course resources. In addition, in view of the common problems of cold start and data sparsity in traditional Collaborative filtering recommendation methods, the research deeply mines the characteristics of learners' Demographics and curriculum resources' content attributes, and constructs a learner interest model based on DBN combined with learners' behavior characteristics, which effectively solves the problems of cold start and data sparsity, as well as the inaccurate expression of learners' interest preferences for curriculum resources.

Application and practice of personalized education based on big data analysis in Java object-oriented program design

This paper delves into the application and practice of personalized education based on big data analysis in the teaching of Java object-oriented programming. By constructing a big data analysis model, we have achieved precise collection and processing of student learning data, thereby tailoring personalized learning paths and resource recommendations for each student. The aim of this paper is to analyze the implementation effects of this innovative educational model in the teaching of Java object-oriented programming, with the hope of providing valuable insights for improving teaching quality and student learning outcomes. Furthermore, we also explore the advantages of applying Java object-oriented programming in personalized education. The object-oriented nature of Java makes program design more aligned with human thinking patterns, aiding in the development of students' logical thinking and innovative capabilities. Additionally, the widespread use of the Java language also offers expansive opportunities for students' future career development.

Research on the Optimization of English Teaching Content in Colleges and Universities by Combining Decision Tree and Big Data Technology

Abstract English teaching in colleges and universities is facing the growth of personalized teaching demand, and the traditional education model is challenging to meet the diverse learning needs of students. Big data and decision tree technology provide a new way for teaching content optimization, which can achieve a high degree of matching between educational resources and students’ needs, and improve teaching effectiveness and learning efficiency. This study explores the application of decision trees and big data technology in optimizing English teaching content in colleges and universities. By constructing an ontology tree model of learning resources and adopting similarity calculation and personalized recommendation algorithms, the study achieves personalized learning resource recommendations for students. The study utilizes comparative experimental methods to analyze achievement changes between the experimental and control classes after customized learning. The personalized teaching program’s effectiveness can be confirmed by the fact that the average final grade of students in the experimental class is 1.5 points higher than that of the control class. The Analysis of CET-4 scores found that personalized teaching improved students’ English listening, reading, and writing skills. This paper combines decision trees and big data technology to optimize teaching content, effectively enhancing students’ English learning outcomes and providing new teaching strategies for English education in colleges and universities.

TRENDS IN HR MANAGEMENT AT THE ENTERPRISE

The purpose of this article is to assess the possibility of introducing new approaches to personnel management into domestic practice. Summarizing the results of the study, we can note the following: there is a discrepancy in the study of HR management issues in domestic scientific works and foreign scientific thought. Recent studies by Ukrainian scholars are related to the assessment of international experience in HR practices, adaptation of domestic HR systems to external challenges (war, pandemic, etc.). Foreign works are devoted to the disclosure of the theoretical and practical foundations of the application of new HR practices, empirical research of the effectiveness and efficiency of their implementation, and case studies. In the light of the trend in HR management to take into account the interests of the employee and ensure his/her well-being, the following newest HR practices have been selected for implementation in domestic enterprises: personalized human resource management; management practices based on corporate social responsibility; HR co-creation; Agile HR. Among the disadvantages and problems of applying personalized human resource management is the lack of time and personnel in the HR department to select an individual management strategy for each employee if the company is medium or large in size. The difficulty of assessing employee well-being can be an obstacle to implementing the principles of corporate social responsibility in human resources management. It is necessary to take a balanced approach to the formation of a system of direct and indirect indicators of employee satisfaction to obtain a true assessment. A rather patriarchal society, which is characterised by top-down implementation of innovations rather than the design of new HR management practices with the involvement of outsiders, may be an obstacle to the introduction of HR co-creation approaches. The main obstacle to the introduction of Agile HR may be the reluctance to change the organisational structure of HR management, as well as the reluctance of staff to abandon template solutions. Prospects for further research in the subject of this article are related to the assessment of the readiness of domestic enterprises to introduce innovations in the field of HR management.

A fuzzy clustering approach for cloud-based personalized distance music education and resource management

A fuzzy clustering approach for cloud-based personalized distance music education and resource management

Exploration of an Innovative Model of Higher Education Management and Student Training Mechanism Based on Cognitive Mapping

Abstract In this paper, we use cognitive mapping for four-parameter Logistics model fitting computation and obtain personalized learning resource paths incorporating learners’ fuzzy cognitive mapping after eliminating the influence of blunders and guessing factors on learners’ cognitive assessment. After calculating peer similarity based on the cognitive map, the cognitive change trajectory is tracked, and learning resources are recommended iteratively until students become proficient. Based on the cognitive objective function and knowledge relevance, the cognitive mapping of education management of college students is constructed. The research on the mechanism of higher education management and student cultivation is analyzed from the goal of talent cultivation in colleges and universities. Statistical analysis is utilized to analyze the research on the mechanism of higher education management and student cultivation. The results show that the t-value of the regression results are all greater than 2, the regression results are significant, and its regression coefficient is 0.87, which means that all dimensions of the cultivation mechanism of colleges and universities have a positive impact on external employability. In terms of academic attitude, moral cultivation and academic norms, the supervisor has a greater role in influencing postgraduates, and its percentage values are 49.2%, 52.1% and 46.5%, respectively, and the mean values of the three dimensions are above 4.1, while the standard deviation values are above 1.0. This study provides basic references and effective suggestions to promote the continuous improvement of graduate student training quality and is of great significance to the innovation of educational management and student training mechanisms.

A Perceptual Machine Model Based Approach to Recommending Online Learning Resources

Abstract The bias values of various learning resources are computed using neuron excitation functions based on the perceptual machine model in this paper. Each learning sample is calculated using the weight vector value of each layer in the learning resources. The difference between the output result of the network and the expected value is calculated and converted into the minimum value of the loss function for solving the normalized processing of the weight matrix of the learning resources. It is found that the average square root error in the online learning resources is 0.0897, the decreasing rate is 35.28% compared with the empirical mixing method, and the bias of the online resource recommendation model is 0.2453, which indicates that the proposed model can learn the mixing weight matrix more quickly and obtain a better mixing analysis field for more accurate and personalized learning resource recommendation.

Design and Implementation of a Learning Resource Recommendation System based on User Habits Based on GNN

This project aims to design and implement a learning resource recommendation system based on Graph Neural Networks (GNN). The system utilizes user learning habits as a foundation to provide personalized learning resource recommendations. By collecting and preprocessing user learning history data, and constructing a user-resource relationship graph, the GNN model is used to learn the representation vectors of users and resources. Combined with user habit features, appropriate recommendation algorithms are employed to recommend learning resources that align with their interests and habits.

The application of big data technology in online subject education innovation research

This paper applies big data technology to promote the innovative development of online subject education and improve students' self-learning efficiency to promote innovative management interaction in the education industry. In the design process, big data technology is used to mine and analyze massive educational data, combine the learning needs of online subjects, and provide technical support for six application levels of the online subject education system. Document transformation of education data is performed through the DCF mechanism, and the synchronization time slot is divided into a safe time slot and a reservation time slot. Then, the adaptive recommendation function is used to extract valuable information from behavioral data for personalized learning resource pushing. To verify the practical application effect of big data technology in the online subject education innovation system, the simulation analysis results show that after applying big data technology, the recommended resources preference of the education system is above 86%, the subject coverage rate is 90.48%, and the performance of test scores is improved by 17.5% relative to Class C. This shows that big data technology optimizes the application mode of online subject education and can provide students with better-quality educational resources.

User interest modeling and collaborative filtering algorithms application in English personalized learning resource recommendation

User interest modeling and collaborative filtering algorithms application in English personalized learning resource recommendation

Colorectal cancer and digital/live screening navigation: Promoting prevention through personalized recommendations and access.

10566 Background: This project evaluates the effectiveness of an advocacy organization-led digital and live navigation framework aimed at colorectal cancer (CRC) screening completion. The Colorectal Cancer Alliance’s screening quiz guides patients to a clinically valid, personalized CRC screening recommendation with a handoff to live navigation for those at risk. The framework utilizes digital innovation, targeted awareness, and financial support to support populations experiencing the greatest disparities and increase screening intention, behavior, and further health equity in colorectal cancer. This simple intervention is critical due to existing research consistently indicating on-time screening for CRC leads to favorable outcomes. Methods: In July 2022, the Alliance launched an enhanced quiz to improve the CRC screening navigation experience and increase engagement. The new survey instrument was restructured to streamline time to completion while preserving clinically accurate risk stratification. The follow-up navigation protocol was reordered from digital-first to live-first to leverage high-touch strategies earlier in the screening journey and dynamic content was added to the recommendation page to create a more personalized resource. The Alliance also deployed social media and influencer campaigns to increase outreach to at-risk communities. Results: The enhanced quiz delivered over 8,300 CRC screening recommendations and improved the average monthly completion rate (33%) and contact capture rate (14.4%) compared to the previous quiz in 2022 (24%; 8%). The median age of respondents was 55, and 37.2% of the respondents were between the ages of 45 and 64. Of the respondents, 26.7% were male and 73.3% were female. The majority were White (77.1%), 7.3% identified as Black/African American, 5.5% were Hispanic or Latino, and 3% were Asian. Most respondents were symptomatic (67.8%) but 8.1% were asymptomatic high-risk. Respondents (1,078) were triaged to live Alliance patient navigation. Conclusions: This digital and live navigation framework may serve as a strong solution in driving colorectal cancer screening and supporting shared-decision making conversations compared to other available interventions. The framework provides users with robust access to live navigation, educational resources, and support services for CRC screening and diagnosis. The Alliance is uniquely positioned to utilize its communications channels, social media and influencer campaigns to reach at-risk communities with credibility. Data attributed to specific campaigns are still being analyzed, and the Alliance will continue to optimize its navigation protocol and awareness efforts as quality improvement processes allow for a deeper understanding of more inclusive and impactful navigation experiences to close screening gaps among at-risk populations.

DEVELOPMENT OF A DIGITAL EDUCATIONAL ENVIRONMENT IN CHINA

Current model design research in the field of personalized learning mainly includes three categories: personalized learner model, personalized learning resource recommendation model, and personalized learning path model. The development of a personalized student model mainly depends on the basic information of the student, his interests and preferences, learning style, behavioral characteristics, etc.; and all learner information and data are also used to develop and implement a personalized learning resource recommendation model and an individualized learning path model Essential framework. The learner model is developed through an in-depth analysis of the learner's main attributes, learning process and learning outcomes, and on this basis, a model of the learning path that fits the learner is planned and personalized learning resources are presented. Among the various developed models, the student model occupies the largest share. In the study of personalized learning, different models can be developed that correspond to the individual characteristics and actual needs of students, so as to be more in line with the concept of respecting the individual characteristics of students, thereby contributing to the high-quality development of individualized learning and the overall development of students. We also described the model with tables that are given in the article.

Personalized Learning Resources Recommendation for Interest-Oriented Teaching

An interest-oriented teaching method can stimulate students' interest in learning, thus generating great internal drive. The personalized learning resource recommendation method for interest-oriented teaching meets students' personalized learning preference needs, reduces students' learning resource selection cost, and provides students with more diversified and rational learning resource supply. Different from traditional recommendation algorithms, the recommendation algorithm constructed in this article essentially adjusts the recommendation results in real time based on college students' adoption behavior of historical recommendation information. This article describes the problem of personalized learning resource recommendation for interest-oriented teaching, and constructs a personalized learning resource recommendation model based on the communication power of high-scoring learning resources. Experimental results verify the effectiveness of the model.

Personalized Course Resource Recommendation Algorithm Based on Deep Learning in the Intelligent Question Answering Robot Environment

Aiming at the problems of difficult-to-extract effective information and insufficient feature extraction in the existing intelligent question answering robot environment, a personalized course resource recommendation algorithm based on deep learning is proposed. Firstly, the potential preferences of users are obtained through course-related data. Secondly, the authors use one-hot coding and embedding to convert word vectors into low-dimensional, dense real-valued vectors and input them into the CIN-GRU model. Finally, the attention mechanism is used to improve the attention of some words and the accuracy of personalized course recommendation. The experiment shows that when the recommended list is 35, the precision, recall, and F1 value of the proposed personalized course recommendation method are 0.862, 0.851, and 0.857, respectively, which are higher than those of the comparison method. Therefore, the performance of the proposed method in sustainable personalized course resource recommendation is better than that of the comparison method.

A Personalized Course Resource Recommendation Method Based on Deep Learning in an Online Multi-Modal Multimedia Education Cloud Platform

Aiming at the problem that unstructured text in online multi-modal multimedia education is easy to cause error propagation, this paper proposes a personalized course resource recommendation method using deep learning in online multi-modal multimedia education cloud platform. First, the word vector of the text is obtained from the course data set by using the BERT pre-training model, and its semantic information in different contexts is analyzed. Then, the more complex representation of each word is extracted through the long short-term memory network (LSTM), in which the multi-head attention layer adds different weights to different word vector to better capture the key information in the sentence. Finally, the CRF layer is used to identify sentence entities, and the Sigmoid layer is used to extract relations, thus completing personalized course resource recommendation, which is significantly improved compared with other models. Experimental analysis shows that the algorithm is effective in personalized course resource recommendation.