Learning with personalized recommender systems: A psychological view

Recommender System was widely used in commercial websites for the past few years. These systems track past activities of customers and recommend them the relevant items. The emergence of E-learning activities over a few decades develops a variety of E-learning content available for virtual learning environments (VLE). A large amount of learning objects is present in E-learning repositories. Dealing with problems of the diversity of data, Educational Recommender System (ERS) plays a vital role in the educational sector. Educational recommender systems track the learners' past activities, know the users' preferences, assist the educators and learners, provide relevant content to learners, and enhance their learning outcomes. A personalized recommender system will intensify the learners' interest in particular content and reduce the course dropout rate. The recommender system makes the decision-making process for choosing the appropriate content easy for learners. ERS uses various approaches and technologies for assisting the learners' and helps them to run their learning process smoothly. Collaborative filtering, Content-based, and knowledge-based are the basic techniques of recommender systems. The research shows that a combination of these approaches will give more effective and efficient results. This mixing of approaches refers to the hybridization techniques. Traditional approaches with deep learning networks will improve the recommendations and provide results with higher accuracy. This paper provides how E-learning support recommender systems produce recommendations using different techniques. The technical results of recommender techniques help to find the best approach for making a recommender system in the future.

Recommendation systems (RS) have been used in many scenarios, from entertainment to health. Inside the RS area, Educational Recommendation Systems (ERS) are becoming popular, been used for different types of recommendations such as recommending materials, exercises, and learning paths. As ERS works in a different scenario of classics RS, ERS requires specific evaluation metrics. However, the task of evaluating ERS is difficult once the educational field has its features to be analyzed. To help other researchers in this field, this work presents a systematic mapping on methods used for evaluating ERS. This study analyzed 91 papers of the last five years and provide an overview of the main methodologies, subject, metrics, and trends in the evaluation of ERS.

Purpose – The purpose of this paper is not only to design a more effective recommendation system for libraries, but also to eliminate many of the weaknesses found in the existing library recommender systems.Design/methodology/approach – A novel library recommender system was designed for English collections by integrating personal ontology model and collaborative filtering model with domain specification.Findings – The trend of the traditional library is evolving toward that of digital library. The personal ontology recommender (PORE) system offers a friendly user interface and provides several personalized services.Research limitations/implications – This system is only implemented and tested in the Library of National Chung Hsing University in Taiwan.Originality/value – The paper demonstrates a good methodology to offer an active, effective, and personalized recommendation system for library patrons.

The increasing integration of Artificial Intelligence (AI) in e-commerce has transformed digital marketing strategies, particularly through personalized recommendation systems. However, this advancement has raised ethical concerns regarding data privacy, algorithmic transparency, and consumer autonomy. In Southeast Asia, where digital platforms rapidly expand, these concerns become more complex due to diverse regulatory landscapes and user expectations. This study aims to analyze and compare the transparency of AI-based recommendation systems across three major e-commerce platforms in the region: Shopee, Lazada, and Tokopedia. A qualitative comparative approach was employed using content analysis of official policy documents, including privacy policies and AI guidelines, sourced from each platform between January and March 2024. The analysis utilized LLM-assisted text mining and thematic coding to identify ethical indicators such as algorithmic transparency, user control, and policy readability. The results reveal significant variation in ethical practices: Shopee scored the highest in all dimensions, including algorithmic transparency (score: 9/10), user control (8/10), and policy readability (9/10). Lazada ranked moderately with scores of 6/10, 4/10, and 6/10 respectively, while Tokopedia scored lowest with 3/10 for transparency, 0/10 for user control, and 4/10 for readability. These disparities indicate that ethical communication and user empowerment remain uneven across platforms. This study contributes to the discourse on digital ethics by highlighting the need for regional standards in AI transparency and promoting user-centric ethical design. The findings provide valuable insights for policymakers, platform designers, and digital consumers navigating trust in algorithm-driven environments.

Recommender systems are used to suggest items that are useful to users. The recommendations can be surprising and may be categorized as serendipitous recommendations. One of the limitations with serendipitous recommendations is that the user interface of such a recommender system rarely supports the user to switch from accuracy orientation to serendipity facilitations. Using serendipitous recommendations can be challenging. This is because the user might not fully benefit from and understand the serendipitous recommendations. One main advantage of this type of system is that a serendipity-oriented recommender system can be used for the supervision of research students. It can help them to find a novel topic in the area of their research interests. This paper reports on a novel user interface design for facilitating serendipitous recommendations generation in educational environments. The user interface of this recommender system provides students with user controls and visualization in order to explore research articles. This research comprises user experience experiments conducted in an academic environment and evaluated by means of a user centered design evaluation. It involves research articles recommender system named JabRef. The recommender systems were used by students at the undergraduate level. Users reported an enhanced user experience while using the user controls and visualization and serendipitous resource discovery. It was found that user interface design can facilitate a serendipity recommender system in the learning environment. University professors supervising students during the research can also benefit from the recommender system.

Nowadays, large volumes of valuable data of different degrees of veracity can be easily generated or collected at a high velocity from a wide variety of data sources. Embedded in these big data are implicit, previously unknown and potentially useful information and knowledge. Hence, big data analytics are in demand as they assist users to analyze the big data and discover new knowledge. This in turn helps users gain insight into big data, obtain useful information, and make personalized recommendation. In this paper, we focus on big data analytics on music-i.e., music analysis-for personalized music recommendation systems. In particular, we present a system that exploits the frequent tags attached to the tracks in an user's listening history and a hidden Markov model (HMM) for generating predictions and thus making personalized recommendation. Knowledge learned from this personalized music recommendation can be transferred to building other personalized recommendation systems.

How to quickly and accurately retrieve the products that users are interested in from a huge amount of financial products has become a business pain point that financial institutions must solve. In this study, an interpretable EPRSA model for personalized financial service recommendations based on self-attention mechanisms is proposed by combining an LSTM model and an LDA topic model with AI technology support. A customized recommendation system for financial services is constructed by introducing the Nginx server into the Flask framework, and the design of the database and personalized recommendation module is interpreted. For the financial service personalized recommendation system proposed in this paper, its recommendation performance and system performance are tested, and the stock financial products are selected as the recommendation objects to explore its recommendation effect. It is found that the DNCG index of personalized recommendation of financial products of the EPRSA model is improved by 40.18%, the average response time of the system when the number of concurrent users is 1,000 is 1.96 s. The average quality of the personalized recommendation of the collection of stocks reaches 0.153. The customized recommendation of financial services using AI technology can select financial products based on the investor’s preference, help investors better understand the product returns, and improve the service quality of the financial industry.

In recent years, Educational Recommender Systems (ERSs) have attracted great attention as a solution towards addressing the problem of information overload in e-learning environments and providing relevant recommendations to online learners. These systems play a key role in helping learners to find educational resources relevant and pertinent to their profiles and context. So, it is necessary to identify information that helps learner’s profile definition and in identifying requests and interests. In this context, we suggest to take advantage of the annotation activity used usually in the learning context for different purposes and which may reflect certain learner’s characteristics useful as input data for the recommendation process. Therefore, we propose an educational recommender system of web services based on learner’s annotative activity to assist him in his learning activity. This process of recommendation is founded on two preparatory phases: the phase of modelling learner’s personality profile through analysis of annotation digital traces in learning environment realized through a profile constructor module and the phase of discovery of web services which can meet the goals of annotations made by learner via the web service discovery module. The evaluation of the developed annotation based recommendation system through empirical studies realized on groups of learners based on the Student’s t-test showed significant results.

This paper is a preliminary study of the state of the art on Recommender Systems (RS) in Higher Education. This work presents the initial phase towards the development of a prototype of RS of personalized learning path (PLP). The prototype can be seen as a choice for higher education professors' training in ICT, considering Mobile Learning and Microlearning as a working paradigm. The literature about RS focused on Technology Enhanced Learning (TEL) is varied and extensive. However, the presence of RS in the application of PLP is scarce. This review was conducted by exploring the core subject in specialized databases of education and computing. The revised corpus consisted of open access and high impact publications developed from 1990 to 2018 in the context of education. In the process of reviewing the literature, ten studies based on RS for TEL were identified, analyzed and compared. These studies reveal the possibility of applying various techniques and frequent tasks of RS in E-Commerce to the field of RS with educational purposes. It demonstrates that RS to access to Microlearning educational resources in mobile environments are limited, thus making this research appropriate and relevant.

This study analyzed the impact of system quality and HCI factors on user acceptance intention, mediated by perceived trust and immersion, in the context of a deep learning-based makeup recommendation system. The results indicate that system quality and HCI factors significantly influence user acceptance intention through perceived trust and immersion. This underscores the importance of system quality and HCI factors for the successful application of makeup recommendation systems. In particular, factors such as diversity, accuracy, anthropomorphism, and realism enhance user trust and immersion, leading to higher acceptance intention. However, it was found that certain factors, such as personalization, do not significantly influence acceptance intention through immersion. This suggests that the impact of specific factors should be considered in the design of recommendation systems. The study is limited by its focus on a specific age group and gender in the survey, which may restrict the generalization of the results. Additionally, there is a lack of research on users with different cultural backgrounds, necessitating an understanding of the global market applicability. Future research should extend to users with diverse demographic characteristics to derive universal design principles for makeup recommendation systems. Furthermore, the impact of factors such as personalization on user experience should be explored in depth to enhance user-centered, customized beauty services. This research provides a theoretical and practical foundation for the effective design and implementation of makeup recommendation systems and is expected to contribute to the digital transformation of the beauty industry.

The personalized recommender system, which is extensively used in many domains, is suggested as a solution to the information overload issue.Recently, and with great speed, the area of job recommender systems for recruiting has arisen.The user profiles and recommendation technologies of the job recommender system have attracted attention, have undergone academic study, and have been implemented for various use cases in industries.. Based on the available research, we present some fundamental user profile concepts as well as some popular recommendation technologies in this paper.Across many areas, adaptive recommender systems are becoming more widespread.Regardless of the domain, personalized recommendations are a great method to enhance user experience, but they must be implemented properly within the interaction context.By limiting the search area to items associated with the user's profile and alerting the user to those items most likely to suit their interests, adaptive recommender systems basically give users a more intelligent way to traverse and explore complex information landscapes.Customized recommender systems have recently piqued the interest of firms that serve job seekers.

Introduction: In the current educational landscape, universities provide a vast array of diverse and obscure courses. However, the primary challenge students face is decision overload, as the abundance of options can make it difficult to choose courses that align with their interests, career aspirations, and strengths. The development and application of proper course suggestion systems might assist students in overcoming the challenges associated with choosing the right courses. However, these recommendation systems still require improvement to address explainability issues, security issues, and cold start. Our analysis reveals that there is limited research addressing how course recommendation systems can assist 12th-grade students in selecting courses for higher education. Therefore, this study presents a novel personalized recommendation system, namely "Interpretability-Driven Course Recommendation: A Random Forest Approach with Explainable AI", that chooses the top-3 courses for students based on their intermediate class grades/- marks. This research provides accurate and interpretable recommendations using the Random Forest algorithm with Explainable AI that ensures transparency by explaining why a particular course is recommended. Method: The system uses a Random Forest classifier with SHAP (SHapley Additive exPlanations) to forecast the top-3 courses with the greatest expected scores for appropriateness. The system uses SHAP (SHapley Additive exPlanations) values to integrate Explainable AI (XAI) to guarantee openness and trust. The proposed model solves the cold start problem and provides data security. Results: In terms of precision (0.90), recall (0.92), and F1-score (0.92), Random Forest fared better than any other classifier. By combining predictions from several decision trees, its ensemble learning technique increases stability, decreases overfitting, and improves generalization across a broad range of input data patterns. Discussions: A major drawback of conventional black-box machine learning models is their lack of transparency, which is addressed by the incorporation of SHAP into the course recommendation system. In this model, students get suggestions in addition to information on which topic scores had the biggest influence on their choice. Conclusion: This study presents a practical and interpretable course recommendation system designed for 12th-grade students transitioning into higher education. Through the use of Explainable AI-enhanced Random Forest, the model provides precise, transparent, and customized recommendations. It addresses the main drawbacks of conventional systems, such as their lack of explainability and their cold start problems. The model';s excellent precision, recall, and F1-score indicate its superior performance, which makes it a useful tool for student guidance and academic advice. For even more thorough recommendations, future research may consider combining long-term academic objectives, aptitude test results, and student interests.

Recommender system has received tremendous attention and has been studied by scholars in recent years due to its wide applications in different domains. With the in‐depth study and application of deep learning algorithms, deep neural network is gradually used in recommender systems. The success of modern recommender system mainly depends on the understanding and application of the context of recommendation requests. However, when leveraging deep learning algorithms for recommendation, the impact of context information such as recommendation time and location is often neglected. In this paper, a time‐aware convolutional neural network‐ (CNN‐) based personalized recommender system TC-PR is proposed. TC-PR actively recommends items that meet users’ interests by analyzing users’ features, items’ features, and users’ ratings, as well as users’ time context. Moreover, we use Tensorflow distributed open source framework to implement the proposed time‐aware CNN‐based recommendation algorithm which can effectively solve the problems of large data volume, large model, and slow speed of recommender system. The experimental results on the MovieLens‐1m real dataset show that the proposed TC-PR can effectively solve the cold‐start problem and greatly improve the speed of data processing and the accuracy of recommendation.

Recommendation technology is an essential component of the Internet of Things (IoT) services that can help users get information at any time and from any place. Traditional recommendation algorithms, on the other hand, are unable to satisfy the IoT environment’s swift and reliable recommendation criteria. The use of mathematical and information discovery methods to overcome the relationship with target consumers in order to have desired items is known as a recommendation system. In this paper, a recommendation algorithm based on collaborative filtering is proposed. In this sense, the recommendation method (Recommender Systems) was developed; it is focused on the user’s characteristics, such as hobbies, and it is recommended to satisfy the object’s user specifications, also known as customized recommendation system (Personalized Recommender Systems), The majority of modern e-commerce recommender programs tend to recommend the best goods to a customer, believing that each product’s properties remain constant. Some properties, such as price discounts, can, however, be customized to respond to the preferences of each customer..

Very Large Online Platforms (VLOPs) use personalized recommender systems to optimize their main performance metric: attention-based user engagement. In doing so, these systems might however amplify systemic risks by promoting controversial or polarizing content, thereby exacerbating issues such as misinformation, societal polarization, and the manipulation of civic discourse. To mitigate these risks, regulations such as the European Union’s Digital Services Act (DSA) mandate increased data access and transparency, including for the auditing of personalized recommender systems. However, the data access provided by VLOPs remains limited—often restricted to specific user demographics, aggregate statistics, or curated datasets—hindering meaningful oversight. Consequently, new methods are needed to audit recommender systems effectively at the user level. In this paper, based on an analysis of the legal context and technical alternatives for data access, we present SOAP, the System for Observing and Analyzing Posts. SOAP is an open-source framework for auditing recommender systems using sock-puppet accounts. It enables fine-grained user-level analysis beyond the constrained data access typically provided by platforms. We detail SOAP’s technical implementation and evaluate its ability to scrutinize systemic risks. Additionally, we tested SOAP in a workshop with over 100 participants and observed a measurable increase in participants’ algorithmic literacy. This demonstrates SOAP’s potential not only for research and regulatory auditing, but also as an educational framework to foster public awareness of algorithmic influence.