Publication Search

The exponential growth of digital music catalogs on streaming platforms such as Spotify has made personalized recommendation systems crucial for enhancing user experience. This study develops a hybrid music recommendation system that addresses both warm-user and cold-user scenarios by combining Alternating Least Squares (ALS) collaborative filtering with content-based filtering (CBF) augmented by a popularity component. The dataset consists of 8,549,544 user-track interactions and a master file of 1,204,025 tracks with ten audio features. After preprocessing, users were segmented into 14,880 warm users and 723 cold users based on a five-interaction threshold. The ALS model was trained on the user-item implicit feedback matrix and tuned through grid search over factors, alpha, and regularization. CBF was implemented using cosine similarity on normalized audio features, while popularity scores were applied for new users with insufficient history. Evaluation used Precision@10, Recall@10, and NDCG@10. The final ALS configuration achieved NDCG@10 of 0.1116, representing a 30% improvement over baseline, while the hybrid CBF improved NDCG@10 for cold users from 0.0070 to 0.0201. Findings indicate that adaptive routing among ALS, CBF, and popularity reliably handles different user states, providing a practical foundation for production-grade music recommendation systems.

The architecture of consumer decision-making has completely changed due to the quick development of recommendation systems based on artificial intelligence (AI). The majority of earlier studies saw algorithms as instruments for forecasting and maximizing preexisting preferences. This study, however, makes a different claim: algorithmic curation actively shapes preferences rather than just reflecting them. This study creates and evaluates a structural model that examines the impact of algorithmic curation intensity on perceived search autonomy, identity resonance, affective evaluation, and the development of initial preferences. The model is based on identity-based consumption theory and the literature on human-AI interaction. The study's findings, which are based on survey data from Generation Z consumers and Structural Equation Modeling (SEM) analysis, demonstrate a contradictory dynamic: algorithmic curation improves identity resonance and directly influences initial preferences while simultaneously decreasing feelings of autonomy. The primary mediating mechanism that links algorithmic exposure to emotional assessment and preference creation is identified as identity resonance. In addition to introducing the concept of algorithmic consumer formation as a new conceptual framework for comprehending consumer behavior in the AI-based digital era, our findings expand the notion of bounded rationality toward algorithmically bounded agency.

This study aims to analyze how the TikTok and Instagram Reels algorithms play a role in the distribution of multimedia content and their implications for content visibility, user engagement, and digital marketing practices. The research method used is a qualitative approach through a Systematic Literature Review by analyzing articles from accredited national journals and reputable international journals published in the period 2020-2025. The literature search process was carried out systematically through openly accessible scientific databases, then selected using inclusion and exclusion criteria to ensure the relevance and quality of the sources. The research findings show that the TikTok and Instagram Reels algorithms both rely on analysis of user behavior, initial engagement levels, and the characteristics of short-form audiovisual content in determining content distribution. TikTok emphasizes an interest-based recommendation system that allows content from new creators to gain broad reach, while Instagram Reels combines algorithmic recommendations with established social networks. The implications of this study emphasize that understanding the mechanics of algorithms is a strategic factor for content creators, business actors, and digital marketing practitioners in designing effective, adaptive, and sustainable multimedia content distribution strategies.

The rapid development of digital streaming platforms such as Netflix has generated a large volume of content data with diverse characteristics, thereby requiring effective analytical methods to understand emerging patterns and trends. This study aims to classify Netflix content into two main categories, namely movies and television shows, and to analyze genre trends and content characteristics using a data mining approach with the Naive Bayes algorithm. The dataset used in this study is the Netflix Shows dataset, consisting of 8,809 content entries, with the primary features analyzed including genre, rating, and country of production. The research process begins with data exploration and preprocessing stages, including data cleaning, handling missing values, and transforming categorical features to enable effective model construction. Subsequently, the dataset is divided into training and testing sets to objectively and systematically build and evaluate the Naive Bayes classification model. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics to assess the model’s ability to accurately distinguish between Netflix content types. The experimental results demonstrate that the Naive Bayes algorithm is able to classify Netflix content into Movie and TV Show categories with accuracy, precision, recall, and F1-score values of 100%, respectively. The confusion matrix indicates that no misclassification occurred, suggesting that genre, rating, and country of production features provide a very clear separation between content classes. These findings indicate that the Naive Bayes algorithm can achieve exceptionally high classification performance with optimal evaluation results. The results further reveal distinct differences in characteristics between movies and television shows based on genre and production attributes. Therefore, this study is expected to contribute to the development of content recommendation systems and strategic content management within the streaming industry.

Tourism is one of the sectors that plays an important role in boosting economic growth through travel activities and destination exploration. Tourists' preferences for nature-based tourism options, such as mountain hiking or beach tourism, are influenced by various factors, ranging from personal experiences and recreational interests to social characteristics. Therefore, a technology-based approach is needed to predict destination choice tendencies more accurately. As artificial intelligence technology develops, deep learning methods have been widely used in classification processes due to their ability to process large amounts of data and recognize complex patterns. In this study, a Multilayer Perceptron (MLP) model is used to classify tourists' preferences between mountain or beach destinations based on a survey dataset. The research stages include data processing, data splitting using a train-test split, model training, and performance evaluation using accuracy, precision, recall, and F1-score. The test results show that the MLP model is capable of achieving an accuracy rate of 99%, confirming that deep learning methods are effective in automatically mapping tourism preference trends. This research is expected to serve as a basis for the development of more personalized travel destination recommendation systems, as well as to support tourism management in formulating targeted promotional strategies.

In today's digital era, recommendation systems have become an integral part of supporting consumer purchasing decisions, including in the food and beverage industry. This study aims to develop a product recommendation system for snacks and beverages using the item-based collaborative filtering method. This method was chosen due to its ability to handle large-scale user and product data, as well as its efficiency in providing relevant recommendations based on user consumption patterns. In this study, the system calculates the average user rating and implements   Cosine Similarity to measure the similarity between products, resulting in more accurate recommendations. The system also evaluates the accuracy of recommendations using the Mean Absolute Error (MAE) metric. Based on the results obtained, which is 0.285403 for the average error on 17 items, the developed recommendation system can improve consumers' shopping experience, help them find products that suit their tastes, and support the sales of snacks and beverages products in the market

This study aims to analyze user sentiment toward the integration of Artificial Intelligence (AI) in online learning platforms, which are increasingly expanding in the digital era. With the growing use of AI technologies in education—such as learning chatbots, material recommendation systems, and automated assessments—it is essential to understand users’ perceptions and reactions to these implementations. The research employs sentiment analysis based on text mining using user review data collected from various online learning platforms. The analysis process includes data preprocessing, sentiment classification using machine learning algorithms, and interpretation of results based on the proportion of positive, negative, and neutral sentiments. The findings indicate that most users express positive sentiments toward AI integration, as it enhances learning efficiency and personalization. However, some users raise concerns regarding data privacy and the lack of human interaction. This study is expected to serve as a reference for educational platform developers to design AI systems that are more adaptive, transparent, and user-centered

The development of artificial intelligence (AI) technology has brought about a major transformation in the world of libraries and information services. Automation, data analysis, and AI-based recommendation systems have increased the efficiency and accessibility of information for users. These advances also pose new challenges for librarians, particularly in maintaining human values ​​in the service process. Humanist librarians in the AI ​​era are required not only to understand technology but also to maintain an ethical, empathetic, and communicative role in interactions with users. This research uses a literature review to address the questions raised. Librarians, as mediators between technology and humans, act as bridges between digital literacy and ethical information, maintaining warmth and empathy in library services. By prioritizing human values ​​such as empathy, responsibility, and information justice, librarians can ensure that the application of AI in libraries remains oriented toward human needs and does not diminish the essence of civilized service.

The selection of a thesis topic that aligns with students’ interests and competencies often poses a challenge in academic environments. Inappropriate topic selection can lead to decreased motivation and delays in completing the final project. This study aims to develop a thesis topic recommendation system based on a genetic algorithm that considers students’ interests and academic abilities. The data used include grades from core courses, results of research interest questionnaires, and a list of thesis topics provided by academic supervisors. Each topic is represented as a chromosome, while the fitness function is calculated based on the level of compatibility between student attributes and topics. The selection process employs the roulette wheel method, with single-point crossover and random mutation to generate an optimal solution population. The test results show that the recommendation system based on the genetic algorithm achieves an accuracy rate of 86.7%, higher than the keyword-matching method, which only reaches 71.2%. Therefore, this approach is proven effective in assisting students to determine thesis topics that are suitable, objective, and efficient.

Selecting a faculty that aligns with students’ interests and talents is a strategic step in determining the success of higher education and future career paths. However, most vocational high school (SMK) students still face difficulties in identifying the most suitable faculty due to the lack of data-driven analysis. This study implements the C4.5 classification algorithm within data mining techniques to build an automatic and measurable faculty recommendation system. The dataset consists of attributes such as SMK major, interest level, aptitude test results, academic grade average, and gender, with the output being the recommended faculty. The C4.5 algorithm was chosen for its ability to generate a transparent and interpretable decision tree, which helps both guidance counselors and students understand the rationale behind the recommendations. The experimental results show that the constructed classification model achieved an accuracy rate of 88%, based on cross-validation testing using data from 12th-grade students. The implementation of this system is expected to serve as an objective tool in the faculty selection process and to promote a data-driven decision-making approach in secondary education environments.

This study presents the integration of a Large Language Model (LLM) Ollama with the OpenStreetMap (OSM) API within a Business Intelligence (BI) framework to develop an intelligent, location-based recommendation system. The system is designed to assist users in finding dining, leisure, and resting places through natural language interaction and contextual understanding. The LLM interprets user input semantically, transforms it into structured spatial queries, and retrieves relevant geospatial data from OSM. The data are then analyzed, categorized, and visualized using BI methods to enhance interpretability and decision-making. The system was implemented using Next.js, Leaflet.js, ensuring interactivity and scalability for web-based deployment. Technical evaluation focused on system accuracy, response time, and output consistency. Results demonstrate an average response time of 1.74 seconds, 80% accuracy, and 80% consistency, proving the model’s efficiency in producing relevant, context-aware recommendations. This integration highlights the potential of combining open geospatial data, local LLMs, and BI analytics to create intelligent, data-driven decision support systems applicable to tourism, urban planning, and spatial information management.

The rapid development of digital technology has significantly transformed commercial activities, particularly through the emergence of marketplaces as platforms for online transactions. The vast number of products available in a marketplace often creates difficulties for users in finding items that suit their needs and preferences. To address this challenge, a recommendation system is required to provide personalized and relevant product suggestions. This study discusses the implementation of a product recommendation system in a marketplace using the Collaborative Filtering method. This method works by leveraging information from users’ previous behavior, such as purchase history, ratings, and similarity of preferences with other users, to generate more accurate product recommendations. The Collaborative Filtering approach has proven effective in identifying user preference patterns based on relationships between users as well as between items. This study employs user interaction data such as ratings and shopping activities as the processing foundation. The process involves data collection, preprocessing, calculation of similarity between users or products, and generating recommendation lists. The results indicate that this method enhances the shopping experience by providing relevant product suggestions tailored to user interests, thereby increasing customer satisfaction and potentially improving sales performance in the marketplace. Thus, the application of a Collaborative Filtering-based recommendation system not only simplifies product discovery for users but also offers strategic advantages for marketplace operators in digital business competition

The implementation of a recommendation feature in the courier service selection system on e-commerce platforms is a technological innovation aimed at improving logistics efficiency while providing a more optimal user experience. Through this feature, consumers can find alternative delivery services based on certain indicators, such as cost, estimated time, and service quality. However, in practice, the implementation of recommendation features has the potential to raise legal issues when platforms prioritize internal couriers or certain partners without transparency and clear objective indicators. This situation can lead to discriminatory treatment, limit market access for other businesses, and reduce consumer freedom in choosing services. This study aims to analyze the implementation of recommendation features by e-commerce platforms from a competition law perspective, specifically based on Law Number 5 of 1999 concerning the Prohibition of Monopolistic Practices and Unfair Business Competition. The method used is normative juridical research with a descriptive-analytical approach, through the review of secondary data in the form of laws and regulations, literature, and the practice of implementing recommendation systems in the digital industry. The research results indicate that recommendation features that unilaterally prioritize internal couriers without objective basis and without information transparency have the potential to violate Article 19 letter d of Law Number 5 of 1999. This practice can hinder competition, close opportunities for other courier service providers, and create distortions in the digital logistics ecosystem. Therefore, this study recommends that recommendation features in e-commerce be designed in a neutral, transparent manner, and based on objective indicators, such as rates, estimated delivery times, and service performance. This will maintain healthy business competition and protect consumers' rights to obtain the best service options.

This research aims to develop a recommendation system that can help retail business owners design more effective, data-driven promotional strategies. This system utilizes data mining techniques and the Apriori algorithm to extract association rules from consumer transaction data, thereby identifying more specific and accurate consumer purchasing patterns. Based on these patterns, the system can provide relevant promotional recommendations, such as product bundling, buy-one-get-one offers, or special discounts, which can attract consumer interest and increase sales. The system's implementation process is presented in the form of an interactive dashboard, which allows business owners to upload their transaction data, adjust analysis parameters, and visualize the promotional recommendation results in a way that is easier to understand and can be directly applied to their marketing strategies. This system not only provides well-structured promotional recommendations but also enables retail business owners to make more informed and efficient decisions in determining the type of promotion to implement, based on insights gained from analyzing their own transaction data. By utilizing this system, business owners can optimize their promotional strategies more efficiently and effectively, because they can quickly identify promotions that best suit consumer purchasing patterns. This can increase impulse sales, as relevant promotions will encourage consumers to purchase more products. Furthermore, this system shows great potential in increasing consumer engagement, as the promotions provided are more personalized and tailored to each consumer's preferences. Therefore, the implementation of this recommendation system has the potential to drive significant sales growth and help retail business owners achieve greater profits, as well as accelerate their business decision-making process. This system, ultimately, not only benefits business owners but also enhances the consumer shopping experience with promotions that are more tailored to their needs and preferences.

The need for adaptive and personalized learning systems is increasing along with the advancement of information technology. Informatics students face challenges in choosing materials that suit their abilities and interests. This research aims to design and evaluate an Generative AI-based independent learning recommendation system in Indonesian that can help students navigate the learning process more efficiently. The system utilizes a generative language model to provide relevant learning material suggestions based on students' individual learning history and preferences. This study uses a software engineering approach and experimental evaluation. The dataset is collected from various reference sources of learning and user interaction with the system. The Generative AI model is trained to generate contextual and Indonesian-language content recommendations. The results of the evaluation show that this system is able to increase the effectiveness and satisfaction of students' independent learning. These findings confirm the great potential of generative AI technology in supporting higher education, particularly in supporting personalized learning in local languages.

This paper explores the application of quantum-inspired optimization algorithms in the training of large-scale Graph Neural Networks (GNNs) within distributed cloud-edge environments. GNNs have gained significant attention due to their ability to model complex relationships in graph-structured data, yet their training presents challenges such as high computational demand, inefficient resource allocation, and slow convergence, especially for large datasets. Traditional meta-heuristic algorithms, while useful, often face scalability and performance issues when applied to such large-scale tasks. To address these challenges, we propose a quantum-inspired meta-heuristic algorithm that leverages quantum principles, such as superposition and entanglement, to enhance optimization processes. The algorithm was integrated into a hybrid cloud-edge system, where computational tasks are dynamically distributed between edge nodes and the cloud, optimizing resource utilization and reducing latency. Our experimental results demonstrate significant improvements in training speed, resource efficiency, and convergence rate when compared to traditional optimization methods such as Genetic Algorithms and Simulated Annealing. The quantum-inspired algorithm not only accelerates the training process but also reduces memory usage, making it well-suited for large-scale GNN applications. Furthermore, the system's scalability was enhanced by the hybrid cloud-edge architecture, which balances computational load and enables real-time data processing. The findings suggest that quantum-inspired optimization algorithms can significantly improve the training of GNNs in distributed systems, opening new avenues for real-time applications in areas such as social network analysis, anomaly detection, and recommendation systems. Future work will focus on refining these algorithms to handle even larger datasets and more complex GNN architectures, with potential integration into edge devices for enhanced real-time decision-making.

In a context where students face increasingly complex academic choices, this work proposes a recommendation system based on Bayesian networks to guide new baccalaureate holders in their university choices. Using a dataset containing variables such as secondary school section, gender, type of school, percentage obtained, age, and first-year honors, we have constructed a probabilistic model capturing the dependencies between these characteristics and the option chosen. The data is collected at the Catholic University of Bukavu, the Official University of Bukavu, and the Higher Institute of Education of Bukavu, preprocessed and then used to learn the structure via the hill-climbing algorithm with the BIC score using R's bnlearn tool. The model enables us to estimate the probability that a candidate will choose a given stream, depending on their profile. The approach has been validated using metrics such as BIC, cross-validation, and bootstrap and offers a good compromise between interpretability and predictive performance. The results highlight the potential of Bayesian networks in constructing explainable recommendation systems in the field of academic guidance. The system produces orientation probability maps for each candidate, which can be used by enrollment service advisers, as well as an ordered list of options relevant to the candidate's profile. With a remarkable performance on a test sample of precision@k=0.85, recall@k=0.61, ndcg=0.8, and Map=0.88, it constitutes an effective lever for reducing the risk of being misdirected in universities in South-Kivu, in the Democratic Republic of Congo

Learners are continually faced with choosing appropriate courses or making career choices due to increased educational opportunities. The emergence of machine learning-based course and career recommender systems has the potential to address this issue, offering personalized course recommendations tailored to individual learning pathways, preferences, and learning history. The optimization and feature engineering techniques and practical deployment environments have not been collectively examined in the previous research, despite the significant advancements in this area of research. Furthermore, previous research has rarely synthesized how these technical components help students choose appropriate courses and careers. This systematic review was carried out to investigate the current state of machine learning-based course and career recommender systems, focusing on key elements, such as primary data sources, feature engineering methods, algorithms, optimization techniques, evaluation metrics, and the environments where the existing course recommendation models are deployed. The PRISMA method for conducting a systematic review was used to choose studies that met the requirements for inclusion and exclusion. The study findings show significant reliance on interpretable and traditional machine learning algorithms, such as K-Nearest Neighbor and Random Forest, to develop recommender models. Feature engineering remains basic, as most studies rely on normalization, while optimization processes are often underreported. Also, evaluation metrics varied widely, impeding comparability, while most of the recommender models are deployed in an e-learning environment, leaving the traditional learning environment underrepresented. Furthermore, the study findings identified issues including data sparsity and diversity, data security and privacy, and changes in learner preferences that may have an impact on the performance of recommender systems while recommending further studies to make use of standardized optimization methods, and automated domain-informed feature engineering frameworks, benchmark and annotated datasets in developing models the gives priority to learners’ success and educational relevance.

Technological advancements have brought significant transformations across various fields, including the application of machine learning in recommendation and classification systems. Machine learning leverages data processing, utilizes algorithms, and efficiently identifies patterns to produce accurate recommendations and predictions. This study aims to review machine learning-based recommendation system approaches, analyze model performance, and compare the algorithms used. A literature review was conducted by examining journals published in the past five years, focusing on algorithm implementation. The findings indicate that the Naïve Bayes algorithm delivers the best performance, achieving an accuracy of up to 97%. This algorithm is particularly well-suited for processing small to medium-sized datasets with high efficiency. The research provides comprehensive insights into the performance and limitations of various algorithms, serving as a valuable guide for future developments in the field.

The growth of the internet has influenced the tourism industry because the internet makes it easier for individuals to obtain reviews about places to visit and because the internet is a tool used by tourist site managers to assess the quality of their offerings. The increase in the number of tourists of almost two million in just three years in West Sumba is proof of this influence. Social media is a tool that people use to interact with each other online; some people have multiple accounts on platforms such as Instagram, WhatsApp, Facebook, Telegram, Twitter, and so on. Tourists can receive recommendations for tourist attractions based on price and type of trip desired through a tourist attraction recommendation system that uses the KNN algorithm. Three factors were used in this research: activity, type of tourism, and type of price. An accuracy of 63.16% is found in the test results using the KNN algorithm and the Rapid Miner application with a K value of 5. The analysis results show that the K-Nearest Neighbor (K-NN) approach can be used as a guideline for recommending tourist destinations to visitors in West Sumba.