Recommender System Algorithms Research Articles

A Self-Evaluating Collaborative Filtering Recommendation Algorithm: A Case Study of Anime Recommendations

Abstract. This paper introduces a collaborative filtering recommendation algorithm aimed at addressing the issues of information insufficiency and the mismatch of user personalization needs in anime recommendations. Firstly, we review relevant literature to explore the application of collaborative filtering algorithms in recommendation systems and previous research findings. Then, we detail the design and implementation of collaborative filtering algorithms based on anime and user data, calculating similarities between anime and between users respectively for recommendation purposes. Finally, a self-evaluation is conducted to achieve optimal recommendation performance. Experimental results show that when recommending 10 anime titles, the ROC analysis results indicate a high level of precision, with both algorithms performing well in terms of accuracy.

An Entropy-Based Composite Indicator for Evaluating the Effectiveness of Recommender System Algorithms

The problem of forming a composite indicator for evaluating the effectiveness of recommender system algorithms is considered. A novel composite indicator is proposed by combining individual metrics using the entropy method. The testing base of this study consists of 12 algorithms (on the one hand) and 3 datasets (on the other). For each algorithm–dataset combination, we calculate partial criteria used in evaluating recommender systems. According to the results presented below, the composite indicator is an effective tool for evaluating the performance of recommender system algorithms. As is shown, the performance of the algorithms varies depending on the size and other basic characteristics of a particular dataset. This indicator can be used to develop more efficient algorithms and their ensembles as well as to optimize hyperparameters and improve the quality of recommendations.

An interval-valued matrix factorization based trust-aware collaborative filtering algorithm for recommendation systems

In existing trust-aware collaborative filtering algorithms, each trust relationship between two users is usually represented by a real number, but such a number is neither sufficient to reflect the quantity of the trust relationship existing in the user’s mind nor easy to be given. This leads to the inaccuracy of the trust relationship and poor final recommendations. To solve this problem, we propose an approach to deduce interval-valued trust relationships from the given real-valued trust relationships, which enables the new trust relationships to optimally reflect the true trust relationships existing in users’ minds. The coming problem we face is how to fuse the interval-valued trust relationships and the real-valued ratings. Though most existing trust-aware collaborative filtering algorithms use matrix factorization to fuse the real-valued data, they are not capable of fusing interval-valued trust relationships and real-valued ratings. The reason is that the arithmetic operations on intervals and arithmetic operations on real numbers are different. Therefore, we proposed a novel interval-valued matrix factorization approach. After that, an interval-valued matrix factorization based trust-aware collaborative filtering (IMF_TCF) algorithm is designed. The experiments carried out with open datasets indicate that IMF_TCF achieves the best recommendation performance compared with the state-of-the-art algorithms.

Tourism Application Development with a Recommendation System based on Fuzzy Logic

The article addresses issues related to the breadth and multifaceted aspects of the tourism industry. It discusses the practical benefits of using recommendation systems based on mobile devices. Mobile applications with recom­mendation systems play an important role in the tourism planning process, offering users personalized suggestions that enhance their travel experience. The main focus of this work is on the use of fuzzy logic as the basis for the rec­ommendation system, which allows for a more flexible and accurate suggestion mechanism that takes into account uncertainties and the diversity of user preferences. The methodology proposed by the authors is based on applying a fuzzy content model to the described problems as an effective extension of the collaborative model. The article describes a method for implementing the recommendation system algorithm, lists the technical tools used to imple­ment the application, presents an activity diagram of the working application, describes the process of searching, preparing, and annotating data used in the working application. The presented software and methodological tools help to solve problems associated with the clear categorization of tourist objects within traditional types of tourism, arising from the broad classification of tourist objects, thereby improving the quality of the tourist experience.

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.

Enhancing movie recommendations through comparative analysis of UCB algorithm variants

In the digital realm, recommendation systems are pivotal in shaping user experiences on online platforms, tailoring content based on user feedback. A notable algorithm in this domain is the multi-armed bandit algorithm, with the Upper Confidence Bound (UCB) emerging as a classic and effective variant. This paper delves into an array of Upper Confidence Bound algorithm variations, encompassing UCB1, Asymptotically Optimal UCB, UCB-V, and UCB1Tuned. The research harnesses the MovieLens dataset to assess the performance of these algorithms, employing cumulative regret as the primary metric. For l in UCB1 and c in UCB-V, both oversized and undersized parameters will result in negative outcomes. And UCB1Tuned outperforms the other three algorithms in this experiment, since it considers variance and adjusts parameters dynamically. The study demonstrates that setting a appropriate UCB index is crucial for enhancing the performance of the UCB algorithm in recommendation system. It holds significance for both improve recommendation system algorithms and enhance user experience.

The effects of social media usage on vicarious traumatization and the mediation role of recommendation systems usage and peer communication in China after the aircraft flight accident

ABSTRACT Background: Previous research has indicated that continuous exposure to disaster-related information through social media can lead to vicarious trauma. However, scholars have recognized the need for further in-depth research into the underlying mechanisms influencing this relationship. Objective: The purpose of this study is to investigate the impact mechanism of social media usage on vicarious traumatization in users and analyze the roles of recommendation systems and peer communication. Methods: This study was conducted with college students in China, focusing on the context of the MU5735 aircraft flight accident in China in which 123 passengers and 9 crew members died. Data were collected through an online questionnaire. The partial least square structural equation modelling (PLS-SEM) method was used to test the data and model. Results: This study obtained valid responses from 1317 participants. The study findings revealed a significant positive correlation between social media usage(β = 0.180，P < .001), recommendation systems usage (β = 0.172, P < .001), peer communication (β = 0.303, P < .001), and the development of vicarious traumatization. Recommendation systems usage (specific indirect effect = 0.063, P < .001) and peer communication (specific indirect effect = 0.138, P < .001) mediated the relationship between social media use and vicarious trauma. Additionally, the impact of peer communication on vicarious trauma was found to be higher compared to the effects of continuous social media use and recommendation system use. Conclusion: The study found that the use of social media to obtain information about accidents, the frequent pushing of accident information by recommender systems, and the frequent discussion of accidents among peers during unexpected accidents contribute to vicarious traumatization. The study suggests that users’ reduced retrieval of accident information via social media, as well as reduced peer-to-peer discussions about accidents, and social media platforms’ adjustment of recommender system algorithm rules to reduce accident information pushes, may help reduce the likelihood of users experiencing vicarious traumatization.

The Implementation of Recommender Systems for Mental Health Recovery Narratives: Evaluation of Use and Performance.

Recommender systems help narrow down a large range of items to a smaller, personalized set. NarraGive is a first-in-field hybrid recommender system for mental health recovery narratives, recommending narratives based on their content and narrator characteristics (using content-based filtering) and on narratives beneficially impacting other similar users (using collaborative filtering). NarraGive is integrated into the Narrative Experiences Online (NEON) intervention, a web application providing access to the NEON Collection of recovery narratives. This study aims to analyze the 3 recommender system algorithms used in NarraGive to inform future interventions using recommender systems for lived experience narratives. Using a recently published framework for evaluating recommender systems to structure the analysis, we compared the content-based filtering algorithm and collaborative filtering algorithms by evaluating the accuracy (how close the predicted ratings are to the true ratings), precision (the proportion of the recommended narratives that are relevant), diversity (how diverse the recommended narratives are), coverage (the proportion of all available narratives that can be recommended), and unfairness (whether the algorithms produce less accurate predictions for disadvantaged participants) across gender and ethnicity. We used data from all participants in 2 parallel-group, waitlist control clinical trials of the NEON intervention (NEON trial: N=739; NEON for other [eg, nonpsychosis] mental health problems [NEON-O] trial: N=1023). Both trials included people with self-reported mental health problems who had and had not used statutory mental health services. In addition, NEON trial participants had experienced self-reported psychosis in the previous 5 years. Our evaluation used a database of Likert-scale narrative ratings provided by trial participants in response to validated narrative feedback questions. Participants from the NEON and NEON-O trials provided 2288 and 1896 narrative ratings, respectively. Each rated narrative had a median of 3 ratings and 2 ratings, respectively. For the NEON trial, the content-based filtering algorithm performed better for coverage; the collaborative filtering algorithms performed better for accuracy, diversity, and unfairness across both gender and ethnicity; and neither algorithm performed better for precision. For the NEON-O trial, the content-based filtering algorithm did not perform better on any metric; the collaborative filtering algorithms performed better on accuracy and unfairness across both gender and ethnicity; and neither algorithm performed better for precision, diversity, or coverage. Clinical population may be associated with recommender system performance. Recommender systems are susceptible to a wide range of undesirable biases. Approaches to mitigating these include providing enough initial data for the recommender system (to prevent overfitting), ensuring that items can be accessed outside the recommender system (to prevent a feedback loop between accessed items and recommended items), and encouraging participants to provide feedback on every narrative they interact with (to prevent participants from only providing feedback when they have strong opinions).

Effectiveness of Recommender Systems in Knowledge Discovery

Purpose: The general purpose of the study was to investigate the effectiveness of recommender systems in knowledge discovery.&#x0D; Methodology: The study adopted a desktop research methodology. Desk research refers to secondary data or that which can be collected without fieldwork. Desk research is basically involved in collecting data from existing resources hence it is often considered a low cost technique as compared to field research, as the main cost is involved in executive’s time, telephone charges and directories. Thus, the study relied on already published studies, reports and statistics. This secondary data was easily accessed through the online journals and library.&#x0D; Findings: The findings reveal that there exists a contextual and methodological gap relating to recommender systems in knowledge discovery. The study on the effectiveness of recommender systems in knowledge discovery found that such systems played a pivotal role in facilitating users' exploration of vast information repositories, enabling them to uncover relevant resources and expand their knowledge. It found that recommender systems employing advanced algorithms and personalized techniques demonstrated higher effectiveness in generating relevant recommendations tailored to users' preferences and needs. Additionally, the study highlighted the positive correlation between user engagement metrics and knowledge discovery outcomes, emphasizing the importance of fostering active user participation in the recommendation process. Contextual information was also identified as a crucial factor influencing recommendation effectiveness. Overall, the study underscored the significance of continuous refinement and optimization of recommender system algorithms to enhance knowledge discovery outcomes for users.&#x0D; Unique Contribution to Theory, Practice and Policy: The Social Learning theory, Information Foraging theory and Cognitive Load theory may be used to anchor future studies on recommender systems in knowledge discovery. The study provided recommendations to enhance the efficacy of such systems. It suggested adopting hybrid recommender systems that combine collaborative and content-based filtering techniques to offer more accurate and diverse recommendations. Additionally, the study emphasized the importance of integrating contextual information into recommendation algorithms to dynamically adjust recommendations based on situational context. Furthermore, it recommended the use of explainable AI techniques to improve transparency and user understanding of recommendation processes. Maximizing user engagement through active participation and feedback was also highlighted as crucial, along with prioritizing recommendation diversity to foster exploration and serendipitous discovery of new knowledge resources.

Precision-Driven Product Recommendation Software: Unsupervised Models, Evaluated by GPT-4 LLM for Enhanced Recommender Systems

This paper presents a pioneering methodology for refining product recommender systems, introducing a synergistic integration of unsupervised models—K-means clustering, content-based filtering (CBF), and hierarchical clustering—with the cutting-edge GPT-4 large language model (LLM). Its innovation lies in utilizing GPT-4 for model evaluation, harnessing its advanced natural language understanding capabilities to enhance the precision and relevance of product recommendations. A flask-based API simplifies its implementation for e-commerce owners, allowing for the seamless training and evaluation of the models using CSV-formatted product data. The unique aspect of this approach lies in its ability to empower e-commerce with sophisticated unsupervised recommender system algorithms, while the GPT model significantly contributes to refining the semantic context of product features, resulting in a more personalized and effective product recommendation system. The experimental results underscore the superiority of this integrated framework, marking a significant advancement in the field of recommender systems and providing businesses with an efficient and scalable solution to optimize their product recommendations.

The investigation and application of Muti-Armed algorithms in recommendation systems

In the contemporary Internet recommendation systems in various fields, muti-armed algorithms will show high accuracy and practicability. Internet users can always get abundant positive feedback through the recommendation system via utilizing these algorithms. In this paper, there are three most typical muti-armed algorithms as examples are provided. Explore-Then-Commit (ETC) algorithm is the first to mentioned. The physical meaning of this algorithm is that in the exploration stage, the action will be selected in a certain order, and after a certain number of rounds, the action with the largest average reward will be directly selected. Moreover, Upper Confidence Bond (UCB) algorithm is also a type of pivotal tool. The main function of UCB algorithm is to make the selection by calculating the upper bound of each arm confidence interval instead of the expected reward of the slot machine. Thus, it is an optimistic algorithm. First, select each arm in random order, then calculate the value of the upper bound of each arm confidence interval, and finally, select the arm with the largest value. The last mentioned Thompson Sampling (TS) Algorithm take Bayesian optimization as the theoretical basis. This algorithm takes out the candidate parameters, generates a random number, and selects the maximum value for input. This paper also introduced two fields related to the topic of the application of muti-armed algorithms in the recommendation systems in modern fields. News recommendation algorithms and personalized recommendation systems can be more comprehensive and representative to illustrate the practicality of these algorithms. Therefore, muti-armed algorithms reflect the importance in the recommendation fields via the balance of exploration and exploitation.

Unveiling the Latest Trends and Advancements in Machine Learning Algorithms for Recommender Systems: A Literature Review

This paper presents a comprehensive literature review of the research and application of machine learning (ML) algorithms in recommender systems (RS). The study aims to identify recent trends, explore real-life applications, and guide researchers in positioning their research activities in this domain published in 2023 (Jan-June). The findings are categorized into different domains including education, healthcare, ML algorithms (auto-encoders and reinforcement learning), e-commerce, and digital journalism. The review highlights the enhanced recommendation accuracy, increased scalability, personalization and context awareness, diverse ML techniques, and strategies for handling cold start and data sparsity, and the foundation for future advancements in ML algorithms for RSs considering the application in manufacturing enterprises.

Transparency of algorithms as a legal principle of automated processing of data relating to a person

The article discusses the problems of implementing the principle of transparency of algorithms when using information technology. The computer algorithms underlying the software often remain "black boxes" for individuals. The proposed article substantiates the need for legislative stipulation of the principle of transparency of algorithms. It assumes the openness and accessibility of information about the information used by the algorithm, the sources of obtaining such information, logical circuits and mechanisms for their processing, as well as the nature of the information obtained as a result of processing, the purposes and methods of its use. Noting the positive trends in Russian legislative regulation, the author emphasizes the need to improve legislation. The study was carried out using the comparative legal method. Examples of the legal consolidation of the principle of transparency of algorithms in the legislation of foreign countries are considered. In relation to Russian legislation, gaps in regulation are noted on the basis of the formal legal method, and proposals are formulated to eliminate them. The scientific novelty of the research lies in the formulation of the content of the principle of transparency of algorithms. It is noted that the principle of transparency should be manifested in the realization by individuals of their right to receive reliable, comprehensive and understandable information about the functioning of algorithms, about the information used and about the derived data. It is emphasized that at the level of the federal law, a criterion for the comprehensibility of information for users should be formulated. The position is also expressed that in the case of using algorithms in recommendation systems or in targeted advertising, the user should be able to refuse algorithmic processing of data about him, or limit the use of certain personal information by algorithms.

Comparative analysis of collaborative filtering recommender system algorithms for e-commerce

&lt;p&gt;Collaborative recommender systems are information filtering systems that seek to predict a user’s rating or preference for an item. They play a vital role in various business use cases, such as personalized recommendations, item ranking and sorting, targeted marketing and promotions, content curation and catalog organization, and feedback analysis and quality control. When evaluating these systems, rating prediction metrics are commonly employed. Efficiency, including the prediction time, is another crucial aspect to consider. In this study, the performance of different algorithms was investigated. The study employed a dataset consisting of e-commerce product ratings and assessed the algorithms based on rating prediction metrics and efficiency. The results demonstrated that each algorithm had its own set of strengths and weaknesses. For the metric of Root Mean Squared Error (RMSE), the BaselineOnly algorithm achieved the lowest mean value. Regarding Mean Absolute Error (MAE), the Singular Value Decomposition with Positive Perturbations Singular Value Decomposition with Positive Perturbations (SVDPP) algorithm exhibited the lowest mean value; Mean Squared Error (MSE) also achieved the lowest mean value. Moreover, the BaselineOnly algorithm showcased superior performance with the lowest mean test times when considering efficiency. Researchers and practitioners can use the findings of this study to select the best algorithm for a particular application. Researchers can develop new algorithms that combine the strengths of different algorithms. Practitioners can also use the findings of this study to tune the parameters of existing algorithms.&lt;/p&gt;

Using Graph Neural Networks for Social Recommendations

Recommender systems have revolutionized the way users discover and engage with content. Moving beyond the collaborative filtering approach, most modern recommender systems leverage additional sources of information, such as context and social network data. Such data can be modeled using graphs, and the recent advances in Graph Neural Networks have led to the prominence of a new family of graph-based recommender system algorithms. In this work, we propose the RelationalNet algorithm, which not only models user–item, and user–user relationships but also item–item relationships with graphs and uses them as input to the recommendation process. The rationale for utilizing item–item interactions is to enrich the item embeddings by leveraging the similarities between items. By using Graph Neural Networks (GNNs), RelationalNet incorporates social influence and similar item influence into the recommendation process and captures more accurate user interests, especially when traditional methods fall short due to data sparsity. Such models improve the accuracy and effectiveness of recommendation systems by leveraging social connections and item interactions. Results demonstrate that RelationalNet outperforms current state-of-the-art social recommendation algorithms.

A Recommendation Engine Model for Giant Social Media Platforms using a Probabilistic Approach

Existing recommender system algorithms often find it difficult to interpret and, as a result, to extract meaningful recommendations from social media. Because of this, there is a growing demand for more powerful algorithms that are able to extract information from low-dimensional spaces. One such approach would be the cutting-edge matrix factorization technique. Facebook is one of the most widely used social networking platforms. It has more than one billion monthly active users who engage with each other on the platform by sharing status updates, images, events, and other types of content. Facebook's mission includes fostering stronger connections between individuals, and to that end, the platform employs techniques from recommender systems in an effort to better comprehend the actions and patterns of its users, after which it suggests forming new connections with other users. However, relatively little study has been done in this area to investigate the low-dimensional spaces included within the black box system by employing methods such as matrix factorization. Using a probabilistic matrix factorization approach, the interactions that users have with the posts of other users, such as liking, commenting, and other similar activities, were utilized in an effort to generate a list of potential friends that the user who is the focus of this work may not yet be familiar with. The proposed model performed better in terms of suggestion accuracy in comparison to the original matrix factorization, which resulted in the creation of a recommendation list that contained more correct information.

Implementation of Vikor Algorithm in Web-Based Recommendation System for Obstetrician Selection

The process of childbirth is a natural event for women; with the increase in birth rates, selecting a suitable obstetrician becomes essential. However, many couples find it challenging to choose the right obstetrician, from consultations to hospital births. This study aims to develop an obstetrician recommendation system to overcome decision-making challenges that involve many criteria. The method used is VIseKriterijumska Optimizacija Kompromisno Resenje (VIKOR), which is one of the best methods in Multiple Criteria Decision Making (MCDM) for ranking and selecting alternatives. This method involves several steps, including determining the weight of the criteria, normalizing the matrix, calculating the Utility Measure and Regret Measure, and calculating the VIKOR index. Testing was carried out through scenario tests and user survey tests using the USE questionnaire. The scenario test results show the successful implementation of VIKOR in this system. The results of the user survey test indicated a high level of satisfaction with a score of 83.34%, which fulfilled the four variables in the USE questionnaire: usability (79.76%), ease of use (84.81%), ease of learning (84.81), and satisfaction (83.31%). The results of this study have important implications for increasing the effectiveness of decision-making in selecting the right obstetrician. By incorporating the VIKOR method into an application, this research provides a valuable contribution to developing a VIKOR-based recommendation system. It emphasizes the importance of applying this method in complex decision-making environments.

Fairness in Recommender Systems: Evaluation Approaches and Assurance Strategies

With the wide application of recommender systems, the potential impacts of recommender systems on customers, item providers and other parties have attracted increasing attention. Fairness, which is the quality of treating people equally, is also becoming important in recommender system evaluation and algorithm design. Therefore, in the past years, there has been a growing interest in fairness measurement and assurance in recommender systems. Although there are several reviews on related topics, such as fairness in machine learning and debias in recommender systems, they do not present a systematic view on fairness in recommender systems, which is context aware and has a multi-sided meaning. Therefore, in this review, the concept of fairness is discussed in detail in the various contexts of recommender systems. Specifically, a comprehensive framework to classify fairness metrics is proposed from four dimensions, i.e.,Fairness for Whom,Demographic Unit,Time Frame, andQuantification Method. Then the strategies for eliminating unfairness in recommendations, fairness in different recommendation tasks and datasets are reviewed and summarized. Finally, the challenges and future work are discussed.

Comparative Analysis of Recommendation System Algorithms for Building Recommendation System as a Service

Comparative Analysis of Recommendation System Algorithms for Building Recommendation System as a Service

Artificial Intelligence Algorithms for Collaborative Book Recommender Systems

Book recommender systems provide personalized recommendations of books to users based on their previous searches or purchases. As online trading of books has become increasingly important in recent years, artificial intelligence (AI) algorithms are needed to recommend suitable books to users and encourage them to make purchasing decisions in the short and the long run. In this paper, we consider AI algorithms for so called collaborative book recommender systems, especially the matrix factorization algorithm using the stochastic gradient descent method and the book-based k-nearest-neighbor algorithm. We perform a comprehensive case study based on the Book-Crossing benchmark data set, and implement various variants of both AI algorithms to predict unknown book ratings and to recommend books to individual users based on the highest predicted ratings. This study aims to evaluate the quality of the implemented methods in recommending books by using selected evaluation metrics for AI algorithms.