Collaborative Filtering Methods Research Articles

ANALYSIS OF CONTENT RECOMMENDATION METHODS IN INFORMATION SERVICES

The object of the research is the process of selecting a content recommendation method in information services. The study's relevance stems from the rapid development of informational and entertainment resources and the increasing volume of data they operate on, thus prompting the utilisation of recommendation systems to maintain user engagement. Considering the different types of content, it is necessary to address the problem of data filtration based on their characteristics and user preferences. To solve this task, we analysed content-based and collaborative filtering methods using various techniques (model-based, memory-based, and hybrid collaborative filtering techniques), knowledge-based filtering, and hybrid filtering methods. Considering each method's advantages and disadvantages, we chose a hybrid method using model-based collaborative filtering and content-based filtering for the future development of our universal recommendation system.

Towards similar alignment and unique uniformity in collaborative filtering

Representation learning, with its desired properties, including Alignment and Uniformity, has recently emerged as an effective approach in collaborative filtering (CF) for recommender systems. Alignment measures the distance between positive pairs, and uniformity describes the distribution of all samples on the unit hypersphere. Despite the effectiveness of existing research, the challenges of insufficient alignment and uniformity bias persist in studies on the desired properties of recommender systems: (1) Sparse interaction information leads to an insufficient alignment representation. (2) Calculating the uniformity loss based on duplicate samples introduces bias, which affects the overall representation uniformity.Building on aforementioned challenges, we propose a Similar Alignment and Unique Uniformity model called SUAU. SUAU mitigates insufficient alignment by introducing additional item-similar item pairs for model training and employing a uniqueness strategy to prevent uniformity bias. More specifically, we propose a similar items generation method that identifies the most similar items based on the interaction behavior of the original items’ related users to form item-similar item pairs. The experimental results obtained on three highly sparse datasets demonstrate that the propose model achieves superior alignment and uniformity compared with state-of-the-art models, notably surpassing the best CF methods in terms of recommendation performance. We have open-sourced the source code on a publicly accessible website: https://github.com/ZzYUuuu/SUAU.

Embedding Enhancement Method for LightGCN in Recommendation Information Systems

In the modern digital age, users are exposed to a vast amount of content and information, and the importance of recommendation systems is increasing accordingly. Traditional recommendation systems mainly use matrix factorization and collaborative filtering methods, but problems with scalability due to an increase in the amount of data and slow learning and inference speeds occur due to an increase in the amount of computation. To overcome these problems, this study focused on optimizing LightGCN, the basic structure of the graph-convolution-network-based recommendation system. To improve this, techniques and structures were proposed. We propose an embedding enhancement method to strengthen the robustness of embedding and a non-combination structure to overcome LightGCN’s weight sum structure through this method. To verify the proposed method, we have demonstrated its effectiveness through experiments using the SELFRec library on various datasets, such as Yelp2018, MovieLens-1M, FilmTrust, and Douban-book. Mainly, significant performance improvements were observed in key indicators, such as Precision, Recall, NDCG, and Hit Ratio in Yelp2018 and Douban-book datasets. These results suggest that the proposed methods effectively improved the recommendation performance and learning efficiency of the LightGCN model, and the improvement of LightGCN, which is most widely used as a backbone network, makes an important contribution to the entire field of GCN-based recommendation systems. Therefore, in this study, we improved the learning method of the existing LightGCN and changed the weight sum structure to surpass the existing accuracy.

Exploring collaborative filtering through K-Nearest Neighbors and Non-Negative Matrix Factorization

Collaborative filtering (CF) algorithms have received a lot of interest in recommender systems due to their ability to give personalized recommendations by exploiting user-item interaction data. In this article, we explore two popular CF methods—K-Nearest Neighbors (KNN) Regression and Non-Negative Matrix Factorization (NMF)—in detail as we dig into the world of collaborative filtering. Our goal is to evaluate their performance on the MovieLens 1M dataset and offer information about their advantages and disadvantages. A thorough explanation of the significance of recommender systems in contemporary content consumption settings is given at the outset of our examination. We look into Collaborative Filtering's complexities and how it uses user choices to produce tailored recommendations. Then, after setting the scene, we explain the KNN Regression and NMF approaches, going over their guiding principles and how they apply to recommendation systems. We conduct an extensive investigation of KNN Regression and NMF on the MovieLens 1M dataset to provide a thorough evaluation. We describe the model training processes, performance measures, and data pre-processing steps used. We measure and analyse the predicted accuracy of these strategies using empirical studies, revealing light on their effectiveness when applied to various user preferences and content categories.

A collaborative filtering method by fusion of facial information features

Personalized recommendation systems fundamentally assess user preferences as a reflection of their emotional responses to items. Traditional recommendation algorithms, focusing primarily on numerical processing, often overlook emotional factors, leading to reduced accuracy and limited application scenarios. This paper introduces a collaborative filtering recommendation method that integrates features of facial information, derived from emotions extracted from such data. Upon user authorization for camera usage, the system captures facial information features. Owing to the diversity in facial information, deep learning methods classify these features, employing the classification results as emotional labels. This approach calculates the similarity between emotional and item labels, reducing the ambiguity inherent in facial information features. The fusion process of facial information takes into account the user’s emotional state prior to item interaction, which might influence the emotions generated during the interaction. Variance is utilized to measure emotional fluctuations, thereby circumventing misjudgments caused by sustained non-interactive emotions. In selecting the nearest neighboring users, the method considers not only the similarity in user ratings but also in their emotional responses. Tests conducted using the Movielens dataset reveal that the proposed method, modeling facial features, more effectively aligns recommendations with user preferences and significantly enhances the algorithm’s performance.

GCNSLIM: Graph convolutional network with sparse linear methods for e-government service recommendation

E-government service recommendation aims to find target service items for users based on their preferences, behaviors and other information, which is one of the key technologies for information overload in e-government cloud platforms. However, it has not received adequate attention in comparison to other recommendation scenarios like news and music recommendation. Graph Convolutional Networks (GCNs) have made significant strides in Collaborative Filtering (CF) recommendations. However, existing GCN-based CF methods are mainly based on matrix factorization (MF) and incorporate some optimization techniques (e.g., contrastive learning) to enhance performance, which are not enough to handle the complexities of diverse real-world recommendation scenarios. We empirically find that when existing GCN-based CF methods are directly applied to e-government service recommendation, they are limited by the MF framework and showing poor performance. This is attributed to the fact that the equal treatment of users and items by MF is not appropriate for scenarios where the number of users and items is unbalanced. In this work, we propose a new model, GCNSLIM, which combines GCN and sparse linear methods (SLIM) instead of combining GCN and MF to accommodate e-government service recommendation. In particular, GCNSLIM explicitly injects high-order collaborative signals obtained from multi-layer light graph convolutions into the item similarity matrix in the SLIM framework, effectively improving the recommendation accuracy. In addition, we propose two optimization measures, removing layer 0 embedding and adding nonlinear activation, to further adapt to the characteristics of e-government service recommendation scenarios. Furthermore, we propose a joint optimization mode to enhance the adaptability for more diverse recommendation scenarios. We conduct extensive experiments on a real e-government service dataset and two common public datasets and demonstrate the effectiveness of GCNSLIM in recommendation accuracy and operational performance. Our implementation is available at https://github.com/songkk5/GCNSLIM.

HYBRID RECOMMENDER FOR VIRTUAL ART COMPOSITIONS WITH VIDEO SENTIMENTS ANALYSIS

Topicality. Recent studies confirm the growing trend to implement emotional feedback and sentiment analysis to improve the performance of recommender systems. In this way, a deeper personalization and current emotional relevance of the user experience is ensured. The subject of study in the article is a hybrid recommender system with a component of video sentiment analysis. The purpose of the article is to investigate the possibilities of improving the effectiveness of the results of the hybrid recommender system of virtual art compositions by implementing a component of video sentiment analysis. Used methods: matrix factorization methods, collaborative filtering method, content-based method, knowledge-based method, video sentiment analysis method. The following results were obtained. A new model has been created that combines a hybrid recommender system and a video sentiment analysis component. The average absolute error of the system has been significantly reduced. Added system reaction to emotional feedback in the context of user interaction with virtual art compositions. Conclusion. Thus, the system can not only select the most suitable virtual art compositions, but also create adaptive and dynamic content, which will increase user satisfaction and improve the immersive aspects of the system. A promising direction of further research may be the addition of a subsystem with a generative neural network, which will create new virtual art compositions based on the conclusions of the developed recommendation system.

Less is More: Removing Redundancy of Graph Convolutional Networks for Recommendation

While Graph Convolutional Networks (GCNs) have shown great potential in recommender systems and collaborative filtering (CF), they suffer from expensive computational complexity and poor scalability. On top of that, recent works mostly combine GCNs with other advanced algorithms which further sacrifice model efficiency and scalability. In this work, we unveil the redundancy of existing GCN-based methods in three aspects: (1) Feature redundancy . By reviewing GCNs from a spectral perspective, we show that most spectral graph features are noisy for recommendation, while stacking graph convolution layers can suppress but cannot completely remove the noisy features, which we mostly summarize from our previous work; (2) Structure redundancy . By providing a deep insight into how user/item representations are generated, we show that what makes them distinctive lies in the spectral graph features, while the core idea of GCNs (i.e., neighborhood aggregation) is not the reason making GCNs effective; and (3) Distribution redundancy . Following observations from (1), we further show that the number of required spectral features is closely related to the spectral distribution, where important information tends to be concentrated in more (fewer) spectral features on a flatter (sharper) distribution. To make important information be concentrated in as few features as possible, we sharpen the spectral distribution by increasing the node similarity without changing the original data, thereby reducing the computational cost. To remove these three kinds of redundancies, we propose a Simplified Graph Denoising Encoder (SGDE) only exploiting the top- K singular vectors without explicitly aggregating neighborhood, which significantly reduces the complexity of GCN-based methods. We further propose a scalable contrastive learning framework to alleviate data sparsity and to boost model robustness and generalization, leading to significant improvement. Extensive experiments on three real-world datasets show that our proposed SGDE not only achieves state-of-the-art but also shows higher scalability and efficiency than our previously proposed GDE as well as traditional and GCN-based CF methods.

A Study on the Precision Effect of Blended Learning in English Teaching and Learning

Abstract Realizing personalized and precise teaching using traditional English methods is challenging. This paper proposes a blended precision teaching model that relies on student portraits, using technical methods to provide tailored learning resources for every student. A deep neural network is used to extract student features, and the k-means algorithm is used to construct a clustered portrait of students. Based on the student portraits, the similarity between student objects is calculated, and the collaborative filtering method is combined to achieve personalized recommendations for English learning resources. And the learning warning model is established by considering the ranking order relationship when predicting students’ English scores. Setting up the experimental class and the control class to analyze the effect of blended teaching precision, in terms of English scores, the average score of the experimental class is 6.06 points higher than that of the control class, with a significant P-value of less than 0.05, which shows a considerable difference. Its classroom teaching observation dimension score totaled 91.6, students’ classroom performance and teaching effect performed well, English literacy was improved, and the mean values of each satisfaction of emotional experience showed significant differences (P<0.05). The mean values of several dimensions of learning motivation were higher than those of the control class, with highly significant differences in the dimensions of extrinsic goal orientation, learning beliefs, and intrinsic goal orientation (P<0.01).

Aplikasi Rekomendasi Pemesanan Paket Wisata Menggunakan Metode Collaborative Filltering

The advancement of information technology has led to the rapid growth of tourism information, causing difficulties for tourists to find relevant information according to their needs. Recommendation systems are one of the solutions to recommend tourist destinations based on user preferences. Tourism has become an industry that provides significant benefits to a region. Therefore, tourist attractions need to be developed to achieve maximum results. There are various impacts of tourism development, one of which is the improvement of the local economy in tourist areas. Yogyakarta is one of the cities with various tourist attractions and is a popular destination for people living in Central Java, specifically. However, the abundance of tourist destinations poses a challenge for tourists in making decisions. Tourism recommendations are made based on various factors, such as ticket prices, the distance of the tourist destination from the user's current location on maps, and facilities. The technique used is Collaborative Filtering (CF). Using this technique can provide accurate recommendations to each user. In this research, the Collaborative Filtering method is used to build a recommendation system by finding similarities among users.

Current Situation and Practical Path of Cultivating Students’ Core Literacy in the Context of the New Era

Abstract In this paper, Bayesian estimation and Coleman filtering are used to compose a multidimensional data fusion algorithm to study the cultivation of students’ personalized core literacy. A Trans E model is constructed based on the calculation of students’ specific course ratings using collaborative filtering algorithms. Combining the knowledge graph and collaborative filtering methods, the similarities between the course and user ratings are calculated respectively. The user’s rating situation can be predicted by combining similarity. Through the empirical analysis method, the overall and specific competency dimensions of students’ core literacy and the effect of core literacy cultivation, as well as students’ satisfaction, were analyzed, and the corresponding practice paths were proposed based on the analysis results. The mean value of students’ core literacy test is 46.25, and the number of students scoring between 50-60 points is the largest, but the number of excellent students is 0, which is poor in the cultivation of core literacy. The analysis of the effect of core literacy cultivation shows that in the correlation analysis of teaching effect and teaching support, the p-value is less than 0.01, but most of the correlation coefficients are less than 0.35, and there exists a weak relationship between the two, and the school authorities should strengthen the teaching support of core literacy.

A highly scalable CF recommendation system using ontology and SVD-based incremental approach

In recent years, the need of recommender systems has increased to enhance user engagement, provide personalized services, and increase revenue, especially in the online shopping industry where vast amounts of customer data are generated. Collaborative filtering (CF) is the most widely used and effective approach for generating appropriate recommendations. However, the current CF approach has limitations in addressing common recommendation problems such as data inaccuracy recommendations, sparsity, scalability, and significant errors in prediction. To overcome these challenges, this study proposes a novel hybrid CF method for movie recommendations that combines the incremental singular value decomposition approach with an item-based ontological semantic filtering approach in two phases, online and offline. The ontology-based technique is leveraged to enhance the accuracy of predictions and recommendations. Evaluating our method on a real-world movie recommendation dataset using precision, F1 scores, and mean absolute error (MAE) demonstrates that our system generates accurate predictions while addressing sparsity and scalability issues in recommendation system. Additionally, our method has the advantage of reduced running time.

Enhancing Recommendation System using Ontology-based Similarity and Incremental SVD Prediction

Background: With the explosion of data in recent years, recommender systems have become increasingly important for personalized services and enhancing user engagement in various industries, including e-commerce and entertainment. Collaborative filtering (CF) is a widely used approach for generating recommendations, but it has limitations in addressing issues such as sparsity, scalability, and prediction errors. Methods: To address these challenges, this study proposes a novel hybrid CF method for movie recommendations that combines an incremental singular value decomposition approach with an item-based ontological semantic filtering approach in both online and offline phases. The ontology-based technique improves the accuracy of predictions and recommendations. The proposed method is evaluated on a real-world movie recommendation dataset using several performance metrics, including precision, F1 scores, and MAE. Results: The results demonstrate that the proposed method outperforms existing methods in terms of accuracy while also addressing sparsity and scalability issues in recommender systems. Additionally, our approach has the advantage of reduced running time, making it a promising solution for practical applications. Conclusion: The proposed method offers a promising solution to the challenges faced by traditional CF methods in recommender systems. By combining incremental SVD and ontological semantic filtering, the proposed method not only improves the accuracy of predictions and recommendations but also addresses issues related to scalability and sparsity. Overall, the proposed method has the potential to contribute to the development of more accurate and efficient recommendation systems in various industries, including e-commerce and entertainment.

A Systematic Review on Recommendation Systems Developed for the Field of Adult Education

Today, the changing job performances and the desire of individuals to improve themselves have created the desire of people to quickly reach the content that is suitable for them. The use of suggestion systems designed to identify the needs of individuals and present the most appropriate content is considered as a solution method in this regard. The aim of this systematic study is to determine the trends in the field by making a comprehensive analysis about what kind of suggestions are given in the studies on the recommendation systems used and designed in the field of adult education, in which year the studies were conducted, the research method used, the filtering methods used and the algorithms used, and to identify the trends in this field to establish an up-to-date basis for new entrants. As a result of the review made in various databases, 113 studies were reached, and a systematic analysis of 75 studies that met the inclusion criteria was carried out. As a result of the review, it was seen that the most content suggestions were made, the most publications were made in 2020, the research method focused on determining the system performance and promoting, and a limited number of experimental studies were included. It has been determined that the most collaborative filtering method is used, and content-based and hybrid filtering methods are less preferred. It has been concluded that the K nearest neighbor algorithm is used much more than other algorithms, and besides this algorithm, artificial neural networks, support vector machines, decision trees and newly proposed algorithms by the researchers are also included. In line with the results obtained, investigations were made and suggestions were made for practice and research for future studies.

Item Attribute-aware Graph Collaborative Filtering

Collaborative filtering (CF) is a widely used technique in recommender systems. While many CF methods primarily focus on collaborative signals derived from user–item interactions, they often overlook other types of similarities (e.g., user similarity in loving actors, movie similarity in sharing genres, etc.). These similarities offer the fine-grained knowledge to understand users and items, which can complement the collaborative signal. In this paper, we introduce a model that harnesses these additional similarities for improved recommendations. Our approach involves constructing both a user and an item relational graph, based on multiple item attributes. These graphs reflect semantic similarities from various perspectives among users and items. Then, we develop a recommendation framework that employs a dual graph neural network, integrating these graphs into the recommendation process. We name our approach Item Attribute-aware Graph Collaborative Filtering (IAGCF). Through evaluations on six real-world datasets, we found that IAGCF surpasses several state-of-the-art recommenders.

Probabilistic Matrix Factorization Recommendation Approach for Integrating Multiple Information Sources

Most previous studies on matrix factorization (MF)-based collaborative filtering (CF) have focused solely on user rating information for predicting recommendations. However, to further enhance the performance of recommender systems (RSs), it is important to also consider review information and rating reliability in the model. This article proposes a new probabilistic MF (PMF)-based CF method that integrates multiple information sources to provide reliable predictions. First, we introduce a sentiment-based PMF to handle user reviews and fit the normalized sentiment information obtained from our previously proposed sentiment analysis method. We also consider the helpfulness of reviews to highlight their reliability and effectiveness in this model. Subsequently, our proposed noise detection method is adopted to determine the reliability of user ratings, and then the rating matrix is transformed into a binary reliability matrix. A rating reliability-based PMF through Bernoulli distribution is then proposed to factorize it. To effectively integrate three types of information (ratings, reviews, and rating reliability) into a PMF procedure, we design a weight matrix using the proposed weighting strategy to generate a set of comprehensive prediction ratings with corresponding reliability probabilities. Experiments on four Amazon datasets demonstrate that our model outperforms comparison methods in terms of comprehensive evaluation.

Improving Collaborative Filtering Recommendations with Tag and Time Integration in Virtual Online Communities

In recent years, virtual online communities have experienced rapid growth. These communities enable individuals to share and manage images or websites by employing tags. A collaborative tagging system (CTS) facilitates the process by which internet users collectively organize resources. CTS offers a plethora of useful information, including tags and timestamps, which can be utilized for recommendations. A tag represents an implicit evaluation of the user’s preference for a particular resource, while timestamps indicate changes in the user’s interests over time. As the amount of information increases, it is feasible to integrate more detailed data, such as tags and timestamps, to improve the quality of personalized recommendations. The current study employs collaborative filtering (CF), which incorporates both tag and time information to enhance recommendation precision. A computational recommender system is established to generate weights and calculate similarities by incorporating tag data and time. The effectiveness of our recommendation model was evaluated by linearly merging tag and time data. In addition, the proposed CF method was validated by applying it to big data sets in the real world. To assess its performance, the size of the neighborhood was adjusted in accordance with the standard CF procedure. The experimental results indicate that our proposed method significantly improves the quality of recommendations compared to the basic CF approach.

Uninteresting Items: Concept and Its Application to Effective Collaborative Filtering in Recommender Systems

Recommender systems aim to predict user preferences by analyzing users' past behavior. Collaborative filtering (CF) is one of the key techniques employed in recommender systems that uses explicit ( e.g. , ratings) and implicit ( e.g. , browsing) feedback from users to predict unknown feedback, providing top- N recommendations. However, CF faces challenges when dealing with sparse data, which can decrease the accuracy of recommendations. To overcome these inherent challenges in recommender systems, this article introduces the concept of "uninteresting items" that have not been rated by a user, but are unlikely to be liked even when recommended. We then review our previous works that utilize both positive preferences from rated items and negative preferences from uninteresting items to improve recommendation accuracy. Specifically, we discuss a family of our eight CF methods that are assisted by the uninteresting items: Zero-injection (ZI), l -injection, Imputation, RAGAN, and Deep-ZI, which are designed for explicit feedback, as well as gOCCF, M-BPR, and CNS, which are designed for implicit feedback. Also, we report some evaluation results for showing their effectiveness.

Research on personalized recommendation method of preschool e-learning resources

Abstract E-learning is a very popular learning method at this stage, and Internet learners need to invest much time to retrieve the required e-learning network resources. In building the existing e-learning resources, the cognitive level, thinking ability, learning style, and other factors of learners are not considered. For this challenge, the paper gives the recommendation methods of the collaborative filtering algorithm model and learner model, compares the advantages and disadvantages of these models and traditional recommendation methods using the data of mean square error, response time, and accuracy, and examines the students’ suggestions for this recommendation method in the field. The collaborative filtering recommendation technique had the highest completion rate, above 0.7 for 5-20 recommendations and above 0.75 and 0.8 for 20-35. The rate of the learner model is stable between 0.7 and 0.8. In contrast, the detection rate of traditional methods is between 0.6 and 0.7. The collaborative filtering recommendation method outperforms the other two methods regarding completeness, response time, accuracy, and F1 value. In terms of satisfaction, the collaborative filtering recommendation algorithm had the highest satisfaction rate, followed by the learner model; the collaborative filtering method had the best results in improving learning performance. Therefore, personalized recommendation methods can improve learning efficiency and reduce retrieval time, and the collaborative filtering recommendation method is the most effective among the two methods proposed in this paper.

Factoring textual reviews into user preferences in multi-criteria based content boosted hybrid filtering (MCCBHF) recommendation system

Recommendation systems help customers to find interesting and valuable resources in the internet services. Their priority is to create and examine users’ individual profiles, which contain their preferences, and then update their profile content with additional features to finally increase the users’ satisfaction. Specific characteristics or descriptions and reviews of the items to recommend also play a significant part in identifying the preferences. However, inferring the user’s interest from his activities is a challenging task. Hence it is crucial to identify the interests of the user without the intervention of the user. This work elucidates the effectiveness of textual content together with metadata and explicit ratings in boosting collaborative techniques. In order to infer user’s preferences, metadata content information is boosted with user-features and item-features extracted from the text reviews using sentiment analysis by Vader lexicon-based approach. Before doing sentiment analysis, ironic and sarcastic reviews are removed for better performance since those reviews inverse the polarity of sentiments. Amazon product dataset is used for the analysis. From the text reviews, we identified the reasons that would have led the user to the overall rating given by him, referred to as features of interest (FoI). FoI are formulated as multi-criteria and the ratings for multiple criteria are computed from the single rating given by the user. Multi-Criteria-based Content Boosted Hybrid Filtering techniques (MCCBHF) are devised to analyze the user preferences from their review texts and the ratings. This technique is used to enhance various collaborative filtering methods and the enhanced proposed MCKNN, MCEMF, MCTFM, MCFM techniques provide better personalized product recommendations to users. In the proposed MCCBHF algorithms, MCFM yields better results with the least RMSE value of 1.03 when compared to other algorithms.