Search

In response to the COVID-19 crisis, higher education institutions increasingly rely on e-learning systems. Indeed, the higher education market has become increasingly competitive with the addition of open education models. However, the abundance of accessible online courses makes it challenging to deliver education that meets student needs. Learners have diverse profiles based on their traits, motivations, prior knowledge, and learning preferences. Recently, much research has given attention to the importance of using the contextual parameters to perform more accurate recommendations. In this context, context-aware recommendation of pedagogical resources can deal with the issue of information overload, cold start problem and meeting the learner's preferences. This paper describes a context-aware recommender system that harness the learner's contextual information. Our proposed approach is called Context Embedding Deep Collaborative Filtering (CEDCF), which enriches the learner profile with extracted sentiments from previous interactions. The proposed approach comprises three models, called Generalized Matrix Factorzation (GMF) , Multilayer Perceptron (MLP) and Neural Matrix Factorization (NeuMF). The GMF and the MLP are respectively applied to the rating matrix and the contextual parameters. The outputs of these models are then fed into a neural network to perform rating prediction. To put our proposal into shape, we model a real-world application of a merged coursera dataset to recommend courses. The experimental evaluation shows relevant results attesting the efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

Implementing effective content moderation systems at scale is an unavoidable and complex challenge facing technology platforms. Developing systems that automate detection and removal of violative content is fraught with performance, safety and fairness considerations that make their implementation challenging. In particular, content-based systems require large amounts of data to train, cannot be easily transferred between contexts, and are susceptible to data drift. For these reasons, platforms employ a wide range of content classification models and rely heavily on human moderation, which can be prohibitively expensive to implement at scale. To address some of these challenges, we developed a framework that relies on consumption patterns to find high-quality leads for human reviewers to assess. This framework leverages consumption networks, and ranks candidate items for review using two techniques: Mean Percentile Ranking (MPR), which we have developed, and an adaptation of Label Propagation (LP). We demonstrate the effectiveness of this approach to find violative material in production settings using professional reviewers, and on a publicly available dataset from MovieLens. We compare our results with a popular collaborative filtering (CF) baseline, and we show that our approach outperforms CF in production settings. Then, we explore how performance can improve using Active Learning techniques. The key advantage of our approach is that it does not require any content-based data; it is able to find both low- and high-consumption items, and is easily scalable and cost effective to run. [ABSTRACT FROM AUTHOR]

The general personality traits, notably the Big-Five personality traits, have been increasingly integrated into recommendation systems. The personality-aware recommendations, which incorporate human personality into recommendation systems, have shown promising results in general recommendation areas including music, movie, and e-commerce recommendations. On the other hand, the number of research delving into the applicability of personality-aware recommendations in specialized domains such as finance and education remains limited. In addition, these domains have unique challenges in incorporating personality-aware recommendations as domain-specific psychological traits such as risk tolerance and behavioral biases play a crucial role in explaining user behavior in these domains. Addressing these challenges, this study addresses an in-depth exploration of personality-aware recommendations in the financial domain, specifically within the context of stock recommendations. First, this study investigates the benefits of deploying general personality traits in stock recommendations through the integration of personality-aware recommendations with user-based collaborative filtering approaches. Second, this study further verifies whether incorporating domain-specific psychological traits along with general personality traits enhances the performance of stock recommender systems. Thirdly, this paper introduces a personalized stock recommendation model that incorporates both general personality traits and domain-specific psychological traits as well as transaction data. The experimental results show that the proposed model outperformed baseline models in financial stock recommendations. [ABSTRACT FROM AUTHOR]

Recommender systems are currently a suitable alternative for providing easy and appropriate access to information for users in today's digital information-overloaded world. However, an important drawback of these systems is the inconsistent behavior of users in providing item preferences. To address this issue, several natural noise management (NNM) approaches have been proposed, which positively influence recommendation accuracy. However, a major limitation of such previous works is the disregarding of the time-related information coupled to the rating data in RSs. Based on this motivation, this paper proposes two novel methods, named SeqNNM and SeqNNM-p for NNM focused on an incremental, time-aware recommender system scenario that has not yet been considered, by performing a classification-based NNM over specific preference sequences, driven by their associated timestamps. Such methods have been evaluated by simulating a real-time scenario and using metrics such as mean absolute error, root-mean-square error, precision, recall, NDCG, number of modified ratings, and running time. The obtained experimental results show that in the used settings, it is possible to achieve better recommendation accuracy with a low intrusion degree. Furthermore, the main innovation associated with the overall contribution is the screening of natural noise management approaches to be used on specific preferences subsets, and not over the whole dataset as discussed by previous authors. These proposed approaches allow the use of natural noise management in large datasets, in which it would be very difficult to correct the entire data. [ABSTRACT FROM AUTHOR]

Recommendation systems are crucial in boosting companies' revenues by implementing various strategies to engage customers and encourage them to invest in products or services. Businesses constantly desire to enhance these systems through different approaches. One effective method involves using hybrid recommendation systems, known for their ability to create high-performance models. We introduce a hybrid recommendation system that leverages two types of recommendation systems: first, a novel deep learning-based recommendation system that utilizes users' and items' content data, and second, a traditional recommendation system that employs users' past behaviour data. We introduce a novel deep learning-based recommendation system called convolutional autoencoder recommendation system (CAERS). It uses a convolutional autoencoder (CAE) to capture high-order meaningful relationships between users' and items' content information and decode them to predict ratings. Subsequently, we design a traditional model-based collaborative filtering recommendation system (CF) that leverages users' past behaviour data, utilizing singular value decomposition (SVD). Finally, in the last step, we combine the two method's predictions with linear regression. We determine the optimal weight for each prediction generated by the collaborative filtering and the deep learning-based recommendation system. Our main objective is to introduce a hybrid model called CAERS-CF that leverages the strengths of the two mentioned approaches. For experimental purposes, we utilize two movie datasets to showcase the performance of CAERS-CF. Our model outperforms each constituent model individually and other state-of-the-art deep learning or hybrid models. Across both datasets, the hybrid CAERS-CF model demonstrates an average RMSE improvement of approximately 3.70% and an average MAE improvement of approximately 5.96% compared to the next best models. [ABSTRACT FROM AUTHOR]

The evolution of recommendation systems has revolutionized user experiences by providing personalized recommendations. Although conventional systems such as collaborative and content-based filtering are reliable, they still suffer from inherent limitations. We introduce a hybrid recommendation system that combines content-based filtering using TF-IDF and cosine similarity with collaborative filtering and SVD to address these challenges. We bolster our model through supervised machine learning algorithms like decision trees (DT), random forests (RF), and support vector regression (SVR). To amplify predictive prowess, boosting algorithms including CatBoost and XGBoost are harnessed. Our experiments are performed on the benchmark dataset MovieLens 1M, which highlights the superiority of our hybrid method over more traditional alternatives with SVR being the best-performing algorithm consistently. Our hybrid model achieved an MSLE score of 2.3 and an RMSLE score of 1.5, making SVR consistently the best-performing algorithm in the recommendation system. This combination demonstrates the potential of collaborative-content hybrids supported by cutting-edge machine-learning techniques to reshape the field of recommendation systems. [ABSTRACT FROM AUTHOR]

There should be some improvements to increase the performance of Metaverse investments. However, businesses need to focus on the most important actions to provide cost effectiveness in this process. In summary, a new study is needed in which a priority analysis is made for the performance indicators of Metaverse investments. Accordingly, this study aims to evaluate the main determinants of the performance of the metaverse investments. Within this context, a novel model is created that has four different stages. The first stage is related to the prioritizing the experts with artificial intelligence-based decision-making method. Secondly, missing evaluations are estimated by expert recommendation system. Thirdly, the criteria are weighted with Quantum picture fuzzy rough sets-based (QPFR) M-Step-wise Weight Assessment Ratio Analysis (SWARA). Finally, investment decision-making priorities are ranked by QPFR VIKOR (Vlse Kriterijumska Optimizacija Kompromisno Resenje). The main contribution of this study is the integration of the artificial intelligence methodology to the fuzzy decision-making approach for the purpose of computing the weights of the decision makers. Owing to this condition, the evaluations of these people are examined according to their qualifications. This situation has a positive contribution to make more effective evaluations. Organizational effectiveness is found to be the most important factor in improving the performance of metaverse investments. Similarly, it is also identified that it is important for businesses to ensure technological improvements in the development of Metaverse investments. On the other side, the ranking results indicate that regulatory framework is the most critical alternative in this regard. [ABSTRACT FROM AUTHOR]

Memory-based collaborative filtering schemes are among the most effective recommendation technologies in terms of prediction quality, despite commonly facing issues related to accuracy, scalability, and privacy. A prominent approach suggests an intuitively reasonable modification to the similarity function, which has been proven to provide more accurate recommendations than those generated by state-of-the-art memory-based collaborative filtering methods. However, this scheme exacerbates the scalability problem due to additional computational costs and fails to protect individual privacy. In this study, we recommend using a preprocessing method to eliminate relatively dissimilar items from the prediction estimation process, thereby enhancing the scalability of the proposed approach. We explore how to provide recommendations based on the previously proposed similarity function while preserving privacy and propose privacy-preserving schemes to accomplish this task. Additionally, we apply our preprocessing approach to our proposed privacy-preserving schemes to improve both scalability and accuracy. After analyzing our schemes with respect to privacy and additional costs, we conduct experiments with real data to examine the impact of our schemes on scalability and accuracy. The empirical outcomes indicate that our preprocessing scheme significantly alleviates scalability issues in both conventional and privacy-preserving environments and enhances accuracy within privacy-preserving frameworks. [ABSTRACT FROM AUTHOR]

In this study, we propose a novel SeqMF model to solve the problem of predicting the next app launch during mobile device usage. Although this problem can be represented as a classical collaborative filtering problem, it requires proper modification since the data are sequential, the user feedback is distributed among devices, and the transmission of users' data to aggregate common patterns must be protected against leakage. According to such requirements, we modify the structure of the classical matrix factorization model and update the training procedure to sequential learning. Since the data about user experience are distributed among devices, the federated learning setup is used to train the proposed sequential matrix factorization model. One more ingredient of our approach is a new privacy mechanism that guarantees the protection of the sent data from the users to the remote server. To demonstrate the efficiency of the proposed model, we use publicly available mobile user behavior data. We compare our model with sequential rules and models based on the frequency of app launches. The comparison is conducted in static and dynamic environments. The static environment evaluates how our model processes sequential data compared to competitors. The dynamic environment emulates the real-world scenario, where users generate new data by running apps on devices. Our experiments show that the proposed model provides comparable quality with other methods in the static environment. However, more importantly, our method achieves a better privacy-utility trade-off than competitors in the dynamic environment, which provides more accurate simulations of real-world usage. [ABSTRACT FROM AUTHOR]

Traditional collaborative filtering recommendation algorithms suffer from low recommendation efficiency and poor accuracy when calculating similarities between users or items. To address this issue and improve the efficiency of recommendation systems, the paper introduces an algorithm called K-nearest neighbors and non-negative matrix factorization (KNNCNMF) collaborative filtering recommendation algorithm. When calculating the similarity between users or items, the algorithm extracts the latent factors of users and items through matrix decomposition, constructs a low-dimensional dense “user–item factor” matrix, and inputs it into the classifier for rating prediction, which replaces the complex similarity calculation and further improves the efficiency of the user–item similarity calculation. We use performance metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Precision, and Recall to measure our method. The experimental results show that compared to other algorithms, our method improves the MAE metric by 1.78% on average, the RMSE metric by 4.48% on average, the Precision metric by 4.66% on average, and the Recall metric by 7.95% on average. It proves the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Within the realm of social recommendation, a recommender system can enhance its performance through the use of social information among users. Due to the abundance of redundant information in user interactions and social connections, it affects the performance of recommendation results negatively. Existing recommendation models do not distinguish the influence of different users and different friends. To solve this problem, this paper introduces a new recommendation framework, user preference and social relationship-aware light graph convolutional networks (USLGCN). The proposed framework distinguishes between users based on their interactions with items and social relationships to enhance recommendation accuracy. Specifically, we design a subgraph classification strategy that divides the user–item interaction graph and social graph into different subgraphs to capture the impact of various user types on items and friends, thereby reducing negative information and enhancing model resilience. On top of that, we also design a graph fusion module that enhances recommendation performance by fusing data from multiple subgraphs together. Experiments on public datasets show that USLGCN exhibits a 2.6% increase in recall accuracy compared to other social recommendation methods. [ABSTRACT FROM AUTHOR]

The interaction data used for training recommender systems often exhibit a long-tail distribution. Such highly imbalanced data distribution results in an unfair learning process among items. Contrastive learning alleviates the above issue by data augmentation. However, it lacks consideration of the significant disparity in popularity between items and may even introduce false negatives during the data augmentation, misleading user preference prediction. To address this issue, we combine contrastive learning with a weighted model for negative validation. By penalizing identified false negatives during training, we limit their potential harm within the training process. Meanwhile, to tackle the scarcity of supervision signals for unpopular items, we design Popularity Associated Modeling to mine the correlation among items. Then we guide unpopular items to learn hidden features favored by specific users from their associated popular items, which provides effective supplementary information for their representation modeling. Extensive experiments on three real-world datasets demonstrate that our proposed model outperforms state-of-the-art baselines in recommendation performance, with Recall@20 improvements of 4.2%, 2.4% and 3.6% across the datasets, but also shows significant effectiveness in relieving popularity bias. [ABSTRACT FROM AUTHOR]

Cloud application programming interface (API) is a software intermediary that enables applications to communicate and transfer information to one another in the cloud. As the number of cloud APIs continues to increase, developers are inundated with a plethora of cloud API choices, so researchers have proposed many cloud API recommendation methods. Existing cloud API recommendation methods can be divided into two types: content-based (CB) cloud API recommendation and collaborative filtering-based (CF) cloud API recommendation. CF methods mainly consider the historical information of cloud APIs invoked by mashups. Generally, CF methods have better recommendation performances on head cloud APIs due to more interaction records, and poor recommendation performances on tail cloud APIs. Meanwhile, CB methods can improve the recommendation performances of tail cloud APIs by leveraging the content information of cloud APIs and mashups, but their overall performances are not as good as those of CF methods. Moreover, traditional cloud API recommendation methods ignore the complementarity relationship between mashups and cloud APIs. To address the above issues, this paper first proposes the complementary function vector (CV) based on tag co-occurrence and graph convolutional networks, in order to characterize the complementarity relationship between cloud APIs and mashups. Then we utilize the attention mechanism to systematically integrate CF, CB, and CV methods, and propose a model named Content and Complementarity enhanced Attentional Collaborative Filtering (CCeACF). Finally, the experimental results show that the proposed approach outperforms the state-of-the-art cloud API recommendation methods, can effectively alleviate the long tail problem in the cloud API ecosystem, and is interpretable. [ABSTRACT FROM AUTHOR]

In light of the remarkable capacity of graph convolutional network (GCN) in representation learning, researchers have incorporated it into collaborative filtering recommendation systems to capture high-order collaborative signals. However, existing GCN-based collaborative filtering models still exhibit three deficiencies: the failure to consider differences between users' activity and preferences for items' popularity, the low-order feature information of users and items has been inadequately employed, and neglecting the correlated relationships among isomorphic nodes. To address these shortcomings, this paper proposes a degree-aware embedding-based multi-correlated graph convolutional collaborative filtering (Da-MCGCF). Firstly, Da-MCGCF combines users' activity and preferences for items' popularity to perform neighborhood aggregation in the user-item bipartite graph, thereby generating more precise representations of users and items. Secondly, Da-MCGCF employs a low-order feature fusion strategy to integrate low-order features into the process of mining high-order features, which enhances feature representation capabilities, and enables the exploration of deeper relationships. Furthermore, we construct two isomorphic graphs by employing an adaptive approach to explore correlated relationships at the isomorphic level between users and items. Subsequently, we aggregate the features of isomorphic users and items separately to complement their representations. Finally, we conducted extensive experiments on four public datasets, thereby validating the effectiveness of our proposed model. [ABSTRACT FROM AUTHOR]

Recommendation systems are ubiquitous in various domains, facilitating users in finding relevant items according to their preferences. Identifying pertinent items that meet their preferences enables users to target the right items. To predict ratings for more accurate forecasts, recommender systems often use collaborative filtering (CF) approaches to sparse user-rated item matrices. Due to a lack of knowledge regarding newly formed entities, the data sparsity of the user-rated item matrix has an enormous effect on collaborative filtering algorithms, which frequently face lazy learning issues. Real-world datasets with exponentially increasing users and reviews make this situation worse. Matrix factorization (MF) stands out as a key strategy in recommender systems, especially for CF tasks. This paper presents a neural network matrix factorization (NNMF) model through machine learning to overcome data sparsity challenges. This approach aims to enhance recommendation quality while mitigating the impact of data sparsity, a common issue in CF algorithms. A thorough comparative analysis was conducted on the well-known MovieLens dataset, spanning from 1.6 to 9.6 M records. The outcomes consistently favored the NNMF algorithm, showcasing superior performance compared to the state-of-the-art method in this domain in terms of precision, recall, F 1 score , MAE, and RMSE. [ABSTRACT FROM AUTHOR]

In this research, a GAmified Mobile Leaning Framework (GAMOLEAF) developed as a new intelligent application designed for mobile devices to ensure learning, assessing, and advancing learners' knowledge in programming complex data structures in Java programming language. GAMOLEAF adopted motivational strategies to solve motivational problems during the COVID-19 pandemic by employing a gamification module, that integrates levels, scores, badges, leaderboard, and feedback. Furthermore, in order to assist learners to find useful and relevant lessons and best solutions for each data structure, GAMOLEAF incorporated personalized recommendations through two intelligent modules: a Lessons Recommendation Module (LRecM) and a problem-solving Solutions Recommender Module (PSSORecM). LrecM aims to provide learners with personalized lessons depending on the ratings collected explicitly from them. Whereas, PSSORecM bases on learners' behaviors and directs them to consult other solutions. Both modules were based on the collaborative filtering method and used Matrix Factorization (MF) applying Singular Value Decomposition (SVD) and Negative Matrix Factorization (NMF) algorithms, respectively. To explore how the integration of personalized recommendations and gamification impact on students motivation and learning achievements in higher education to learning programming complex data structures course using mobile technologies, especially in difficult times like COVID-19, an experiment was carried out to compare the learning achievement and motivation of 90 students divided into three groups (control group, first experimental group, and second experimental group) using three versions of GAMOLEAF respectively: GAMOLEAF-V1 without gamification and without recommendation, GAMOLEAF-V2 integrating gamification only and GAMOLEAF-V3 integrating both gamification and recommendation. The One-way ANOVA (analysis of variance) test and Post hoc Tukey test were employed to analyze the performances of the three groups before and after the learning activity. The results suggested that the students who learned with GAMOLEAF-V3 using gamification and recommendation achieved significantly better learning achievement than those who learned with GAMOLEAF-V2 and GAMOLEAF-V1. From the experimental results, it was found that the gamification applied in GAMOLEAF-V2 and GAMOLEAF-V3 had significantly better effectiveness in improving only students' motivation without improving their learning achievement. Moreover, the analysis result of the learning achievement indicated that the students in the second experimental group showed significantly higher learning achievement using GAMOLEAF-V3 in comparison with those in both the control group and the first experimental group who used GAMOLEAF-V1 and GAMOLEAF-V2 respectively. Such findings indicate that the personalized recommendations offered by the Lessons Recommendation Module (LRecM) and the problem-solving Solutions Recommender Module (PSSORecM) in GAMOLEAF-V3 may be one of the reasons why the learning achievement of students was increased. [ABSTRACT FROM AUTHOR]

Successful computer-based assessments for learning greatly rely on an effective learner modeling approach to analyze learner data and evaluate learner behaviors. In addition to explicit learning performance (i.e., product data), the process data logged by computer-based assessments provide a treasure trove of information about how learners solve assessment questions. Unfortunately, how to make the best use of both product and process data to sequentially model learning behaviors is still under investigation. This study proposes a novel deep learning-based approach for enhanced learner modeling that can sequentially predict learners' future learning performance (i.e., item responses) based on modeling their history learning behaviors. The evaluation results show that the proposed model outperforms another popular deep learning-based learner model, and process data learning of the model contributes to improved prediction performance. In addition, the model can be used to discover the mapping of items to skills from scratch without prior expert knowledge. Our study showcases how product and process data can be modelled under the same framework for enhanced learner modeling. It offers a novel approach for learning evaluation in the context of computer-based assessments. [ABSTRACT FROM AUTHOR]

Due to the superior performance of graph convolutional networks (GCNs) in feature extraction and representation, researchers have introduced GCNs to collaborative filtering (CF) to improve the accuracy of recommendations. However, existing GCN-based CF models still have three shortcomings: degrading the model performance due to symmetric normalization in neighborhood aggregation, underutilizing the node (user or item) representations at lower layers, and failing to alleviate the over-smoothing effect in graph convolution operations. We present a Residual Graph Convolution Collaborative Filtering model with Asymmetric neighborhood aggregation (ARGCCF) to tackle the above shortcomings. Firstly, ARGCCF utilizes asymmetric normalization in neighborhood aggregation, enabling better preservation of high-degree node information for more precisely learning node representations. Secondly, the propagation of ARGCCF embeddings proceeds in two steps. During the initial propagation, a residual connection is established between the node representation of the current layer and the previous layer to utilize the low-level layer's node representation fully. The embeddings generated after the initial propagation are propagated again in the same graph convolutional layer, which obtains more refined embedding representations to alleviate the over-smoothing problem. Finally, experimentations on five truthful datasets exhibit that ARGCCF has better-improved performance over several mainstream methods. [ABSTRACT FROM AUTHOR]

Graph Neural Networks (GNNs) have been successfully adopted in recommender systems by virtue of the message-passing that implicitly captures collaborative effect. However, in practical recommendation scenarios, user-item interaction data is often sparse and exhibits a skewed distribution. To address these issues, some contrastive learning methods based on data augmentation are applied to recommender systems to enhance the representation of users and items. Nevertheless, many data enhancements solely rely on graph topology, missing crucial structural information and potentially biasing the model. In this paper, we propose a contrastive learning recommendation framework called GDA-GCL based on a generative model data augmentation strategy. Specifically, we use the Conditional Variational Autoencoder(CVAE) generative model to learn the distribution of neighbor node features conditioned on the features of the central node. Due to the randomness of resampling, we design a mirror graph comparison strategy to generate different comparison views, which introduces additional high-quality training signals into the GNN paradigm. Experimental results on three real-world public datasets demonstrate that GDA-GCL achieves significant improvement in performance over various baseline methods. Extensive analysis, including ablation studies, has demonstrated the effectiveness and robustness of our proposed generative data-augmented contrastive recommendation framework in addressing the data sparsity issue in recommendation systems. [ABSTRACT FROM AUTHOR]

Sports recommender systems receive an increasing attention due to their potential of fostering healthy living, improving personal well-being, and increasing performances in sports. These systems support people in sports, for example, by the recommendation of healthy and performance-boosting food items, the recommendation of training practices, talent and team recommendation, and the recommendation of specific tactics in competitions. With applications in the virtual world, for example, the recommendation of maps or opponents in e-sports, these systems already transcend conventional sports scenarios where physical presence is needed. On the basis of different examples, we present an overview of sports recommender systems applications and techniques. Overall, we analyze the related state-of-the-art and discuss future research directions. [ABSTRACT FROM AUTHOR]

Nowadays, the personalized recommendation has become a research hotspot for addressing information overload. Despite this, generating effective recommendations from sparse data remains a challenge. Recently, auxiliary information has been widely used to address data sparsity, but most models using auxiliary information are linear and have limited expressiveness. Due to the advantages of feature extraction and no-label requirements, autoencoder-based methods have become quite popular. However, most existing autoencoder-based methods discard the reconstruction of auxiliary information, which poses huge challenges for better representation learning and model scalability. To address these problems, we propose Serial-Autoencoder for Personalized Recommendation (SAPR), which aims to reduce the loss of critical information and enhance the learning of feature representations. Specifically, we first combine the original rating matrix and item attribute features and feed them into the first autoencoder for generating a higher-level representation of the input. Second, we use a second autoencoder to enhance the reconstruction of the data representation of the prediciton rating matrix. The output rating information is used for recommendation prediction. Extensive experiments on the MovieTweetings and MovieLens datasets have verified the effectiveness of SAPR compared to state-of-the-art models. [ABSTRACT FROM AUTHOR]

Recommender systems are essential tools for many e-commerce services, such as Amazon, Netflix, etc. to recommend new items to users. Among various recommendation techniques, collaborative filtering has shown tremendous performance by using the rating patterns of users. Traditional collaborative filtering, matrix factorization, and deep matrix factorization are the most representative collaborative filtering techniques. However, despite their extensive utility, the selection of the method which provides better recommendation performance is still a major concern in multi-criteria recommender systems. Most recommender systems (RSs) work only on the single criterion rating, i.e., the overall rating. Single-criterion collaborative filtering (CF) generates less reliable recommendations because it suffers from correlation-based similarity problems. However, predictions based on multiple criteria have proven more accurate. This paper compares traditional collaborative filtering, matrix factorization and deep matrix factorization in recommender systems on multi-criteria datasets. We describe details of these techniques in various aspects of recommendation quality, such as how those methods handle cold-start problems, which typically happen in collaborative filtering. We performed several experiments extensively over two real-world datasets to evaluate the performance of each method in terms of qualitative and quantitative measures and observe that deep matrix factorization techniques is superior to all other techniques. [ABSTRACT FROM AUTHOR]

Graph convolutional neural networks have been successfully applied to collaborative filtering to capture high-quality user-item representations. Despite their remarkable performance, there are still limitations that hinder further improvement of recommender systems. Most existing recommendation systems utilize implicit feedback data for model training, but such data inevitably contains adversarial interaction noise. The conventional graph-based collaborative filtering method fails to effectively filter out this noise, and instead amplifies its impact, resulting in degraded model performance. To address this issue, we propose a robustness-enhanced collaborative filtering graph neural network model that does not rely on explicit noise filtering. Our approach involves simulating user-item interactions that do not exist in practice as adversarial interaction noise using random noise. To mitigate the impact of this noise in hidden feedback, we replace them with randomly selected partial nodes based on the principle of mutual information maximization. Our model has been extensively experimented on three public datasets (MovieLens-1 M, Yelp, and Ta-feng) and achieves performance improvements of about 5%, 10%, and 14%, respectively, compared to the state-of-the-art baseline model. In particular, in model robustness experiments, our model achieves significant performance improvements of about 13% and 17% in Yelp and Ta-feng. A comprehensive experimental study shows that our proposed method is reasonably effective and interpretable. [ABSTRACT FROM AUTHOR]

With the rapid development of cloud computing paradigm and mobile devices, the number of cloud services and user interest data are growing explosively. It becomes harder for users to find suitable cloud services within satisfying response time. Thus a suitable cloud service automatic recommendation system is needed to solve the above problem. In this work, we propose KG2Rec, a novel recommendation method based on Knowledge Graph to provide users with appropriate recommendations to meet their real-time needs. The property-specific knowledge graph model is designed to model user–item and item–item bipartite relations. Based on the property-specific knowledge graph model, property-specific user–item relation features can be mined from it. Then the user–item relation features will be integrated into an improved collaborative filtering algorithm based on the local sensitive hash technique for Top-N item recommendation. Finally, we evaluate the proposed method in terms of Top-N recommendation on the MovieLens dataset, and prove it outperforms numbers of state-of-the-art recommendation systems. In addition, we prove it has well performance in term of long tail recommendation and big data processing. [ABSTRACT FROM AUTHOR]

Recommendation system is currently attracting the interest of many explorers. Various new businesses have surfaced with the rise of online marketing (E-Commerce) in response to Covid-19 pandemic. This phenomenon allows recommendation items through a system called Collaborative Filtering (CF), aiming to improve shopping experience of users. Typically, the effectiveness of CF relies on the precise identification of similar profile users by similarity algorithms. Traditional similarity measures are based on the user-item rating matrix. Approximately, four custom ratings (CR) were used along with a new rating formula, termed New Custom Rating (NCR), derived from the popularity of users and items in addition to the original rating. Specifically, NCR optimized recommendation system performance by using the popularity of users and items to determine new ratings value, rather than solely relying on the original rating. Additionally, the formulas improved the representativeness of the new rating values and the accuracy of similarity algorithm calculations. Consequently, the increased accuracy of recommendation system was achieved. The implementation of NCR across four CR algorithms and recommendation system using five public datasets was examined. Consequently, the experimental results showed that NCR significantly increased recommendation system accuracy, as evidenced by reductions in RMSE, MSE, and MAE as well as increasing FCP and Hit Rate. Moreover, by combining the popularity of users and items into rating calculations, NCR improved the accuracy of various recommendation system algorithms reducing RMSE, MSE, and MAE up to 62.10%, 53.62%, 65.97%, respectively, while also increasing FCP and Hit Rate up to 11.89% and 31.42%, respectively. [ABSTRACT FROM AUTHOR]

One of the most important strategies used to mitigate the adverse impacts of traffic growth on mobile networks is caching. By caching at the edge, the backhaul traffic load is reduced, and the quality of service for the user is increased. Developing an effective caching algorithm requires accurate prediction of the future popularity of the content, which is a challenging issue. In recent years, deep learning models have achieved high predictive accuracy due to advancements in data availability and increased computing power. In this paper, we present a caching algorithm called the user preference-aware content caching algorithm (UPACA). This algorithm is specifically designed for an edge content delivery platform where users can access content services provided by a remote content provider. UPACA operates in two steps. In the first step, the proposed collaborative filtering-based popularity prediction algorithm (CFPA) is used to predict future content popularities. CFPA utilizes a gated residual variational autoencoder collaborative filtering model to predict users' future preferences and calculate the future popularity of content. This algorithm considers the popularity of the content as well as the number and timing of content requests. Experimental results demonstrate that UPACA outperforms previous methods in terms of cache hit rates and user utilities. [ABSTRACT FROM AUTHOR]

In recent years, graph neural networks (GNNs) have been widely applied in recommender systems. However, existing recommendation algorithms based on GNNs still face challenges in node aggregation and feature extraction processes because they often lack the ability to capture the interactions between users and items, as well as users' multiple intentions. This hinders accurate understanding of users' needs. To address the aforementioned issues, we propose a recommendation model called multi-intent-aware interactive graph convolutional network (Multi-IAIGCN). This model is capable of integrating multiple user intents and adopts an interactive convolution approach to better capture the information on the interaction between users and items. First, before the interaction between users and items begins, user intents are divided and mapped into a graph. Next, interactive convolutions are applied to the user and item trees. Finally, by aggregating different features of user intents, predictions of user preferences are made. Extensive experiments on three publicly available datasets demonstrate that Multi-IAIGCN outperforms existing state-of-the-art methods or can achieve results comparable to those of existing state-of-the-art methods in terms of recall and NDCG, thus verifying the effectiveness of Multi-IAIGCN. [ABSTRACT FROM AUTHOR]

Recommendation systems (RS) play a crucial role in enhancing conversion rates in e-commerce by offering personalized product recommendations based on customer preferences. However, traditional RS heavily rely on numerical ratings, which might not fully capture the subtle nuances of user preferences. To overcome this limitation, the integration of textual data, such as reviews using sentiment analysis (SA), has gained considerable significance. Nevertheless, effectively analyzing and comprehending unstructured review data presents its own set of challenges. In this work, we propose a novel RS that synergizes collaborative filtering with sentiment analysis to deliver precise and individualized recommendations. Our approach encompasses three main steps: (1) Developing a BERT fine-tuned model for accurate sentiment classification, (2) Creating a hybrid collaborative filtering-based Recommendation Model, and (3) Improving the product selection process in the RS using BERT insights for enhanced recommendation accuracy in the e-commerce domain. Notably, our SA model exhibits remarkable accuracy, achieving 91%, and outperforming state-of-the-art models on a benchmark dataset. Through extensive experimentation and evaluation, we demonstrate that our method significantly improves the accuracy and personalization of the RS, thereby providing customers with a tailored and reliable recommendation service in the e-commerce domain. [ABSTRACT FROM AUTHOR]

Multi-behavior recommendation systems exploit multi-type user–item interactions (e.g., clicking, adding to cart and collecting) as auxiliary behaviors for user modeling, which can alleviate the problem of data sparsity faced by traditional recommendation systems. The key point of multi-behavior recommendation systems is to make full use of the auxiliary behavior information for the learning of user preferences. However, there are two challenges in existing methods that need to be explored: (1) capturing personalized user preferences based on multiple auxiliary behaviors, especially for negative feedback signals; and (2) explicitly modeling the semantics between auxiliary and target behaviors, and learning the explicit interactions between multiple behaviors. To tackle the two problems described above, we propose a novel model, called explicit behavior interaction with heterogeneous graph for multi-behavior recommendation (MB-EBIH). In particular, we first construct a heterogeneous behavior graph, including both positive and negative behaviors. A pre-trained model based on graph neural network (GNN) is then used to generate explicit behavior interaction values as the edge weights for the heterogeneous behavior graph. These weights reflect the importance of each of the auxiliary behaviors in an explicit manner. Finally, the extracted explicit behavior interaction information is incorporated into the multi-behavior user–item bipartite graphs to learn better representations. Experimental results on four real-world datasets demonstrate the effectiveness of our model in terms of exploring multi-behavioral data; and ablation and analysis experiments further demonstrate the effectiveness of explicit behavior interaction information. [ABSTRACT FROM AUTHOR]

In e-commerce recommender systems, the sparsity of user-item rating data limits the quality of semantic embedding representation of users and items, which affects the accuracy of rating prediction. Previous studies have focused on learning attribute features or interaction features of nodes for recommendation and ignore the preference interest of rating tags in terms of attributes. In this paper, we propose a novel fusion representation method of multi-type node feature embedding for recommendation (MultiFEFR). The framework introduces rating preferences in terms of attributes and interactions and develops three kinds of feature presentations including rating-aware interaction feature embedding, rating-aware attribute feature embedding and heterogeneous attribute matched embedding. We design a multi-task joint learning strategy to optimize the accuracy of rating prediction. Experimental results show that the MultiFEFR outperforms the state-of-the-art models in MAE and RMSE metrics. Our findings are that the fusion of multi-type feature embedding can improve the accuracy of recommendation and the preference of attribute and interaction features are very explanatory for score grades. [ABSTRACT FROM AUTHOR]

One of the most effective and extensively used recommendation technique is collaborative filtering. Based on related users or items, collaborative filtering creates recommendations for the users. Similarity measures play a crucial role in Collaborative Filtering Recommender System. One useful similarity measure for a cold-start situation is the Proximity-Impact-Popularity (PIP) measure. The PIP measure is, nevertheless, subject to several limitations as it penalises users' multiple times throughout similarity computation in addition to ignoring their global rating behaviour. When a user rates the items, their overall rating behavior—whether they are lenient or strict—is referred to as global rating behaviour. In this study, we introduce an improved similarity metric to calculate similarity more accurately and generate high-quality recommendations. Our method takes into account both the user's rating behaviour and the percentage of co-rated items among users. Additionally, we have considered the computation complexity of the suggested work. In addition, to exhibit the performance of the proposed measure, empirical analysis has been done on real datasets. The results of the experiments performed on the dataset show that the suggested work takes precedence over the current similarity metrics. In comparison to state-of-the-art measurements, the suggested work exhibits improvements in MAE of 1.73%, RMSE of 4.01%, and F measure of 1.47% on an average. [ABSTRACT FROM AUTHOR]

The personalized product preference and decision-making recommendation systems are highly demanded to handle big data and to increase service quality of the e-commerce platforms in the competitive industries. Previous recommender systems were hard coded and only extracted items from the same category. With this tactic, customers are limited to viewing only one category of products; items with several categories cannot be viewed. A concern for the e-commerce sector, particularly in the healthcare and pharmaceutical industries, is the growth of consumer preferences, the issue of cold starts, and the huge number of stocks holding units for new items. Therefore, this study aims to develop a product recommendation system for an e-commerce platform which deals with health supplements. For this reason, collaborative and content-based filtering are combined to propose a hybrid recommender system. In the proposed hybrid model, user's actions are converted into implicit rating weightage first. Then, to tackle the problem of increasing customer preferences, collaborative filtering is used to generate user's rating for warm-start items. Moreover, content-based filtering is used to solve cold start problem by recommending products to the users based on the similarity of the products regardless of user profile. Term frequency- inverse document frequency (TF-IDF) algorithm is adopted to weight the feature from the dataset first, then it creates step-by-step cosine similarity table. Finally, the proposed hybrid model is evaluated based on error metrices, ranking metrices, and business metrics and then compared based on the standard benchmarking algorithms. The best algorithm is selected to be used for the system development. Finally, the proposed hybrid model is developed and integrated into the real online e-commerce platform for healthcare company to handle the large number of stocks keeping units, cold start issues, and increasing customer preferences. This study can assist the healthcare companies to recommend relevant products to their customers and to help them stay competitive in healthcare e-commerce industry. [ABSTRACT FROM AUTHOR]

The rapid development of the Internet and information technology has caused a surge in the amount of information in the network, and the problem of "information overload" has affected the user experience. The research object of this paper is the movie recommendation system, mainly from the algorithm of recommendation technology, and the recommendation effect is verified by simulation experiments on the Movielens dataset. High-utility association rule mining is applied to the recommendation algorithm, and the sparse scoring matrix is filled with high-utility itemsets. The experimental results show that the proposed high-efficiency mining method can effectively fill the user rating matrix, and its precision is increased by 9.59% compared with the traditional algorithm, the recall rate is increased by 8.97%, and the coverage rate is increased by 9.30%.It is proposed that the temporal distance is used to process the user rating time series, and then the temporal similarity is used to calculate the user interest. The experimental results show that the precision of the proposed method is improved by 1.32% and the recall rate is improved by 1.57% compared with the above algorithms. This method can also be applied to other recommender systems. [ABSTRACT FROM AUTHOR]

Nowadays, Deep learning (DL) techniques have been proven successful as learning techniques in various research fields ranging from computer vision to social networks. The approach of DL is flourishing in the field of recommender systems (RS). Researchers have deployed metadata or auxiliary information using DL approaches in diverse applications in the last decade to achieve better recommendation accuracy. Thus, the metadata plays a vital role in obtaining a better user-item interaction. At the same time, existing techniques are based on fixed user and item factors. Therefore, the model does not correctly identify actual latent factors representation, resulting in a high prediction error. To handle this problem, a user metadata embedding using a deep autoencoder RS model called "Metadata Embedding Deep AutoEncoder (MEDAE)" based collaborative filtering is proposed. MEDAE model takes embeds user metadata such as demographics along with the rating data. The MEDAE model consists of an embedding layer, Encoder, and Decoder. The embedding layer generates embedding or latent features of the users, items, and metadata; Encoder receives concatenated features of the user, item, and metadata, then encodes the inputs and passes them to the decoder; and the decoder reconstructs the output. To test the effectiveness of proposed model Root Mean Squared Error and Mean Absolute Error measures are used. Different architectures (like Big-Small-Big (BSB) (5), BSB (3), Small-Big-Small (3), and SBS (5)) of the MEDAE model are evaluated on MovieLens datasets along with different parameters such as activation functions (ELU and SELU) and regularization and results concluded that the MEDAE with SBS (3) and ELU + SELU component improves 4% of RMSE and 2% MAE over the baseline methods. [ABSTRACT FROM AUTHOR]

Researchers would like to publish their research articles in reputed journals along with quick review time. However, with the growing number of academic publications, it is becoming more difficult for scholars to find venues that are relevant to their domain. This study aims on the development of a technique that focuses on the priorities of the researchers that are linked to the recommendation of suitable suggestion of publication journal. The developed Recommendation System (RS) takes title, abstract, and keyword of the manuscript to be submitted. The proposed algorithm, named PUB-VEN which is hybridization of Content-Based Filtering (CBF), and Collaborative Filtering (CF), which is integrated with the Multi-Criteria Decision Making (MCDM) process to provide suitable journal recommendations by considering the researcher's point of view about different attributes gathered such as impact factor, eigen factor, average review time, etc. which affect the research process effectively. Our results demonstrate that the PUB-VEN provides better recommendations in comparison with state-of-the-art algorithms such as Term Frequency and Inverse Document Frequency (TF-IDF) and Latent Semantic Analysis (LSA). The study concluded that PUB-VEN is providing better precision, recall, F1 Score, Discounted Cumulative Gain (DCG), and Normalized DCG (NCDG). For precision, the gain ranges from 1% to 16%, the improvement in recall is between 33% and 3%, the betterment of result in F1 is by the ratio which ranges from 27% and 2%, the improvement in the result of DCG lies between 15% and 5% and the result of NDCG gain ranges from 6% to 1%. It is useful for the researchers in finding suitable venue for publication. [ABSTRACT FROM AUTHOR]

The personalized recommendation has already taken a crucial role in online services to alleviate information overload. However, most existing works pay their attention to user interest modeling with a uniform embedding, which inevitably results in suboptimal recommendations. We argue that users' diverse and mixed interests are positively related to their interacted items with mutual effects, and they are partially matched in decision-making. This work introduces a novel dual interest activation network (DIAN), which forms dual embedding learning of users and items with a dynamic activation for personalized recommendation. By modeling mutual effects between users and items, DIAN constructs dual embedding learning on their identites (IDs) and neighbor groups to encode their diverse and mixed composition of interests implicitly. Specifically, considering the partial matching scenario, we introduce a dynamic interest activation with pairwise matching motivated attention on aggregating neighbor groups of users and items. Experimental analysis verifies the significance of mutual effects and dynamic matching, illustrating the effectiveness of DIAN for personalized recommendation. [ABSTRACT FROM AUTHOR]

Recommendation techniques play a vital role in recommending an actual product to an intended user. The recommendation also supports the user in the decision-making process. In recent years, collaborative filtering has been a widely used technique in recommender systems. A model-based CF technique called matrix factorization fills the user–item interaction matrix’s missing elements. One of the significant challenges in MF is filling those elements in a row or column. The user has a few observations about an item, leading to sparsity issues of collaborative filtering. Therefore, conventional MF alone is not suitable to address the new item or user problem. We propose an MF model that integrates user-side information to handle these issues. We integrate user-side information in terms of vectors and bias to overcome the sparsity problem of collaborative filtering. We exhaustively evaluate our model on real-world datasets for predicting the ratings. The experiment results and analysis demonstrate that the proposed approach improves predictions significantly compared to the state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Social Media (SM) has become a popular medium for individuals to share their opinions on various topics, including politics, social issues, and daily affairs. During controversial events such as political elections, active users often proclaim their stance and try to persuade others to support them. However, disparities in participation levels can lead to misperceptions and cause analysts to misjudge the support for each side. For example, current models usually rely on content production and overlook a vast majority of civically engaged users who passively consume information. These "silent users" can significantly impact the democratic process despite being less vocal. Accounting for the stances of this silent majority is critical to improving our reliance on SM to understand and measure social phenomena. Thus, this study proposes and evaluates a new approach for silent users' stance prediction based on collaborative filtering and Graph Convolutional Networks, which exploits multiple relationships between users and topics. Furthermore, our method allows us to describe users with different stances and online behaviors. We demonstrate its validity using real-world datasets from two related political events. Specifically, we examine user attitudes leading to the Chilean constitutional referendums in 2020 and 2022 through extensive Twitter datasets. In both datasets, our model outperforms the baselines by over 9% at the edge- and the user level. Thus, our method offers an improvement in effectively quantifying the support and creating a multidimensional understanding of social discussions on SM platforms, especially during polarizing events. [ABSTRACT FROM AUTHOR]

Two important challenges in recommender systems are modeling users with heterogeneous taste and providing explainable recommendations. In order to improve our understanding of the users in light of these challenges, we developed the attentive multi-persona collaborative filtering (AMP-CF) model. AMP-CF breaks down the user representation into several latent "personas" (profiles) that identify and discern a user's tastes and inclinations. Then, the exposed personas are used to generate, explain, and diversify the recommendation list. As such, AMP-CF offers a unified solution for both aforementioned challenges. We demonstrate AMP-CF on four collaborative filtering datasets from the domains of movies, music, and video games. We show that AMP-CF is competitive with state-of-the-art models in terms of accuracy while providing additional insights for explanations and diversification. [ABSTRACT FROM AUTHOR]

Collaborative filtering is a powerful marketing tool capable of improving the customer experience and increasing sales. Segmentation of the customer base by collaborative filtering assumes that those interested in specific products will also be interested in similar products. The basic methods of collaborative filtering are analyzed in the present work. The analysis reveals what factors affect the selection of a collaborative filtering method in segmentation of the retail customer base. [ABSTRACT FROM AUTHOR]

In recent years, the Internet has had a main and important contribution to human life and the amount of data on the World Wide Web such as books, movies, videos and, etc. increase rapidly. Recommender systems allow users to quickly access items that are closer to their interests. One of the most popular and easiest models of recommender systems is the Collaborative Filtering (CF) model, which uses the items ratings given by users. The important challenge of CF is robust against the attacks which manipulated by fake users to reduce the efficiency of the system. Therefore, the impact of attacks on the item recommendations will increase and fake items will be easily recommended to users. The purpose of this paper is to design a robust CF recommender system, T&TRS, Time and Trust Recommender System, against user attacks. Our proposed system improves the performance of users clustering for detecting the fake users based on a novel community detection algorithm that is introduced in this paper. Our proposed system calculates the reliably value for all items ratings and tags them as suspicious or correct. T&TRS considered the rating time and implicit and explicit trust among users for constructing the weighted user-user network and detects communities as the nearest neighbors of the users to predict unknown items ratings. After detecting the suspect users and items using a novel community detection method, our proposed system removes them from rating matrix and predict the rating of unobserved items and generate the Top@k items according to the user interests. We inject the random and average attacks into the Epinion data set and evaluate our proposed systems based on Precision, Recall, F1, MAE, RMSE, and RC measures before and after attacks. The experimental results indicated that the precision of items recommendations increase after attack detection and show the effectiveness of T&TRS in comparison to the two base K-means methods such as KMCF-U, KMCF-I and graph-based methods such as TRACCF, and TOTAR. [ABSTRACT FROM AUTHOR]

In today's technologically evolved world, users have become accustomed to personalized tools that provide accurate and precise recommendations that consider their needs and interests, leading to a perceived reduction in information overload in a fiercely competitive marketplace. However, sparsity issues render the effective prediction infeasible and hamper the performance of the recommendation, as users typically only rate a small proportion of the offered items. To solve these problems, we propose, in this paper, a novel hybrid model named Kernelized Finetuned Deep Belief Network (KFDBN) for accurate rating prediction and efficient Top-k recommendation. First, we learn a deep generative model using a Deep Belief Network (DBN) to capture higher-level latent feature representations of users and items to effectively predict missing entries in the rating matrix. Next, we present the practical KFDBN approach to seamlessly incorporate features extracted by the generative model into kernel-based feature extraction. Subsequently, KFDBN is leveraged to learn reliable hidden features that improve the performance of sparse recommendations. Finally, we introduce the KFDBN-based imputation technique to create a denser user-item interaction matrix for a relevant item ranking in the Top-k recommendation. Experimental evaluations on six datasets in various domains reveal that the proposed generative model enhances the accuracy of rating prediction and outperforms the state-of-the-art methods by 21.32% and 16.35% in RMSE and MAE, respectively, averaging on all used datasets. Moreover, the KFDBN exceeds baseline approaches and enhances the Top-k recommendation performance by 5.2% and 8.1% in HR@10 and NDCG@10, respectively, averaging on the six datasets. [ABSTRACT FROM AUTHOR]

Developing online educational platforms necessitates the incorporation of new intelligent procedures in order to improve long-term student experience. Presently, e-learning Recommender Systems rely on deep learning methods to recommend appropriate e-learning materials to the students based on their learner profiles. Fine-grained sentiment analysis (FSA) can be leveraged to enrich the recommender system. Users posted reviews and rating data are vital in accurately directing the student to the appropriate e-learning resources based on posted comments by comparable learners. Innovative has been made in this work to propose a new e-learning recommendation system based on individualization and FSA. A new framework is proposed based on collaborative filtering models (CFMs) integrating with fine-grained sentiment analysis (FSA) for hybrid recommendation (CFISAR) for effective recommendations. CFMs attempt to capture the learner's latent factors based on their selections of interest to build the learner profile. FSA models are introduced to deliver e-content with the highest ranked ratings related to the learner's area and interests based on the extracted learner model. Moreover, a new approach is proposed to update the system continuously and not keep it bound to certain items by adding new books, where the initial rating of these new books is predicted based on FSA models. CFISAR is explored utilizing six CFMs to generate the prediction matrix and derive the learner model, resulting in a low MSE of 0.699 for Asymmetric SVD. The system used multiplication word embeddings for stronger corpus representation that were trained on a dataset generated for an educational context, and leveraging the goodness of deep learning, which predicted an accuracy of 0.9264% for the Peephole algorithm, that performed better than other models. [ABSTRACT FROM AUTHOR]

Collaborative filtering is a popular approach in recommender systems, whose objective is to provide personalized item suggestions to potential users based on their purchase or browsing history. However, personalized recommendations require considerable amount of behavioral data on users, which is usually unavailable for new users, giving rise to the cold-start problem. To help alleviate this challenging problem, we introduce a spectral graph wavelet collaborative filtering framework for implicit feedback data, where users, items and their interactions are represented as a bipartite graph. Specifically, we first propose an adaptive transfer function by leveraging a power transform with the goal of stabilizing the variance of graph frequencies in the spectral domain. Then, we design a deep recommendation model for efficient learning of low-dimensional embeddings of users and items using spectral graph wavelets in an end-to-end fashion. In addition to capturing the graph’s local and global structures, our approach yields localization of graph signals in both spatial and spectral domains and hence not only learns discriminative representations of users and items, but also promotes the recommendation quality. The effectiveness of our proposed model is demonstrated through extensive experiments on real-world benchmark datasets, achieving better recommendation performance compared with strong baseline methods. [ABSTRACT FROM AUTHOR]

To eliminate the concerns of cold-start and scalability within the filtering, collaborative recommendation system for a hotel under the ranking list for the customer; this study proposed an extensive data analysis for such an application. Alongside, the application is very user-friendly. Technology keeps growing daily and is also very helpful in the future. This paper brings out the innovation. This approach configures the latest variant of CNN termed as Capsule Network (CapsNet) to recommend the best suited hotel based on user collaboration. With the help of this application, we can make precise and accurate recommendations to the user. Besides, generally employed, the procedure adopted for the model recommended integrated with the filtering practice that includes analyzing user's preferences and making product or service recommendations through a similarity index among the ratings specified in the database. Finally, the merging technique employed in the system is discussed and evaluated on standard data sets based on the general architectural design of the recommendation system. An enhanced strategy attains fusion idea of filtering technique in collaborative to classified data for addressing this issue. To put the proposed approach to the test, we employ hotel recommendation data. Also, the outcome proved the best findings of the comprehensive list taken as the top listed hotels from which the scale has been considered through the proposed method. [ABSTRACT FROM AUTHOR]

The collaborative model is the needed framework to find a good product in both user- and budget-friendly. These collaborative filtering models have provided product recommendations based on the ratings. Recently, neural networks such as Convolution neural models, recurrent neural networks, boosting models and optimization procedures were implemented for the recommendation system to find the accurate product rating. But, due to the vast amount of data, less accuracy score was reported for finding the book ratings. Considering these issues, the collaborative filtering model has been introduced in the recommendation system. However, this collaborative filtering is only effective for small data, and large data requires additional intelligent models that have maximized the error rate. So, the current research article has aimed to design a novel chimp-based Deep Neural Collaborative Filtering (CbDNCF) for the recommendation system. Initially, the dataset was filtered in a preprocessing layer of the novel CbDNCF. Consequently, the noiseless data is trained in the classification layer. Further, the feature extraction and highest rating prediction process were performed. Incorporating the Chimp functions in the deep neural classification layer has afforded the finest forecasting outcomes. Consequently, the designed model is tested using the Python programming language with book product datasets. Its robustness is measured by measuring the key metrics with other existing models. Hence, the planned approach has earned good prediction results of 97.7% accuracy and the lowest error rate of 0.02%, which is quite better than the associated models. [ABSTRACT FROM AUTHOR]

The multimodal side information such as images and text have been commonly used as supplements to improve graph collaborative filtering recommendations. However, there is often a semantic gap between multimodal information and collaborative filtering information. Previous works often directly fuse or align these information, which results in semantic distortion or degradation. Additionally, multimodal information also introduces additional noises, and previous methods lack explicit supervision to identify these noises. To tackle the issues, we propose a novel contrastive learning approach to improve graph collaborative filtering, named Multimodal-Side-Information-enriched Contrastive Learning (MSICL), which does not fuse multimodal information directly, but still explicitly captures users' potential preferences for similar images or text by contrasting ID embeddings, and filters noises in multimodal side information. Specifically, we first search for samples with similar images or text as positive contrastive pairs. Secondly, some searched sample pairs may be irrelevant, so we distinguish the noise by filtering out sample pairs that have no interaction relationship. Thirdly, we contrast the ID embeddings of the true positive sample pairs to excavate the potential similarity relationship in multimodal side information. Extensive experiments on three datasets demonstrate the superiority of our method in multimodal recommendation. Moreover, our approach significantly reduces computation and memory cost compared to previous work. [ABSTRACT FROM AUTHOR]

The growth of music streaming market is expected to be boosted by the rising use of smart devices and the streaming platforms in the forecast period. Music recommendation systems for groups have been intensively studied as the application scenario becomes more dynamic, where different kinds of group formulations lead to different levels of similarity in music tastes. This paper proposes a music recommendation framework to generate a Top-N list in high-similar, high-dissimilar, and regular groups. Additionally, we investigate the performance of the recommendation system in a wide range of aspects, including precision, ranking quality, and novelty. Based on the listening frequency of each user and for each track, implicit feedback is also derived from the track popularity. To prevent popularity bias, we combine track popularity and group popularity into latent factor models to improve the performance of the recommendation algorithm. As a result of our evaluation, we found that the proposed methods provided excellent recommendations regarding accuracy, diversity, and novelty. [ABSTRACT FROM AUTHOR]

Currently, generative applications are reshaping different fields, such as art, computer vision, speech processing, and natural language. The computer science personalization area is increasingly relevant since large companies such as Spotify, Netflix, TripAdvisor, Amazon, and Google use recommender systems. Then, it is rational to expect that generative learning will increasingly be used to improve current recommender systems. In this paper, a method is proposed to generate synthetic recommender system datasets that can be used to test the recommendation performance and accuracy of a company on different simulated scenarios, such as large increases in their dataset sizes, number of users, or number of items. Specifically, an improvement in the state-of-the-art method is proposed by applying the Wasserstein concept to the generative adversarial network for recommender systems (GANRS) seminal method to generate synthetic datasets. The results show that our proposed method reduces the mode collapse, increases the sizes of the synthetic datasets, improves their ratings distributions, and maintains the potential to choose the desired number of users, number of items, and starting size of the dataset. Both the baseline GANRS and the proposed Wasserstein-based WGANRS deep learning architectures generate fake profiles from dense, short, and continuous embeddings in the latent space instead of the sparse, large, and discrete raw samples that previous GAN models used as a source. To enable reproducibility, the Python and Keras codes are provided in open repositories along with the synthetic datasets generated to test the proposed architecture (https://github.com/jesusbobadilla/ganrs.git). [ABSTRACT FROM AUTHOR]

The cold start problem has always been a major challenge for recommender systems. It arises when the system lacks rating records for new users or items. Addressing the challenge of providing personalized recommendations in the cold start scenario is crucial. This research proposes a new hybrid recommender system named CoDFi-DL which combines demographic and enhanced collaborative filtering. The demographic filtering is performed through a deep neural network (DNN) and used to solve the new user cold start problem. The enhanced collaborative filtering component of our model focuses on delivering personalized recommendations through a neighborhood-based method. The major contribution in this research is the DNN-based demographic filtering which overcomes the new user cold start problem and enhances the collaborative filtering process. Our system significantly improves the relevancy of the recommendation task and thus provides personalized recommended items to cold users. To evaluate the effectiveness of our approach, we conducted experiments on real multi-label datasets, 1M and 100K MovieLens. CoDFi-DL recommender system showed higher performance in comparison with baseline methods, achieving lower RMSE rates of 0.5710 on the 1M MovieLens dataset and 0.6127 on the 100K MovieLens dataset. [ABSTRACT FROM AUTHOR]