Explore the vast range of titles available.

The latest advance in recommendation shows that better user and item representations can be learned via performing graph convolutions on the user-item interaction graph. However, such finding is mostly restricted to the collaborative filtering (CF) scenario, where the interaction contexts are not available. In this work, we extend the advantages of graph convolutions to context-aware recommender system (CARS, which represents a generic type of models that can handle various side information). We propose Graph Convolution Machine (GCM), an end-to-end framework that consists of three components: an encoder, graph convolution (GC) layers, and a decoder. The encoder projects users, items, and contexts into embedding vectors, which are passed to the GC layers that refine user and item embeddings with context-aware graph convolutions on the user-item graph. The decoder digests the refined embeddings to output the prediction score by considering the interactions among user, item, and context embeddings. We conduct experiments on three real-world datasets from Yelp and Amazon, validating the effectiveness of GCM and the benefits of performing graph convolutions for CARS.

Exploiting temporal context has been proved to be an effective approach to improve recommendation performance, as shown, e.g. in the Netflix Prize competition. Time-aware recommender systems (TARS) are indeed receiving increasing attention. A wide range of approaches dealing with the time dimension in user modeling and recommendation strategies have been proposed. In the literature, however, reported results and conclusions about how to incorporate and exploit time information within the recommendation processes seem to be contradictory in some cases. Aiming to clarify and address existing discrepancies, in this paper we present a comprehensive survey and analysis of the state of the art on TARS. The analysis show that meaningful divergences appear in the evaluation protocols used—metrics and methodologies. We identify a number of key conditions on offline evaluation of TARS, and based on these conditions, we provide a comprehensive classification of evaluation protocols for TARS. Moreover, we propose a methodological description framework aimed to make the evaluation process fair and reproducible. We also present an empirical study on the impact of different evaluation protocols on measuring relative performances of well-known TARS. The results obtained show that different uses of the above evaluation conditions yield to remarkably distinct performance and relative ranking values of the recommendation approaches. They reveal the need of clearly stating the evaluation conditions used to ensure comparability and reproducibility of reported results. From our analysis and experiments, we finally conclude with methodological issues a robust evaluation of TARS should take into consideration. Furthermore we provide a number of general guidelines to select proper conditions for evaluating particular TARS.

In the Big Data era, every sector has adapted to technological development to service the vast amount of information available. In this way, each field has benefited from technological improvements over the years. The cultural and artistic field was no exception, and several studies contributed to the aim of the interaction between human beings and artistic-cultural heritage. In this scenario, systems able to analyze the current situation and recommend the right services play a crucial role. In particular, in the Recommender Systems field, Context-Awareness helps to improve the recommendations provided. This article aims to present a general overview of the introduction of Context analysis techniques in Recommender Systems and discuss some challenging applications to the Cultural Heritage field.

Recommender systems have been widely adopted by electronic commerce and entertainment industries for individualized prediction and recommendation, which benefit consumers and improve business intelligence. In this article, we propose an innovative method, namely the recommendation engine of multilayers (REM), for tensor recommender systems. The proposed method utilizes the structure of a tensor response to integrate information from multiple modes, and creates an additional layer of nested latent factors to accommodate between-subjects dependency. One major advantage is that the proposed method is able to address the “cold-start” issue in the absence of information from new customers, new products or new contexts. Specifically, it provides more effective recommendations through sub-group information. To achieve scalable computation, we develop a new algorithm for the proposed method, which incorporates a maximum block improvement strategy into the cyclic blockwise-coordinate-descent algorithm. In theory, we investigate algorithmic properties for convergence from an arbitrary initial point and local convergence, along with the asymptotic consistency of estimated parameters. Finally, the proposed method is applied in simulations and IRI marketing data with 116 million observations of product sales. Numerical studies demonstrate that the proposed method outperforms existing competitors in the literature.

Recommender Systems (RSs) are often assessed in off-line settings by measuring the system precision in predicting the observed user’s ratings or choices. But, when a precise RS is on-line, the generated recommendations can be perceived as marginally useful because lacking novelty. The underlying problem is that it is hard to build an RS that can correctly generalise, from the analysis of user’s observed behaviour, and can identify the essential characteristics of novel and yet relevant recommendations. In this paper we address the above mentioned issue by considering four RSs that try to excel on different target criteria: precision, relevance and novelty. Two state of the art RSs called SKNN and s-SKNN follow a classical Nearest Neighbour approach, while the other two, Q-BASE and Q-POP PUSH are based on Inverse Reinforcement Learning. SKNN and s-SKNN optimise precision, Q-BASE tries to identify the characteristics of POIs that make them relevant, and Q-POP PUSH, a novel RS here introduced, is similar to Q-BASE but it also tries to recommend popular POIs. In an off-line experiment we discover that the recommendations produced by SKNN and s-SKNN optimise precision essentially by recommending quite popular POIs. Q-POP PUSH can be tuned to achieve a desired level of precision at the cost of losing part of the best capability of Q-BASE to generate novel and yet relevant recommendations. In the on-line study we discover that the recommendations of SKNN and Q-POP PUSH are liked more than those produced by Q-BASE. The rationale of that was found in the large percentage of novel recommendations produced by Q-BASE, which are difficult to appreciate. However, Q-BASE excels in recommending items that are both novel and liked by the users.

Explainable recommendations have drawn more attention from both academia and industry recently, because they can help users better understand recommendations (i.e., why some particular items are recommended), therefore improving the persuasiveness of the recommender system and users’ satisfaction. However, little work has been done to provide explanations from the angle of a user’s contextual situations (e.g., companion, season, and destination if the recommendation is a hotel). To fill this research gap, we propose a new context-aware recommendation algorithm based on supervised attention mechanism (CAESAR), which particularly matches latent features to explicit contextual features as mined from user-generated reviews for producing context-aware explanations. Experimental results on two large datasets in hotel and restaurant service domains demonstrate that our model improves recommendation performance against the state-of-the-art methods and furthermore is able to return feature-level explanations that can adapt to the target user’s current contexts.

A rapid growth in multimedia on various application platforms has made essential the provision of additional assistive technologies to handle information overload issues. Consequently, various multimedia recommendation systems have been developed by the research community. Among these Neural Collaborative Filtering (NCF) is one of the most commonly adopted recommendation frameworks. In this research, we argue that weighing contextual features can help the underlined learning model to develop a better understanding of a user’s behavior. We propose a Weighted Context-based Neural Collaborative Filtering (WNCF) model to supplement weighted contextual information into NCF for learning the user–item interaction function with respect to the different contextual conditions. We introduced an interactive mechanism for addressing the user ratings on items in various contextual situations. Learned contextual weights describe the importance of each item in specific contextual conditions. The proposed model can also assign different weights to the contextual conditions depending on their significance. We performed extensive experiments on three real-world datasets and the outcomes demonstrate the significance of our proposal in comparison with the state-of-the-art models. Empirical results highlight that integrating weighted contextual information with NCF has enhanced recommendation performance. Also, the in-depth analysis leads us toward a completely new research direction on context-aware recommender systems.

The recommender system’s primary purpose is to estimate the user’s desire and provide a list of items predicted from the appropriate information. Also, context-aware recommendation systems are becoming more and more favorite since they could provide more accurate or personalized recommendation information than traditional recommendation techniques. However, a context-aware recommendation system suffers from two fundamental limitations known as cold start and sparse data. Singular value decomposition has been successfully integrated with some traditional recommendation algorithms. However, the basic singular value decomposition can only extract the feature vectors of users and items, resulting in lower recommendation precision. To improve the recommendation performance and reduce the challenge of cold start and sparse data, we propose a new context-aware recommendation algorithm, named CSSVD. First, in the CSSVD matrix, using the IFPCC and DPCC similarity criteria, the item’s user property attribute matrices are created, respectively, creating the SSVD matrix for the cold start problem. In the second step, through the CWP similarity criterion on the contextual information, the context matrix is created, which according to the SSVD matrix created in the previous step, creates a three-dimensional matrix based on tensor properties, providing the problem of sparse data. We have used the IMDB and STS data collection because of implementing user features, item features, and contextual data for analyzing the recommended method. Experiential results illustrate that the proposed algorithm CSSVD is better than TF, HOSVD, BPR, and CTLSVD in terms of Precision, Recall, F-score, and NDCG measure.Results show the improvement of the recommendations to users through alleviating cold start and sparse data.

Additional context information is vital for context-aware recommender systems. The whole paradigm of context-aware recommender systems is built upon the availability of contextual features. Apart from the significance of context, we highlight a key issue for existing context-aware recommendation paradigm that if the user environment did not provide contextual features such as time, location, or companion due to privacy constraints or if the data collection system is unable to record contextual attributes due to legal or technical concerns then the existing context-aware recommendation paradigm has no uniform mechanism to deal with this situation. In this research, we address these challenges and propose a novel item-context similarity (ICS) model capable of adaptively generating reliable collaborators for a subject user on a subject item. Additionally, ICS is fused into a weighting model called contextually reliable collaborators (CRC) that considers the current item context, the nonlinear relationship between candidate collaborators and the asymmetry between rating preferences of users to finally generate rating prediction. Experiments show that neighbors computed through ICS are more reliable than the classical similarity estimation methods and the ICS-based CRC model has outperformed state-of-the-art approaches.

Recommender systems are able to suggest the most suitable items to a given user, taking into account the user’s and item`s data. Currently, these systems are offered almost everywhere in the online world, such as in e-commerce websites, newsletters, or video platforms. To improve recommendations, the user’s context should be considered to provide more accurate algorithms able to achieve higher payoffs. In this paper, we propose a pre-filtering recommendation system that considers the context of a coworking building and suggests the best workplaces to a user. A cyber-physical context-aware multi-agent system is used to monitor the building and feed the pre-filtering process using fuzzy logic. Recommendations are made by a multi-armed bandit algorithm, using ϵ -greedy and upper confidence bound methods. The paper presents the main results of simulations for one, two, three, and five years to illustrate the use of the proposed system.