Context-aware Recommender Systems Research Articles

Fast Convolutional Factorization Machine with Enhanced Robustness

Recently, factorization machine and its variants have shown promising results for context-aware recommender systems (CARS), especially when combined with deep neural networks. Among them, convolutional factorization machine (CFM) is a prominent example. The key to the success of CFM is its 3D convolutional architecture for capturing complex interactions on top of embedded features. However, the resultant computational cost can also be demanding. Moreover, the feature embedding scheme of CFM and other factorization models can be potentially vulnerable to noise. To tackle these issues, in this study we propose two models, namely, the fast convolutional factorization machine (FCFM) that slims down the complete pairwise feature interaction for higher computational efficiency, and adversarial fast convolutional factorization machine (AFCFM) that further enhances the robustness of the model by introducing adversarial noise to the feature interaction image generated by the model. Experimental results on four benchmark datasets prove that the proposed FCFM is nearly five times faster than CFM with competitive performance, while AFCFM improves the performance of the state-of-the-art models by about 8\% with higher efficiency than CFM.

Context-aware recommender system for adaptive ubiquitous learning

Context-aware recommender system for adaptive ubiquitous learning

Context-Aware Recommender System for Adaptive Ubiquitous Learning

The use of context-aware recommender systems for adaptive ubiquitous learning has become a promising and interesting research direction in recent years, both as a result of the vast use of ubiquito...

MyDigitalFootprint: An extensive context dataset for pervasive computing applications at the edge

The widespread diffusion of connected smart devices has greatly contributed to the rapid expansion and evolution of the Internet at its edge, where personal mobile devices follow the behavior of their human users and interact with other smart objects located in the surroundings. In such a scenario, the user context is represented by a large variety of information that can rapidly change, and the ability of personal mobile devices to locally process this data is fundamental to make the system able to quickly adapt its behavior to the current situation. This ability, in practice, can be represented by a single elaboration process integrated in the final user application, or by a middleware platform aimed at implementing different context processing and reasoning to support third-party applications. However, the lack of public datasets that take into account the complexity of the user context in the mobile environment strongly limits the advance of the research in this field.In this paper, we present MyDigitalFootprint, a novel large-scale dataset composed of smartphone embedded sensors data, physical proximity information, and Online Social Networks interactions aimed at supporting multimodal context-recognition and social relationships modeling. The dataset includes two months of measurements and information collected from the personal mobile devices of 31 volunteer users, in their natural environment, without limiting their usual behavior. Existing public datasets generally consist of a limited set of context data, aimed at optimizing specific application domains (human activity recognition is the most common example). On the contrary, our dataset contains a comprehensive set of information describing the user context in the mobile environment. In order to demonstrate the efficacy of the proposed dataset, we present three context-aware applications based on different machine learning tasks: (i) a social link prediction algorithm based on physical proximity data, (ii) the recognition of daily-life activities based on smartphone-embedded sensors data, and (iii) a pervasive context-aware recommender system. To the best of our knowledge, this is the first large-scale dataset containing such heterogeneity of information, representing an invaluable source of data to validate new research in mobile and edge computing.

Graph Neural Network and Context-Aware Based User Behavior Prediction and Recommendation System Research.

Due to the influence of context information on user behavior, context-aware recommendation system (CARS) has attracted extensive attention in recent years. The most advanced context-aware recommendation system maps the original multi-field features into a shared hidden space and then simply connects it to a deep neural network (DNN) or other specially designed networks. However, for different areas, the ability of modeling complex interactions in a sufficiently flexible and explicit way is limited by the simple unstructured combination of feature fields. Therefore, it is hard to get the accurate results of the user behavior prediction. In this paper, a graph structure is used to establish the interaction between context and users/items. Through modeling user behavior, we can explore user preferences in different context environments, so as to make personalized recommendations for users. In particular, we construct a context-user and context-item interactions graph separately. In the interactions graph, each node is composed of a user feature field, an item feature field, and a feature field of different contexts. Different feature fields can interact through edges. Therefore, the task of modeling feature interaction can be transformed into modeling the node interaction on the corresponding graph. To this end, an innovative model called context-aware graph neural network (CA-GNN) model is designed. Furthermore, in order to obtain more accurate and efficient recommendation results, first, we innovatively use the attention mechanism to improve the interpretability of CA-GNN; second, we innovatively use the degree of physical fatigue features which has never been used in traditional CARS as critical contextual feature information into our CA-GNN. We simulated the Food and Yelp datasets. The experimental results show that CA-GNN is better than other methods in terms of root mean square error (RMSE) and mean absolute error (MAE).

How does context influence music preferences: a user-based study of the effects of contextual information on users’ preferred music

To simplify effective music filtering, recommender systems (RS) have received great attention from both industry and academia area. To select which music to recommend, traditional RS uses an approximation of users’ real interests. However, while discarding users’ contexts, profiles information is not able to reflect their exact needs and to provide overpowering recommendations. One of the main issues that have to be considered before the conception of context-aware recommender systems (CARS) is the estimation of the relevance of contextual information. The use of irrelevant or superfluous contextual factors can generate serious problems about the complexity and the quality of recommendations. In this paper, we introduce a multi-dimensional context model for music CARS. We started by the acquisition of explicit items rating from a population in various possible contextual situations. Thus, we proposed a user-based methodology aiming to judge the relation between contextual factors and musical genres. Next, we applied the Multiple Linear Regression technique on users’ perceived ratings, to define an order of importance between contextual dimensions. We described raw collected data with basic statistics about the created dataset. We also summarized the key results and discussed key findings. Finally, we propose a new framework for Music CARS.

CAMO: A context-aware movie ontology generated from LOD and movie databases

An ontology is a formal representation of domain knowledge as a set of concepts and their relationships in structured format. Besides various applications, ontology has been frequently used for the development of movie recommender systems that aim to predict the rating a user would give to a movie. Though recommender system is a well-studied research field, issues like cold-start, data sparsity, limited-content, and long tail are still open challenges. Context-aware recommender systems have been considered by many researchers to deal with some of these issues. However, non-existence of domain ontology containing contextual information is the major hindrance for the development of such systems. This is mainly due to the fact that datasets used in most of the existing context-aware recommender systems are either synthetic or generated through surveys. In this paper, we present the development of a context-aware movie ontology (CAMO) that contains movie concepts, relationships, and various representational and interactional contextual features. Since existing movie databases do not contain all contextual features, we have generated a real-world movie dataset from Linked Open Data (LOD) and movie databases like IMDB and Rotten Tomatoes that contain complete context-based movie profiles. CAMO contains the conceptualization of total 1103 movies. Since users generally express their opinion over the interactional features like story, direction, music, visual effects, etc. of the movies, CAMO also contains aspect-based sentiment polarity identified from the reviews generated by 78056 users and 235 critics. The usefulness of CAMO is empirically evaluated using two similarity measures and two state-of-the-art recommendation methods, and it seems a useful movie knowledgebase for the development of context-aware movie recommendation systems. The source code of CAMO is uploaded at https://github.com/vineet-sejwal/CAMO for research and academic reference purposes. The generated movie dataset containing movie details, user ratings, and reviews generated by both users and critics is also uploaded, and it can be used as a benchmark dataset to evaluate movie recommender systems.

The emergence of explainability of intelligent systems: Delivering explainable and personalized recommendations for energy efficiency

The recent advances in artificial intelligence namely in machine learning and deep learning, have boosted the performance of intelligent systems in several ways. This gave rise to human expectations, but also created the need for a deeper understanding of how intelligent systems think and decide. The concept of explainability appeared, in the extent of explaining the internal system mechanics in human terms. Recommendation systems are intelligent systems that support human decision making, and as such, they have to be explainable in order to increase user trust and improve the acceptance of recommendations. In this work, we focus on a context-aware recommendation system for energy efficiency and develop a mechanism for explainable and persuasive recommendations, which are personalized to user preferences and habits. The persuasive facts either emphasize on the economical saving prospects (Econ) or on a positive ecological impact (Eco) and explanations provide the reason for recommending an energy saving action. Based on a study conducted using a Telegram bot, different scenarios have been validated with actual data and human feedback. Current results show a total increase of 19\% on the recommendation acceptance ratio when both economical and ecological persuasive facts are employed. This revolutionary approach on recommendation systems, demonstrates how intelligent recommendations can effectively encourage energy saving behavior.

A Survey of Context-Aware Recommendation Schemes in Event-Based Social Networks

In recent years, Event-based social network (EBSN) applications, such as Meetup and DoubanEvent, have received popularity and rapid growth. They provide convenient online platforms for users to create, publish, and organize social events, which will be held in physical places. Additionally, they not only support typical online social networking facilities (e.g., sharing comments and photos), but also promote face-to-face offline social interactions. To provide better service for users, Context-Aware Recommender Systems (CARS) in EBSNs have recently been singled out as a fascinating area of research. CARS in EBSNs provide the suitable recommendation to target users by incorporating the contextual factors into the recommendation process. This paper provides an overview on the development of CARS in EBSNs. We begin by illustrating the concept of the term context and the paradigms of conventional context-aware recommendation process. Subsequently, we introduce the formal definition of an EBSN, the characteristics of EBSNs, the challenges that are faced by CARS in EBSNs, and the implementation process of CARS in EBSNs. We also investigate which contextual factors are considered and how they are represented in the recommendation process. Next, we focus on the state-of-the-art computational techniques regarding CARS in EBSNs. We also overview the datasets and evaluation metrics for evaluation in this research area, and discuss the applications of context-aware recommendation in EBSNs. Finally, we point out research opportunities for the research community.

TrustTF: A tensor factorization model using user trust and implicit feedback for context-aware recommender systems

In recent years, context information has been widely used in recommender systems. Tensor factorization is an effective method to process high-dimensional information. However, data sparsity is more serious in tensor factorization, and it is difficult to build a more accurate recommender system only based on user–item–context interaction information. Making full use of user’s social information and implicit feedback can alleviate this problem. In this paper, we propose a new tensor factorization model named TrustTF, which mainly works as follows: (1) Using user’s social trust information and implicit feedback to extend the bias tensor factorization (BiasTF), effectively alleviate data sparsity problem and improve the recommendation accuracy; (2) Dividing user’s trust relationship into unilateral trust and mutual trust, which makes better use of user’s social information. To our knowledge, this is the first work to consider the effects of both user trust and implicit feedback on the basis of the BiasTF model. The experimental results in two real-world data sets demonstrate that the TrustTF proposed in this paper can achieve higher accuracy than BiasTF and other social recommendation methods.

Considering Fine-Grained and Coarse-Grained Information for Context-Aware Recommendations

AbstractIn context-aware recommendation systems, most existing methods encode users’ preferences by mapping item and category information into the same space, which is just a stack of information. The item and category information contained in the interaction behaviours is not fully utilized. Moreover, since users’ preferences for a candidate item are influenced by the changes in temporal and historical behaviours, it is unreasonable to predict correlations between users and candidates by using users’ fixed features. A fine-grained and coarse-grained information based framework proposed in our paper which considers multi-granularity information of users’ historical behaviours. First, a parallel structure is provided to mine users’ preference information under different granularities. Then, self-attention and attention mechanisms are used to capture the dynamic preferences. Experiment results on two publicly available datasets show that our framework outperforms state-of-the-art methods across the calculated evaluation metrics.

A Context-Aware Personalized Hybrid Book Recommender System

Contextual information such as emotion, location and time can effectively improve product or service recommendations, however, studies incorporating them are lacking. This paper presents a context-aware recommender system, personalized based on several user characteristics and product features. The recommender system which was customized to recommend books, was aptly named as a Context-Aware Personalized Hybrid Book Recommender System, which utilized users’ personality traits, demographic details, location, review sentiments and purchase reasons to generate personalized recommendations. Users’ personality traits were determined using the Ten Item Personality Inventory. The results show an improved recommendation accuracy compared to the existing algorithms, and thus indicating that the integration of several filtering techniques along with specific contextual information greatly improves recommendations.

Effective Context-Aware Recommendations Based on Context Weighting Using Genetic Algorithm and Alleviating Data Sparsity

ABSTRACT Context-aware collaborative filtering (CACF) is an effective approach for adapting recommendations under users’ specific contextual situations and aims to improve predictive accuracy for Context-aware recommender systems (CARSs). Incorporating context in recommender systems (RSs) considering the equal importance to all contextual dimensions is not appropriate for seeking an intelligent and useful recommendation. In this paper, we propose a Real-coded Genetic Algorithm (RCGA) based CARS framework that exploits contextual pre-filtering and contextual modeling paradigms into CACF with appropriate context feature weights for enhancing accuracy as well as the diversity of the recommendation list. Further to alleviate the data sparsity, an effective missing value prediction (EMVP) algorithm is applied into proposed framework. The accuracy based on RCGA is compared with other two schemes: Support Vector Machine (SVM) and Particle Swarm Optimization (PSO), and RCGA has shown better results. Experimental results based on real-world datasets have clearly established the effectiveness of our proposed CARS schemes.

The Importance of Context When Recommending TV Content: Dataset and Algorithms

Home entertainment systems feature in a variety of usage scenarios with one or more simultaneous users, for whom the complexity of choosing media to consume has increased rapidly over the last decade. Users' decision processes are complex and highly influenced by contextual settings, but data supporting the development and evaluation of context-aware recommender systems are scarce. In this paper we present a dataset of self-reported TV consumption enriched with contextual information of viewing situations. We show how choice of genre associates with, among others, the number of present users and users' attention levels. Furthermore, we evaluate the performance of predicting chosen genres given different configurations of contextual information, and compare the results to contextless predictions. The results suggest that including contextual features in the prediction cause notable improvements, and both temporal and social context show significant contributions.

REHAB-C: Recommendations for Energy HABits Change

This paper introduces REHAB-C, a goal-based context-aware recommendation system that supports users in transforming their energy habits. A combination of smart sensors and actuators collects information about user actions and their context and evaluates the actions to be proposed. Based on user decisions, REHAB-C either triggers an energy saving action, postpones or cancels it and records user preferences. The recommendation system continuously evaluates the user context and action against a rule base along with user goals and prioritizes the recommended actions, also considering other user preferences. The prototype implementation of REHAB-C is evaluated on two real-world scenarios, in an office setup. The user actions and presence are recorded for four weeks, as well as the user behavior towards energy saving, and his preferences on the recommended actions. The analysis of recorded results shows that goal-based context-aware recommendations can help users to improve their energy efficiency and in the long term can automatically adapt to user habits and reduce their energy footprint.

New contextual collaborative filtering system with application to personalized healthy nutrition education

Nowadays, the Internet is becoming a platform of choice where the number of users and items grows dramatically making recommender systems (RS) the most required and widespread technology. This paper deals with context aware collaborative RS and presents a double contribution that consists of a two Dimensions Contextual Collaborative Recommender System (2DCCRS) and a related application. Our first contribution proposes a new framework for collaborative context aware RS that relies on two key ideas. The first one suggests splitting the context into two parts namely internal and external contexts in order to deal with both internal and external context attributes in different and more appropriate manners. This allows addressing the complexity of the context model in a more effective way. In the second idea, we introduce two concepts; namely the “Stakeholders” and “Aggregation” to effectively alleviate the problems of new user and new item. 2DCCRS is based on a multi-layer architecture. Its highest layer relies on a pre-filtering algorithm that deals with the cold start system problem, and is mainly based on the similarity between the user profile and the items features. The middle layer is based on a collaborative filtering algorithm that takes into account the users’ preferences, interests and priorities; while the deepest layer, which is considered the most relevant in our multilayer architecture, focuses on a post-filtering algorithm in which the recommendations are much more adapted to the user environment. In Our second contribution, we present a case study of 2DCCRS in order to demonstrate the usefulness and effectiveness of the proposed approach. Indeed, we propose a personalized Healthy and Tasty application (H&T) that generates items based on 2DCCRS framework to guide the user toward the healthy and tasty meals that best meet his needs. The obtained results are very promising and show the effectiveness of our proposal.

Fast Tensor Factorization for Large-Scale Context-Aware Recommendation from Implicit Feedback

This paper presents a fast Tensor Factorization (TF) algorithm for context-aware recommendation from implicit feedback. For such a recommendation problem, the observed data indicate the (positive) association between users and items in some given contexts. For better accuracy, it has been shown essential to include unobserved data that indicate the negative user-item-context associations. As such unobserved data greatly outnumber the observed ones, for efficiency existing algorithms usually use only a small part of the unobserved data for model training. We show in this paper that it is possible, and beneficial, to use all the unobserved data in training a TF based context-aware recommender system. This is achieved by two technical innovations. First, we scrutinize the matrix computation of the closed-form solution and accelerate the computation by memorizing the repetitive computation. Second, we further boost the generalization and scalability by dropping out some pairwise interactions when updating user, item or context factors to prevent overfitting and to reduce the training time. The resulting whole-data based learning algorithm, referred to as DropTF in the paper, is efficient and scale well. Our evaluation on two small benchmark datasets and a million-scale large dataset demonstrates improved accuracy over some existing algorithms for context-aware recommendation.

A location history-aware recommender system for smart retail environments

Recommender systems (RSs) represent integral parts of e-commerce platforms for almost two decades now. The recent emergence of mobile context-aware RSs (CARS) contributed in improving the relevance of recommendations derived by “traditional” RSs through adapting them to the situational user context. This article presents the design and implementation aspects of a collaborative filtering-based mobile CARS, which has been integrated in a smart retailing platform that enables location-based search for retail products and services. In addition to user location, the introduced CARS considers several context parameters like time, season, demographic data, consumer behavior, and location history of the user in order to derive more meaningful product recommendations. Our RS has undergone field trials as well as formal laboratory evaluation tests demonstrating higher accuracy and relevance of recommendations compared with two baseline approaches.

CRecSys: A Context-Based Recommender System Using Collaborative Filtering and LOD

Linked Open Data (LOD) is an emerging Web technology to store and publish structured data in the form of interlinked knowledgebases like DBpedia, Freebase, Wikidata, and Yago. It uses structured data from multiple domains, and it can be used to conceptualize a concept of interest. Recently, researchers have shown that incorporating contextual features in recommender systems improves rating prediction accuracy. However, identification of contextual features for building context-aware recommender systems is a major bottleneck. To this end, in this article, we present the development of a context-based recommender system, CRecSys, for item ratings prediction in movie domain. CRecSys extracts item-based contextual features from the underlying dataset and generates an RDF graph to model items and their contextual features for computing context-based items similarity using graph matching techniques and item-based collaborative filtering. It uses LOD and two well-known movie data sources - Rotten Tomatoes and IMDB for item profiling using a dataset of 1300 movies. CRecSys is experimentally evaluated over two movie datasets, one is generated by the authors and second is the MovieLens-1M benchmark dataset. CRecSys is also compared with ten baselines and two state-of-the-art recommendation methods, and performs significantly better. It is also empirically established that CRecSys is able to effectively deal with some of the open challenges like cold-start and limited content problems of the traditional recommender systems.

A Hybrid Context Aware Recommender System with Combined Pre and Post-Filter Approach

The domain of context aware recommender approaches has made substantial advancement over the last decade, but many applications still do not include contextual information while providing recommendations. Contextual information is crucial for various application areas and should not be ignored. There are generally three algorithms which can be used to include context and those are: pre-filter approach, post-filter approach, and contextual modeling. Each of the algorithms has their own drawbacks. The proposed approach modifies the post filter approach to rectify its shortcomings and combines it with the pre-filter approach based on the importance of contextual attribute provided by the user. The results of experimental setup also demonstrate that the proposed system improves the precision and ranking of the recommendations provided to user. With the help of this hybrid approach, the proposed system eliminates the problem of sparsity which is present in the pre-filter algorithm, and has performance improvement over the traditional post-filter approach.