Dual influence embedded social recommendation

Recommender systems are designed to solve the information overload problem and have been widely studied for many years. Conventional recommender systems tend to take ratings of users on products into account. With the development of Web 2.0, Rating Networks in many online communities (e.g. Netflix and Douban) allow users not only to co-comment or co-rate their interests (e.g. movies and books), but also to build explicit social networks. Recent recommendation models use various social data, such as observable links, but these explicit pieces of social information incorporating recommendations normally adopt similarity measures (e.g. cosine similarity) to evaluate the explicit relationships in the network - they do not consider the latent and implicit relationships in the network, such as social influence. A target user’s purchase behavior or interest, for instance, is not always determined by their directly connected relationships and may be significantly influenced by the high reputation of people they do not know in the network, or others who have expertise in specific domains (e.g. famous social communities). In this paper, based on the above observations, we first simulate the social influence diffusion in the network to find the global and local influence nodes and then embed this dual influence data into a traditional recommendation model to improve accuracy. Mathematically, we formulate the global and local influence data as new dual social influence regularization terms and embed them into a matrix factorization-based recommendation model. Experiments on real-world datasets demonstrate the effective performance of the proposed method.     

Emotion-based music recommendation by affinity discovery from film music

With the growth of digital music, the development of music recommendation is helpful for users to pick desirable music pieces from a huge repository of music. The existing music recommendation approaches are based on a user’s preference on music. However, sometimes, it might better meet users’ requirement to recommend music pieces according to emotions. In this paper, we propose a novel framework for emotion-based music recommendation. The core of the recommendation framework is the construction of the music emotion model by affinity discovery from film music, which plays an important role in conveying emotions in film. We investigate the music feature extraction and propose the Music Affinity Graph and Music Affinity Graph-Plus algorithms for the construction of music emotion model. Experimental result shows the proposed emotion-based music recommendation achieves 85% accuracy in average.     

Interest-aware influence diffusion model for social recommendation

Journal of Intelligent Information Systems - With the rapid development of social networks, the application of social relationships in recommendation systems has attracted more and more attention....     

Learning to embed music and metadata for context-aware music recommendation

Contextual factors greatly influence users’ musical preferences, so they are beneficial remarkably to music recommendation and retrieval tasks. However, it still needs to be studied how to obtain and utilize the contextual information. In this paper, we propose a context-aware music recommendation approach, which can recommend music pieces appropriate for users’ contextual preferences for music. In analogy to matrix factorization methods for collaborative filtering, the proposed approach does not require music pieces to be represented by features ahead, but it can learn the representations from users’ historical listening records. Specifically, the proposed approach first learns music pieces’ embeddings (feature vectors in low-dimension continuous space) from music listening records and corresponding metadata. Then it infers and models users’ global and contextual preferences for music from their listening records with the learned embeddings. Finally, it recommends appropriate music pieces according to the target user’s preferences to satisfy her/his real-time requirements. Experimental evaluations on a real-world dataset show that the proposed approach outperforms baseline methods in terms of precision, recall, F1 score, and hitrate. Especially, our approach has better performance on sparse datasets.     

A novel method for personalized music recommendation

With the development of digital music technologies, it is an interesting and useful issue to recommend the ‘favored music’ from large amounts of digital music. Some Web-based music stores can recommend popular music which has been rated by many people. However, three problems that need to be resolved in the current methods are: (a) how to recommend the ‘favored music’ which has not been rated by anyone, (b) how to avoid repeatedly recommending the ‘disfavored music’ for users, and (c) how to recommend more interesting music for users besides the ones users have been used to listen. To achieve these goals, we proposed a novel method called personalized hybrid music recommendation, which combines the content-based, collaboration-based and emotion-based methods by computing the weights of the methods according to users’ interests. Furthermore, to evaluate the recommendation accuracy, we constructed a system that can recommend the music to users after mining users’ logs on music listening records. By the feedback of the user’s options, the proposed methods accommodate the variations of the users’ musical interests and then promptly recommend the favored and more interesting music via consecutive recommendations. Experimental results show that the recommendation accuracy achieved by our method is as good as 90%. Hence, it is helpful for recommending the ‘favored music’ to users, provided that each music object is annotated with the related music emotions. The framework in this paper could serve as a useful basis for studies on music recommendation.     

Enhancing recommender systems by incorporating social information

Although recommendation techniques have achieved distinct developments over the decades,the data sparseness problem of the involved user-item matrix still seriously influences the recommendation quality.Most of the existing techniques for recommender systems cannot easily deal with users who have very few ratings.How to combine the increasing amount of different types of social information such as user generated content and social relationships to enhance the prediction precision of the recommender systems remains a huge challenge.In this paper,based on a factor graph model,we formalize the problem in a semi-supervised probabilistic model,which can incorporate different user information,user relationships,and user-item ratings for learning to predict the unknown ratings.We evaluate the method in two different genres of datasets,Douban and Last.fm.Experiments indicate that our method outperforms several state-of-the-art recommendation algorithms.Furthermore,a distributed learning algorithm is developed to scale up the approach to real large datasets.     

Neural content-aware collaborative filtering for cold-start music recommendation

Data Mining and Knowledge Discovery - State-of-the-art music recommender systems are based on collaborative filtering, which builds upon learning similarities between users and songs from the...     

Improving the effectiveness of experiential decisions by recommendation systems

Providing experience-oriented offerings through e-commerce is an issue increasing critical in the growing commoditization of e-commercial services. The high accuracy of predictions rendered by Recommendation System (RS) technologies has strengthened the opportunities for experience-oriented offerings, making RS application an effective way of assisting consumers in online decision-making. This study proposes a RS for movie lovers using neural networks in collaborative filtering systems for consumers’ experiential decisions. The experimental results reveal that it not only improves the accuracy of predicting movie ratings but also increases data transfer rates and provides richer user experiences.     

A personalized music recommendation system based on electroencephalography feedback

Numerous domestic and foreign studies have demonstrated that music can relieve stress and that listening to music is one method of stress relief used presently. Although stress-relief music is available on the market, various music genres produce distinct effects on people. Clinical findings have indicated that approximately 30 % of people listen to inappropriate music genres for relaxation and, consequently, their stress level increases. Therefore, to achieve the effect of stress relief, choosing the appropriate music genre is crucial. For example, a 70-year-old woman living in a military community since childhood might not consider general stress-relief music to be helpful in relieving stress, but when patriotic songs are played, her autonomic nervous system automatically relaxes because of her familiarity with the music style. Therefore, people have dissimilar needs regarding stress-relief music. In this paper, we proposed a personalized stress-relieving music recommendation system based on electroencephalography (EEG) feedback. The system structure comprises the following features: (a) automated music categorization, in which a new clustering algorithm, K-MeansH, is employed to precluster music and improve processing time; (b) the access and analysis of users’ EEG data to identify perceived stress-relieving music; and (c) personalized recommendations based on collaborative filtering and provided according to personal preferences. Experimental results indicated that the overall clustering effect of K-MeansH surpassed that of K-Means and K-Medoids by approximately 71 and 57 %, respectively. In terms of accuracy, K-MeansH also surpassed K-Means and K-Medoids.     

Tag recommendation by machine learning with textual and social features

Tags are very popular in social media (like Youtube, Flickr) and provide valuable and crucial information for social media. But at the same time, there exist a great number of noisy tags, which lead to many studies on tag suggestion and recommendation for items including websites, photos, books, movies, and so on. The textual features of tags, likes tag frequency, have mostly been used in extracting tags that are related to items. In this paper, we address the problem of tag recommendation for social media users. This issue is as important as the tag recommendation for items, because the tags representing users are strongly related to the users’ favorite topics. We propose several novel features of tags for machine learning that we call social features as well as textual features. The experimental results of Flickr show that our proposed scheme achieves viable performance on tag recommendation for users.     

Online social trust reinforced personalized recommendation

Recommendation techniques greatly promote the development of online service in the interconnection environment. Personalized recommendation has attracted researchers’ special attention because it is more targeted to individual tasks with the characteristics of diversification and novelty. However, the data sets that personalized recommendation process usually possess the characteristics of data sparseness and information loss, which is more likely to have problems such as cognitive deviation and interest drift. To solve these issues, in recent years people gradually notice the important role in which trust factor plays in promoting the development of personalized recommendation. Given the difference between online social trust and traditional offline social trust in facilitating personalized recommendation, this paper proposes a novel technique of online social trust reinforced personal recommendation to improve the recommendation performance. Compared with traditional offline social trust-based personal recommendation, our work synthesizes both factors of online social trust and offline social trust to identify private and public trusted user communities. The trusted degree or the accredited degree can be deduced by Bayesian network probabilistic inferences. In this way, the performance of personalized recommendation can be improved by avoiding excessive interest deviation. Moreover, we also get time sequence into personal recommendation model to effectively track how user’s interest changes over time. Accordingly, the recommendation accuracy can be improved by eliminating the unfavorable effect of interest drift caused by temporal variation. Empirical experiments on typical Yelp testing data set illustrate the effectiveness of the proposed recommendation technique.     

Comparison of content-based music recommendation using different distance estimation methods

With rapid growth in the online music market, music recommendation has become an active research area. In most current approaches, content-based recommendation methods play an important role. Estimation of similarity between music content is the key to these approaches. A distance formula is used to calculate the music distance measure, and music recommendations are provided based on this measure. However, people have their own unique tastes in music. This paper proposes a method to calculate a personalized distance measure between different pieces of music based on user preferences. These methods utilize a randomized algorithm, a genetic algorithm, and genetic programming. The first two methods are based on Euclidean distance calculation, where the weight of each music feature in the distance calculation approximates user perception. The third method is not limited to Euclidean distance calculation. It generates a more complex distance function to estimate a user’s music preferences. Experiments were conducted to compare the distance functions calculated by the three methods, and to compare and evaluate their performance in music recommendation.     

Mining tag-clouds to improve social media recommendation

Multimedia Tools and Applications - Massive amounts of data are available on social websites, therefore finding the suitable item is a challenging issue. According to recent social statistics, we...     

Implicit relation-aware social recommendation with variational auto-encoder

World Wide Web - Integrating social networks as auxiliary information shows effectiveness in improving the performance for a recommendation task. Typical models usually characterize the user trust...     

Eye-tracking and social behavior preference-based recommendation system

The Journal of Supercomputing - With the popularization of wireless Internet technology and smartphones, the importance of recommendation systems, which analyze personality of a user using social...     

A social recommendation method based on opinion leaders

With the rapid development of information technology, social media has been widely used, and Internet information has been exploded, and consumers may experience information overload. Recommender systems using the social recommendation method that integrates social relationship information can provide users with target information that meets their needs. However, most of the existing methods only rely on the user’s ordinary friends to make recommendations, neglecting another influential group, the opinion leaders. In this study, we propose a new social recommendation method based on opinion leaders. The proposed method assumes that the influence of the opinion leader on the user is much greater than that of the user’s ordinary friends. The experimental results on two real datasets show that the proposed method not only has a better recommendation effect than the state-of-the-art recommendation algorithms, but also has a good performance in the cases of cold-start users.