融合交互强度的优化社交推荐算法

针对现有社交化推荐算法忽视了评级数据与社交信息之间关联的探索,提出了一种融合交互强度的优化社交推荐算法。首先,利用社交信息和评级数据结合两种相似度丰富社交矩阵;接着,定义用户间交互强度代表用户间复杂关系;最后,利用交互强度与社交关系之间的关联以及用户潜在特征与用户群体参与特征的关联构建新的目标函数,学习用户和项目的潜在特征,实现个性化推荐。在三个真实数据集上进行实验,与基线模型相比,提出的算法在推荐预测精度上有显著提升,且在对不同评级数量的用户进行潜在特征学习时,表现出良好的鲁棒性。综上,融合交互强度可以进一步提升社交化推荐算法性能,增强用户体验感。     

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.     

融合一致性社交关系的协同相似嵌入推荐模型

为了解决推荐系统中新用户评级预测冷启动和数据稀疏等问题,提出了一种融合一致性社交关系的协同相似嵌入推荐模型(collaborative similarity embedding recommendation model incorporating consistent social relationships, CSECSR)。首先,模型通过预热层对图形嵌入进行等权重传播和聚合;其次,采样具有一致性的社交关系邻居,并利用关系注意力机制对这些关系进行聚合;最后,利用用户和项目最终嵌入值的内积进行评分预测,设计具有自适应裕度的BPR损失和相似性损失的损失函数对模型进行优化。在Ciao、Epinions和FilmTrust数据集上与其他代表性的推荐模型进行了对比,实验结果表明所提推荐模型预测误差明显优于其他模型,证明了所提推荐模型的有效性。     

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.     

融合社交关系的轻量级图卷积协同过滤推荐方法

图卷积网络(graph convolution network, GCN)因其强大的建模能力得到了迅速发展,目前大部分研究工作直接继承了GCN的复杂设计（如特征变换,非线性激活等）,缺乏简化工作。另外,数据稀疏性和隐式负反馈没有被充分利用,也是当前推荐算法的局限。为了应对以上问题,提出了一种融合社交关系的轻量级图卷积协同过滤推荐模型。模型摒弃了GCN中特征变换和非线性激活的设计;利用社交关系从隐式负反馈中产生一系列的中间反馈,提高了隐式负反馈的利用率;最后,通过双层注意力机制分别突出了邻居节点的贡献值和每一层图卷积层学习向量的重要性。在2个公开的数据集上进行实验,结果表明所提模型的推荐效果优于当前的图卷积协同过滤算法。     

融合信任用户间接影响的个性化推荐算法

为了解决推荐系统中固有的数据稀疏性和冷启动问题,通常会采用一些额外的与用户或是项目有关的信息。提出了一种新颖的基于矩阵因子分解的推荐算法,其结合了其他用户对于活动用户未来评分的间接影响作用,并进一步将社交网络中的信任关系融入到算法中。同时,为了避免学习参数时过度拟合,引入了一种加权的正规化因子。最后针对一般情况和冷启动情况,分别在Epinions数据集和Ciao数据集上进行了实验。实验结果表明,相比于其它相关算法,本算法在推荐准确性上有了很大的提高,同时能更好地解决相关问题。     

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....     

Utilizing the influence of multiple potential factors for social recommendation

Knowledge and Information Systems - The recommendation system helps users select satisfactory products and services to make reasonable decisions. In recent years, most methods have introduced...     

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.     

融合注意力机制的深度混合推荐算法

大量研究利用用户或项目的边信息来缓解视频推荐中的数据稀疏和冷启动问题,取得了一定的效果,但是没有关注辅助信息中的关键信息.针对此问题进行了研究,提出了一种融合双注意力机制的深度混合推荐模型.该模型通过融合自注意力机制的卷积神经网络挖掘项目端隐藏因子,同时融合自注意力机制的堆栈去噪自编码器提取用户端隐藏因子,深度挖掘项目端和用户端的重要信息.最后,通过结合概率矩阵分解实现视频评分预测.在两个公开数据集上的大量实验结果表明,提出的方法结果在已有ConvMF+、PHD、DUPIA等基线模型基础上有一定提升.     

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.     

基于心率变异性分析的睡眠音乐推荐系统

现有睡眠监测研究主要是针对睡眠质量提出非干扰式监测方法的研究,而缺乏对睡眠质量主动调节方法的研究。基于心率变异性(HRV)分析的精神状态以及睡眠分期研究主要集中在这两种信息的获取上,而这两种信息的获取需要佩戴专业医疗设备,并且这些研究缺乏对信息的应用以及调整。音乐可以作为一种解决睡眠问题的非药物类方法,但现有音乐推荐方法并未考虑个体睡眠及精神状态的差异。针对以上问题提出了一种基于移动设备的精神压力和睡眠状态的音乐推荐系统。首先,用手表采集光体积扫描计信号来提取特征并计算心率;其次,将采集的信号通过蓝牙传递给手机,手机通过这些信号评估人的精神压力以及睡眠状态来播放调整音乐;最后,根据个体每晚的入眠时间进行音乐推荐。实验结果表明,在使用睡眠音乐推荐系统后,用户睡眠总时长相较于使用前增长11.0%。     

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.     

融合社会网络与信任度的个性化推荐方法研究

针对协同推荐技术存在的数据稀疏性和恶意评价行为等问题, 提出了一种新颖的基于社会网络的协同过滤推荐算法。该方法借助社会网络分析技术对协同推荐方法加以改进, 结合用户信任关系与用户自身兴趣, 通过计算网络节点的可信度来消减虚假评分或恶意评分给推荐系统带来的负面影响, 从而提高了推荐系统的准确度。实验表明, 相对于传统的协同过滤算法, 该算法可以有效缓解用户评分稀疏性及恶意评价行为带来的问题, 显著提高推荐系统的推荐质量。