Health-guided recipe recommendation over knowledge graphs

While the availability of large-scale online recipe collections presents opportunities for health consumers to access a wide variety of recipes, it can be challenging for them to discover relevant recipes. Whereas most recommender systems are designed to offer selections consistent with users’ past behavior, it remains an open problem to offer selections that can help users’ transition from one type of behavior to another, intentionally. In this paper, we introduce health-guided recipe recommendation as a way to incrementally shift users towards healthier recipe options while respecting the preferences reflected in their past choices. Introducing a knowledge graph (KG) into recommender systems as side information has attracted great interest, but its use in recipe recommendation has not been studied. To fill this gap, we consider the task of recipe recommendation over knowledge graphs. In particular, we jointly learn recipe representations via graph neural networks over two graphs extracted from a large-scale Food KG, which capture different semantic relationships, namely, user preferences and recipe healthiness, respectively. To integrate the nutritional aspects into recipe representations and the recommendation task, instead of simple fusion, we utilize a knowledge transfer scheme to enable the transfer of useful semantic information across the preferences and healthiness aspects. Experimental results on two large real-world recipe datasets showcase our model’s ability to recommend tasty as well as healthy recipes to users.     

Price-aware matrix factorization model for personalized recommendations

Recommendation methods aim to assist consumers in their decision-making process to find products that they are quite likely interested in. Current recommendation methods generally use online consumer reviews or ratings to predict consumers’ preferences for products. In e-commerce transactions, price plays a significant role in consumers’ purchase decisions. And each consumer's preference for product prices is specific. In this paper, we propose a novel price-aware recommendation method based on the matrix factorization model which fully considers the effect of price. We distill the price preferences of consumers from ratings and discover consumers’ real preferences for products. We further calculate the price sensitivities of consumers, not only considering the difference in price preference between a consumer and others but also focusing on the consumers’ price preferences in a specific price range. The final predicted ratings are calculated by adding the term of price effect into the matrix factorization framework. The results show that the proposed method has achieved high accuracy and performed better than several existing methods in both rating prediction and Top-N recommendation. And the products we recommend for consumers are more in line with their price preferences. Moreover, we find that, to some extent, the proposed method can solve the long-tail product recommendation problem with the consideration of the price effect.     

一种基于用户播放行为序列的个性化视频推荐策略

本文针对在线视频服务网站的个性化推荐问题,提出了一种基于用户播放行为序列的个性化推荐策略.该策略通过深度神经网络词向量模型分析用户播放视频行为数据,将视频映射成等维度的特征向量,提取视频的语义特征.聚类用户播放历史视频的特征向量,建模用户兴趣分布矩阵.结合用户兴趣偏好和用户观看历史序列生成推荐列表.在大规模的视频服务系统中进行了离线实验,相比随机算法、基于物品的协同过滤和基于用户的协同过滤传统推荐策略,本方法在用户观看视频的Top-N推荐精确率方面平均分别获得22.3%、30.7%和934%的相对提升,在召回率指标上分别获得52.8%、41%和1065%的相对提升.进一步地与矩阵分解算法SVD++、基于双向LSTM模型和注意力机制的Bi-LSTM+Attention算法和基于用户行为序列的深度兴趣网络DIN比较,Top-N推荐精确率和召回率也得到了明显提升.该推荐策略不仅获得了较高的精确率和召回率,还尝试解决传统推荐面临大规模工业数据集时的数据要求严苛、数据稀疏和数据噪声等问题.     

一种潜在特征同步学习和偏好引导的推荐方法

根据用户的历史评分数据为用户提供推荐的商品列表，是目前推荐系统研究的主流.研究者发现，随着用户参与度的不断提高，将反映用户偏好的评论文本与评分数据结合，可以进一步提高推荐的质量.提出了基于潜在特征同步学习和偏好引导的商品推荐方法，将评论文本的主题与用户的"打分偏好"进行关联，同步学习用户评论文本的潜在主题、评分矩阵的用户潜在因子和商品潜在因子，并将潜在主题作为用户个人偏好引导来约束推荐方法对商品的预测打分.该方法对推荐质量的优化主要体现在两个方面：一是在评论文本的潜在主题和评分数据的两种潜在因子之间建立映射关系，同步求解主题模型和矩阵分解模型；二是将从评论文本中学习得到的潜在主题作为用户对商品的个性偏好引入到矩阵分解中，进一步优化推荐方法.在来自Amazon网站的28组真实数据集上进行实验，以均方误差为评价指标，与已有的模型进行了对比分析.实验结果表明，该方法有效减少了推荐误差，与已有的TopicMF方法相比，均方误差在数据子集上最大减少了3.32%，平均减少了0.92%.     

Opinion-enhanced collaborative filtering for recommender systems through sentiment analysis

The motivation of collaborative filtering (CF) comes from the idea that people often get the best recommendations from someone with similar tastes. With the growing popularity of opinion-rich resources such as online reviews, new opportunities arise as we can identify the preferences from user opinions. The main idea of our approach is to elicit user opinions from online reviews, and map such opinions into preferences that can be understood by CF-based recommender systems. We divide recommender systems into two types depending on the number of product category recommended: the multiple-category recommendation and the single-category recommendation. For the former, sentiment polarity in coarse-grained manner is identified while for the latter fine-grained sentiment analysis is conducted for each product aspect. If the evaluation frequency for an aspect by a user is greater than the average frequency by all users, it indicates that the user is more concerned with that aspect. If a user's rating for an aspect is lower than the average rating by all users, he or she is much pickier than others on that aspect. Through sentiment analysis, we then build an opinion-enhanced user preference model, where the higher the similarity between user opinions the more consistent preferences between users are. Experiment results show that the proposed CF algorithm outperforms baseline methods for product recommendation in terms of accuracy and recall.     

结合动态多类信息的兴趣点推荐

利用用户的历史签到数据的同时考虑用户的长期偏好和短期偏好已成为当今兴趣点（Point-of-Interest,POI）推荐的主流方法之一。然而,现有方法往往忽略了用户评论中隐含的用户偏好信息,忽视了不同用户在对长期偏好和短期偏好的依赖上所存在的差异性。针对上述局限,本文提出一种结合动态多类信息的兴趣点推荐方法DMGCR。首先,利用注意力机制捕获用户对不同兴趣点的关注程度,定量刻画用户对兴趣点的长期偏好。其次,将评论信息与已有的位置和类别信息相结合,并利用双向长短期记忆网络学习评论文本中隐含的语义特征,在捕获用户对兴趣点情感倾向的基础上准确刻画用户的短期偏好。最后,设计融合动态多类信息的用户偏好综合预测函数,实现下一个兴趣点推荐概率的定量计算。多个数据集上的实验结果验证了该方法在推荐性能上的有效性和优越性。     

User Personality and User Satisfaction with Recommender Systems

In this study, we show that individual users’ preferences for the level of diversity, popularity, and serendipity in recommendation lists cannot be inferred from their ratings alone. We demonstrate that we can extract strong signals about individual preferences for recommendation diversity, popularity and serendipity by measuring their personality traits. We conducted an online experiment with over 1,800 users for six months on a live recommendation system. In this experiment, we asked users to evaluate a list of movie recommendations with different levels of diversity, popularity, and serendipity. Then, we assessed users’ personality traits using the Ten-item Personality Inventory (TIPI). We found that ratings-based recommender systems may often fail to deliver preferred levels of diversity, popularity, and serendipity for their users (e.g. users with high-serendipity preferences). We also found that users with different personalities have different preferences for these three recommendation properties. Our work suggests that we can improve user satisfaction when we integrate users’ personality traits into the process of generating recommendations.     

Combining user preferences and user opinions for accurate recommendation

Recommendation systems represent a popular research area with a variety of applications. Such systems provide personalized services to the user and help address the problem of information overload. Traditional recommendation methods such as collaborative filtering suffer from low accuracy because of data sparseness though. We propose a novel recommendation algorithm based on analysis of an online review. The algorithm incorporates two new methods for opinion mining and recommendation. As opposed to traditional methods, which are usually based on the similarity of ratings to infer user preferences, the proposed recommendation method analyzes the difference between the ratings and opinions of the user to identify the user’s preferences. This method considers explicit ratings and implicit opinions, an action that can address the problem of data sparseness. We propose a new feature and opinion extraction method based on the characteristics of online reviews to extract effectively the opinion of the user from a customer review written in Chinese. Based on these methods, we also conduct an empirical study of online restaurant customer reviews to create a restaurant recommendation system and demonstrate the effectiveness of the proposed methods.     

Joint user knowledge and matrix factorization for recommender systems

Currently, most of the existing recommendation methods treat social network users equally, which assume that the effect of recommendation on a user is decided by the user’s own preferences and social influence. However, a user’s own knowledge in a field has not been considered. In other words, to what extent does a user accept recommendations in social networks need to consider the user’s own knowledge or expertise in the field. In this paper, we propose a novel matrix factorization recommendation algorithm based on integrating social network information such as trust relationships, rating information of users and users’ own knowledge. Specifically, since we cannot directly measure a user’s knowledge in the field, we first use a user’s status in a social network to indicate a user’s knowledge in a field, and users’ status is inferred from the distributions of users’ ratings and followers across fields or the structure of domain-specific social network. Then, we model the final rating of decision-making as a linear combination of the user’s own preferences, social influence and user’s own knowledge. Experimental results on real world data sets show that our proposed approach generally outperforms the state-of-the-art recommendation algorithms that do not consider the knowledge level difference between the users.     

基于情感分析和LDA主题模型的协同过滤推荐算法

协同过滤推荐算法通常基于物品或用户的相似度来实现个性化推荐,但是数据的稀疏性往往导致推荐精度不理想。大多数传统推荐算法仅考虑用户对物品的总体评分,而忽略了评论文本中用户对物品各个属性面的偏好。该文提出一种基于情感分析的推荐算法SACF(reviews sentiment analysis for collaborative filtering),该算法在经典的协同过滤推荐算法的基础上,考虑评论文本对相似度计算的影响。SACF算法利用LDA主题模型挖掘物品潜在的K个属性面,通过用户在各个属性面上的情感偏好计算用户相似度,从而构建推荐模型。基于京东网上评论数据集的实验结果表明,SACF算法不但可以有效地改善传统协同过滤推荐算法中数据稀疏性的问题,而且提高了推荐系统的精度。     

NEWER: A system for NEuro-fuzzy WEb Recommendation

In the era of the Web, there is urgent need for developing systems able to personalize the online experience of Web users on the basis of their needs. Web recommendation is a promising technology that attempts to predict the interests of Web users, by providing them with information and/or services that they need without explicitly asking for them. In this paper we propose NEWER, a usage-based Web recommendation system that exploits the potential of Computational Intelligence techniques to dynamically suggest interesting pages to users according to their preferences. NEWER employs a neuro-fuzzy approach in order to determine categories of users sharing similar interests and to discover a recommendation model as a set of fuzzy rules expressing the associations between user categories and relevances of pages. The discovered model is used by a online recommendation module to determine the list of links judged relevant for users. The results obtained on both synthetic and real-world data show that NEWER is effective for recommendation, leading to a quality of the generated recommendations comparable and often significantly better than those of other approaches employed for the comparison.     

Using online consumer reviews as a source for demographic recommendations: A case study using online travel reviews

Online consumer reviews play an important role in the decision to purchase services online, mainly due to the rich information source they provide to consumers in terms of evaluating “experience”-type products and services that can be booked using the Internet, with online travel services being a significant example. However, different types of travelers assess each quality indicator differently, depending on the type of travel they engage in, and not necessarily their cultural or age background (e.g. solo travelers, young couples with children etc.). In this study, we present architecture for a demographic recommendation system, based on a user-defined hierarchy of service quality indicator importance, and classification of traveler types. We use an algebraic approach to ascertain preferences from a large dataset that we obtained from the popular travel website Booking.com using a web crawler and compared with the customer-constructed preference matrix. Interestingly, the architecture of the evaluated recommendation system takes into account already defined demand characteristics of the hotels (such as the number of reviews of specific consumer types compared to the total number of reviews) in order to provide an example architecture for a recommendation system based on user-defined preference criteria.     

Interactive resource recommendation algorithm based on tag information

With the popularization of social media and the exponential growth of information generated by online users, the recommender system has been popular in helping users to find the desired resources from vast amounts of data. However, the cold-start problem is one of the major challenges for personalized recommendation. In this work, we utilized the tag information associated with different resources, and proposed a tag-based interactive framework to make the resource recommendation for different users. During the interaction, the most effective tag information will be selected for users to choose, and the approach considers the users’ feedback to dynamically adjusts the recommended candidates during the recommendation process. Furthermore, to effectively explore the user preference and resource characteristics, we analyzed the tag information of different resources to represent the user and resource features, considering the users’ personal operations and time factor, based on which we can identify the similar users and resource items. Probabilistic matrix factorization is employed in our work to overcome the rating sparsity, which is enhanced by embedding the similar user and resource information. The experiments on real-world datasets demonstrate that the proposed algorithm can get more accurate predictions and higher recommendation efficiency.     

A recommender system for the TV on the web: integrating unrated reviews and movie ratings

The activity of Social-TV viewers has grown considerably in the last few years—viewers are no longer passive elements. The Web has socially empowered the viewers in many new different ways, for example, viewers can now rate TV programs, comment them, and suggest TV shows to friends through Web sites. Some innovations have been exploring these new activities of viewers but we are still far from realizing the full potential of this new setting. For example, social interactions on the Web, such as comments and ratings in online forums, create valuable feedback about the targeted TV entertainment shows. In this paper, we address this last setting: a media recommendation algorithm that suggests recommendations based on users’ ratings and unrated comments. In contrast to similar approaches that are only ratings-based, we propose the inclusion of sentiment knowledge in recommendations. This approach computes new media recommendations by merging media ratings and comments written by users about specific entertainment shows. This contrasts with existing recommendation methods that explore ratings and metadata but do not analyze what users have to say about particular media programs. In this paper, we argue that text comments are excellent indicators of user satisfaction. Sentiment analysis algorithms offer an analysis of the users’ preferences in which the comments may not be associated with an explicit rating. Thus, this analysis will also have an impact on the popularity of a given media show. Thus, the recommendation algorithm—based on matrix factorization by Singular Value Decomposition—will consider both explicit ratings and the output of sentiment analysis algorithms to compute new recommendations. The implemented recommendation framework can be integrated on a Web TV system where users can view and comment entertainment media from a video-on-demand service. The recommendation framework was evaluated on two datasets from IMDb with 53,112 reviews (50 % unrated) and Amazon entertainment media with 698,210 reviews (26 % unrated). Recommendation results with ratings and the inferred preferences—based on the sentiment analysis algorithms—exhibited an improvement over the ratings only based recommendations. This result illustrates the potential of sentiment analysis of user comments in recommendation systems.     

Analyzing social choice and group ranking of online games for product mix innovation

With the increasing populations of the smartphones and mobile devices these years, the majority of people have played the mobile or online games on their smartphones. As such users have rapidly increased, this research is to propose an innovative service that can automatically recommend the users the appropriate online games as their optional references. In order for market competition, the most online games’ enterprises need to develop and sell the newer online game products or versions continuously for the customers who like to play online games. Now that the types and markets of online games have had the more diverse along with the sustainable development of online game products over time. This research is to propose an integrative analysis from a large amount of data -users’ preference sequences. Firstly, the research utilizes a sequence recommendation technology that can be used to analyze their preference sequences of online game’s types based on other similar users’ sequence preference data. In other words, these recommended online game’s types that can be generated according to the relationships between the query user’s preferences and users themselves. All sequences from numerous data are accumulated to be the inferences of the query users’ preferences. Secondly, the research also utilizes data mining methodology to explore the possibilities of different product mix of game types from numerous user data. For the main methodology, this research uses a ‘partial user ranking algorithm’ to analyze group ranking of online games based on similar users. The purpose is to explore how the players can be recommended based on the other users’ priorities, as well as the product mix of game types which can be the potential business trends come to markets. Furthermore, this study contributes to a research implication for online game industry, and the results also could be the business references of game combinations and product design.     

Personalized Tag Recommendation Using Social Influence

Tag recommendation encourages users to add more tags in bridging the semantic gap between human concept and the features of media object,which provides a feasible solution for content-based multimedia information retrieval.In this paper,we study personalized tag recommendation in a popular online photo sharing site - Flickr.Social relationship information of users is collected to generate an online social network.From the perspective of network topology,we propose node topological potential to characterize user’s social influence.With this metric,we distinguish different social relations between users and find out those who really have influence on the target users.Tag recommendations are based on tagging history and the latent personalized preference learned from those who have most influence in user’s social network.We evaluate our method on large scale real-world data.The experimental results demonstrate that our method can outperform the non-personalized global co-occurrence method and other two state-of-the-art personalized approaches using social networks.We also analyze the further usage of our approach for the cold-start problem of tag recommendation.     

An information gain-based approach for recommending useful product reviews

Recently, many e-commerce Web sites, such as Amazon.com, provide platforms for users to review products and share their opinions, in order to help consumers make their best purchase decisions. However, the quality and the level of helpfulness of different product reviews are not disclosed to consumers unless they carefully analyze an immense number of lengthy reviews. Considering the large amount of available online product reviews, this is an impossible task for any consumer. Therefore, it is of vital importance to develop recommender systems that can evaluate online product reviews effectively to recommend the most useful ones to consumers. This paper proposes an information gain-based model to predict the helpfulness of online product reviews, with the aim of suggesting the most suitable products and vendors to consumers. Reviews are analyzed and ranked by our scoring model and reviews that help consumers better than others will be found. In addition, we also compare our model with several machine learning algorithms. Our experimental results show that our approach is effective in ranking and classifying online product reviews.     

融合三重注意力和评论评分的深度推荐算法

许多购物网站中存在用户编写的大量评论信息,大部分推荐系统虽然利用了评论信息,但仍有很大的改进空间。一方面是评论中信息参差不齐,掺杂了很多无用信息;另一方面是大多数现有的推荐系统都假设一个用户对于某一商品特征的关注对于所有的商品都是相同的,无法准确体现用户偏好。本文提出一种融合三重注意力和评论评分的方面感知深度推荐模型ANAP（Attention and Neural Aspect Perception）,从词和特征2个层面出发,通过构造2种不同的注意力网络提取评论文本中的重要信息,降低无用信息的影响;为了准确体现用户偏好,通过构造注意力交互网络捕捉用户对不同项目各个方面的不同关注度,实现方面感知的细粒度建模。本文在6个真实数据集上进行实验,同时设计了注意力机制对比实验,结果表明ANAP模型有效提高了评分预测精度,平均绝对误差（Mean Absolute Error, MAE）比现有最佳算法降低了4.86个百分点。     

An OWA‐Based Ranking Approach for University Books Recommendation

Generally the book recommendation approaches are personalized in nature, that is, they utilize the users’ purchasing behavior to recommend them the book similar to their preferences. The main problem with the personalized recommendation is its knowledge requirement about users’ past preferences. As a result, these techniques fail in producing appropriate recommendation for a new user whose preferences are not known. The personalized recommendation also needs extra space to store the users’ preferences. In this paper, a framework to recommend books to university students for their studies is presented. In order to answer which books are to be included in the syllabus, a specialized way of recommendation, where recommendations from experts of the subjects at different universities are considered, is presented. We have suggested a ranked recommendation approach for books, which employ Ordered Weighted Aggregation (OWA), a fuzzy‐based aggregation, to aggregate the several ranking of the top universities. On the one hand, it does not need user prior preferences, and on the other hand, it eases the complexities of personalized recommendation to huge number of users and replaces it with a single ranked recommendation. The experimental results are compared with the existing positional aggregation algorithm that demonstrates significant improvement in the results with respect to various performance metrics.     

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.