A hybrid recommender system using artificial neural networks

In the context of recommendation systems, metadata information from reviews written for businesses has rarely been considered in traditional systems developed using content-based and collaborative filtering approaches. Collaborative filtering and content-based filtering are popular memory-based methods for recommending new products to the users but suffer from some limitations and fail to provide effective recommendations in many situations. In this paper, we present a deep learning neural network framework that utilizes reviews in addition to content-based features to generate model based predictions for the business-user combinations. We show that a set of content and collaborative features allows for the development of a neural network model with the goal of minimizing logloss and rating misclassification error using stochastic gradient descent optimization algorithm. We empirically show that the hybrid approach is a very promising solution when compared to standalone memory-based collaborative filtering method.     

Hybrid Recommender Systems: Survey and Experiments

Recommender systems represent user preferences for the purpose of suggesting items to purchase or examine. They have become fundamental applications in electronic commerce and information access, providing suggestions that effectively prune large information spaces so that users are directed toward those items that best meet their needs and preferences. A variety of techniques have been proposed for performing recommendation, including content-based, collaborative, knowledge-based and other techniques. To improve performance, these methods have sometimes been combined in hybrid recommenders. This paper surveys the landscape of actual and possible hybrid recommenders, and introduces a novel hybrid, EntreeC, a system that combines knowledge-based recommendation and collaborative filtering to recommend restaurants. Further, we show that semantic ratings obtained from the knowledge-based part of the system enhance the effectiveness of collaborative filtering.     

一种基于协作过滤的电子图书推荐系统

推荐系统中最常见信息过滤技术是基于内容的过滤和协作过滤,协作过滤由于有其自身的优点得到迅速发展,并得到广泛应用,但传统的协作过滤算法存在着稀疏性、扩展性和同义性等问题。本文提出一种基于评价矩阵列向量的图书协作过滤算法,并把这个算法应用到了一个数字图书馆的电子图书推荐系统中。此图书协作过滤算法主要计算图书之间的相似度而不是用户之间的相似度,可以大大降低计算量。实验也表明,这个算法比传统的基于用户的协作过滤算法有优势。     

Document recommendation for knowledge sharing in personal folder environments

Sharing sustainable and valuable knowledge among knowledge workers is a fundamental aspect of knowledge management. In organizations, knowledge workers usually have personal folders in which they organize and store needed codified knowledge (textual documents) in categories. In such personal folder environments, providing knowledge workers with needed knowledge from other workers’ folders is important because it increases the workers’ productivity and the possibility of reusing and sharing knowledge. Conventional recommendation methods can be used to recommend relevant documents to workers; however, those methods recommend knowledge items without considering whether the items are assigned to the appropriate category in the target user’s personal folders. In this paper, we propose novel document recommendation methods, including content-based filtering and categorization, collaborative filtering and categorization, and hybrid methods, which integrate text categorization techniques, to recommend documents to target worker’s personalized categories. Our experiment results show that the hybrid methods outperform the pure content-based and the collaborative filtering and categorization methods. The proposed methods not only proactively notify knowledge workers about relevant documents held by their peers, but also facilitate push-mode knowledge sharing.     

Hybrid immunizing solution for job recommender system

Two traditional recommendation techniques, content-based and collaborative filtering (CF), have been widely used in a broad range of domain areas. Both methods have their advantages and disadvantages, and some of the defects can be resolved by integrating both techniques in a hybrid model to improve the quality of the recommendation. In this article, we will present a problem-oriented approach to design a hybrid immunizing solution for job recommendation problem from applicant’s perspective. The proposed approach aims to recommend the best chances of opening jobs to the applicant who searches for job. It combines the artificial immune system (AIS), which has a powerful exploration capability in polynomial time, with the collaborative filtering, which can exploit the neighbors’ interests. We will discuss the design issues, as well as the hybridization process that should be applied to the problem. Finally, experimental studies are conducted and the results show the importance of our approach for solving the job recommendation problem.     

基于内容的推荐与协同过滤融合的新闻推荐方法

针对基于内容的新闻推荐方法中用户兴趣多样性的缺乏问题和混合推荐方法存在的冷启动问题,提出一种基于内容与协同过滤融合的方法进行新闻推荐。首先利用基于内容的方法发现用户既有兴趣;再用内容与行为的混合相似度模式,寻找目标用户的相似用户群,预测用户对特征词的兴趣度,发现用户潜在兴趣;然后将用户既有兴趣与潜在兴趣融合,得到兼具个性化和多样性的用户兴趣模型;最后将候选新闻与融合模型进行相似度计算,形成推荐列表。实验结果显示,与基于内容的推荐方法相比,所提方法的F-measure和整体多样性Diversity均有明显提高;与混合推荐方法相比,性能相当,但候选新闻无需耗时积累足够的用户点击量,不存在冷启动问题。     

基于深度学习的论文个性化推荐算法

该文基于学术搜索和数据挖掘平台Aminer向用户进行个性化推荐,提出了结合协同过滤推荐和基于内容推荐的混合模型,实验表明该算法可以有效解决新物品的推荐问题,即冷启动问题。其中在基于内容推荐的模型中,融合深度学习的方法,引进了词向量模型,将用户和论文映射到用词向量空间, 并使用WMD(Word Mover Distance)计算相似度。实验表明,与其他基线模型相比该文提出的推荐模型在准确率上显著提高了4%。     

A new approach for combining content-based and collaborative filters

With the development of e-commerce and the proliferation of easily accessible information, recommender systems have become a popular technique to prune large information spaces so that users are directed toward those items that best meet their needs and preferences. A variety of techniques have been proposed for performing recommendations, including content-based and collaborative techniques. Content-based filtering selects information based on semantic content, whereas collaborative filtering combines the opinions of other users to make a prediction for a target user. In this paper, we describe a new filtering approach that combines the content-based filter and collaborative filter to capitalize on their respective strengths, and thereby achieves a good performance. We present a series of recommendations on the selection of the appropriate factors and also look into different techniques for calculating user-user similarities based on the integrated information extracted from user profiles and user ratings. Finally, we experimentally evaluate our approach and compare it with classic filters, the result of which demonstrate the effectiveness of our approach.     

基于混合模式的文本过滤模型

文本过滤旨在帮助用户处理自己感兴趣的文本,提出了基于混合模式的文本过滤模式,其基本思想是将基于内容的过滤方法和合作过滤方法结合起来,给出了用户评沪的权威性和一致性度是,以便更好地运用用户的评注信息,在此基础上,结合用户的个人兴趣,给出了文硒特征抽取机制、文本推荐机制、文本与信息需求模型的匹配机制,该方法不依赖于具体的领域知识库,大大降低“噪音”影响,并可以适用于多媒体类型文件的过滤和信息服务。     

Symbolic data analysis tools for recommendation systems

Recommender systems have become an important tool to cope with the information overload problem by acquiring data about user behavior. After tracing the user’s behavior, through actions or rates, computational recommender systems use information- filtering techniques to recommend items. In order to recommend new items, one of the three major approaches is generally adopted: content-based filtering, collaborative filtering, or hybrid filtering. This paper presents three information-filtering methods, each of them based on one of these approaches. In our methods, the user profile is built up through symbolic data structures and the user and item correlations are computed through dissimilarity functions adapted from the symbolic data analysis (SDA) domain. The use of SDA tools has improved the performance of recommender systems, particularly concerning the find good items task measured by the half-life utility metric, when there is not much information about the user.     

Leveraging clustering approaches to solve the gray-sheep users problem in recommender systems

Recommender systems apply data mining and machine learning techniques for filtering unseen information and can predict whether a user would like a given item. This paper focuses on gray-sheep users problem responsible for the increased error rate in collaborative filtering based recommender systems. This paper makes the following contributions: we show that (1) the presence of gray-sheep users can affect the performance – accuracy and coverage – of the collaborative filtering based algorithms, depending on the data sparsity and distribution; (2) gray-sheep users can be identified using clustering algorithms in offline fashion, where the similarity threshold to isolate these users from the rest of community can be found empirically. We propose various improved centroid selection approaches and distance measures for the K-means clustering algorithm; (3) content-based profile of gray-sheep users can be used for making accurate recommendations. We offer a hybrid recommendation algorithm to make reliable recommendations for gray-sheep users. To the best of our knowledge, this is the first attempt to propose a formal solution for gray-sheep users problem. By extensive experimental results on two different datasets (MovieLens and community of movie fans in the FilmTrust website), we showed that the proposed approach reduces the recommendation error rate for the gray-sheep users while maintaining reasonable computational performance.     

Effective Hybrid Content-Based Collaborative Filtering Approach for Requirements Engineering

Requirements engineering (RE) is among the most valuable and critical processes in software development. The quality of this process significantly affects the success of a software project. An important step in RE is requirements elicitation, which involves collecting project-related requirements from different sources. Repositories of reusable requirements are typically important sources of an increasing number of reusable software requirements. However, the process of searching such repositories to collect valuable project-related requirements is time-consuming and difficult to perform accurately. Recommender systems have been widely recognized as an effective solution to such problem. Accordingly, this study proposes an effective hybrid content-based collaborative filtering recommendation approach. The proposed approach will support project stakeholders in mitigating the risk of missing requirements during requirements elicitation by identifying related requirements from software requirement repositories. The experimental results on the RALIC dataset demonstrate that the proposed approach considerably outperforms baseline collaborative filtering-based recommendation methods in terms of prediction accuracy and coverage in addition to mitigating the data sparsity and cold-start item problems.     

An Efficient Hybrid Music Recommender System Using an Incrementally Trainable Probabilistic Generative Model

This paper presents a hybrid music recommender system that ranks musical pieces while efficiently maintaining collaborative and content-based data, i.e., rating scores given by users and acoustic features of audio signals. This hybrid approach overcomes the conventional tradeoff between recommendation accuracy and variety of recommended artists. Collaborative filtering, which is used on e-commerce sites, cannot recommend nonbrated pieces and provides a narrow variety of artists. Content-based filtering does not have satisfactory accuracy because it is based on the heuristics that the user's favorite pieces will have similar musical content despite there being exceptions. To attain a higher recommendation accuracy along with a wider variety of artists, we use a probabilistic generative model that unifies the collaborative and content-based data in a principled way. This model can explain the generative mechanism of the observed data in the probability theory. The probability distribution over users, pieces, and features is decomposed into three conditionally independent ones by introducing latent variables. This decomposition enables us to efficiently and incrementally adapt the model for increasing numbers of users and rating scores. We evaluated our system by using audio signals of commercial CDs and their corresponding rating scores obtained from an e-commerce site. The results revealed that our system accurately recommended pieces including nonrated ones from a wide variety of artists and maintained a high degree of accuracy even when new users and rating scores were added.     

Informed Recommender: Basing Recommendations on Consumer Product Reviews

Recommender systems attempt to predict items in which a user might be interested, given some information about the user's and items' profiles. Most existing recommender systems use content-based or collaborative filtering methods or hybrid methods that combine both techniques (see the sidebar for more details). We created Informed Recommender to address the problem of using consumer opinion about products, expressed online in free-form text, to generate product recommendations. Informed recommender uses prioritized consumer product reviews to make recommendations. Using text-mining techniques, it maps each piece of each review comment automatically into an ontology.     

Personalisation in web computing and informatics: Theories, techniques, applications, and future research

Recently, personalised search engines and recommendation systems have been widely adopted by users who require assistance in searching, classifying, and filtering information. This paper presents an overview of the field of personalisation systems and describes current state-of-the-art methods and techniques. It reviews approaches for (1) user profiling, including behaviour, preference, and intention modelling; (2) content modelling, comprising content representation, analysis, and classification; and (3) filtering methods for recommendation, classified into four main categories: rule-based, content-based, collaborative, and hybrid filtering. The paper also discusses personalisation systems in different domains, and various techniques and their limitations. Finally, it identifies several issues and possible directions for further research that can improve recommendation capabilities and enhance personalised systems.     

Exploit latent Dirichlet allocation for collaborative filtering

Previous work on the one-class collaborative filtering (OCCF) problem can be roughly categorized into pointwise methods, pairwise methods, and content-based methods. A fundamental assumption of these approaches is that all missing values in the user-item rating matrix are considered negative. However, this assumption may not hold because the missing values may contain negative and positive examples. For example, a user who fails to give positive feedback about an item may not necessarily dislike it; he may simply be unfamiliar with it. Meanwhile, content-based methods, e.g. collaborative topic regression (CTR), usually require textual content information of the items, and thus their applicability is largely limited when the text information is not available. In this paper, we propose to apply the latent Dirichlet allocation (LDA) model on OCCF to address the above-mentioned problems. The basic idea of this approach is that items are regarded as words, users are considered as documents, and the user-item feedback matrix constitutes the corpus. Our model drops the strong assumption that missing values are all negative and only utilizes the observed data to predict a user’s interest. Additionally, the proposed model does not need content information of the items. Experimental results indicate that the proposed method outperforms previous methods on various ranking-oriented evaluation metrics. We further combine this method with a matrix factorization-based method to tackle the multi-class collaborative filtering (MCCF) problem, which also achieves better performance on predicting user ratings.     

Common structure and properties of filtering systems

Recommendation systems have been studied actively since the 1990s. Generally, recommendation systems choose one or more candidates from a set of candidates through a filtering process. Methods of filtering can be divided into two categories: collaborative filtering, in which candidates are chosen based on choices of other persons whose interests or tastes are similar, and content-based filtering, in which items are chosen based on the profile or action history of the recommendee. However, these methods share the same structure in the sense that both of them recommend items based on relevance degrees of items and references, as well as relevance degrees between the recommendee and each reference. Most discussions about recommendation systems focus on the methods of choosing recommended candidates; few focus on foundational concepts of recommendation conditions that systems must satisfy, and problems that current systems have compared with these conditions. In this paper, recommendation systems are reconsidered from the viewpoint of multi-criteria decision making. Conventional filtering methods (e.g., collaborative filtering and content-based filtering) are formulated as linear weighted sum type recommendation systems. Several properties of linear weighted sum type recommendation systems are identified and formulated from the viewpoint of voting.