Exploiting synergies between semantic reasoning and personalization strategies in intelligent recommender systems: A case study

Current recommender systems attempt to identify appealing items for a user by applying syntactic matching techniques, which suffer from significant limitations that reduce the quality of the offered suggestions. To overcome this drawback, we have developed a domain-independent personalization strategy that borrows reasoning techniques from the Semantic Web, elaborating recommendations based on the semantic relationships inferred between the user’s preferences and the available items. Our reasoning-based approach improves the quality of the suggestions offered by the current personalization approaches, and greatly reduces their most severe limitations. To validate these claims, we have carried out a case study in the Digital TV field, in which our strategy selects TV programs interesting for the viewers from among the myriad of contents available in the digital streams. Our experimental evaluation compares the traditional approaches with our proposal in terms of both the number of TV programs suggested, and the users’ perception of the recommendations. Finally, we discuss concerns related to computational feasibility and scalability of our approach.     

Exploring synergies between content-based filtering and Spreading Activation techniques in knowledge-based recommender systems

Recommender systems fight information overload by selecting automatically items that match the personal preferences of each user. The so-called content-based recommenders suggest items similar to those the user liked in the past, using syntactic matching mechanisms. The rigid nature of such mechanisms leads to recommending only items that bear strong resemblance to those the user already knows. Traditional collaborative approaches face up to overspecialization by considering the preferences of other users, which causes other severe limitations. In this paper, we avoid the intrinsic pitfalls of collaborative solutions and diversify the recommendations by reasoning about the semantics of the user’s preferences. Specifically, we present a novel content-based recommendation strategy that resorts to semantic reasoning mechanisms adopted in the Semantic Web, such as Spreading Activation techniques and semantic associations. We have adopted these mechanisms to fulfill the personalization requirements of recommender systems, enabling to discover extra knowledge about the user’s preferences and leading to more accurate and diverse suggestions. Our approach is generic enough to be used in a wide variety of domains and recommender systems. The proposal has been preliminary evaluated by statistics-driven tests involving real users in the recommendation of Digital TV contents. The results reveal the users’ satisfaction regarding the accuracy and diversity of the reasoning-driven content-based recommendations.     

Improving the Quality of the Personalized Electronic Program Guide

As Digital TV subscribers are offered more and more channels, it is becoming increasingly difficult for them to locate the right programme information at the right time. The personalized Electronic Programme Guide (pEPG) is one solution to this problem; it leverages artificial intelligence and user profiling techniques to learn about the viewing preferences of individual users in order to compile personalized viewing guides that fit their individual preferences. Very often the limited availability of profiling information is a key limiting factor in such personalized recommender systems. For example, it is well known that collaborative filtering approaches suffer significantly from the sparsity problem, which exists because the expected item-overlap between profiles is usually very low. In this article we address the sparsity problem in the Digital TV domain. We propose the use of data mining techniques as a way of supplementing meagre ratings-based profile knowledge with additional item-similarity knowledge that can be automatically discovered by mining user profiles. We argue that this new similarity knowledge can significantly enhance the performance of a recommender system in even the sparsest of profile spaces. Moreover, we provide an extensive evaluation of our approach using two large-scale, state-of-the-art online systems—PTVPlus, a personalized TV listings portal and Físchlár, an online digital video library system.     

User Modeling for Personalized City Tours

Several current support systems for travel and tourism are aimed at providing information in a personalized manner, taking users' interests and preferences into account. In this vein, personalized systems observe users' behavior and, based thereon, make generalizations and predictions about them. This article describes a user modeling server that offers services to personalized systems with regard to the analysis of user actions, the representation of assumptions about the user, and the inference of additional assumptions based on domain knowledge and characteristics of similar users. The system is open and compliant with major standards, allowing it to be easily accessed by clients that need personalization services.     

Personalization on a peer-to-peer television system

We introduce personalization on Tribler, a peer-to-peer (P2P) television system. Personalization allows users to browse programs much more efficiently according to their taste. It also enables to build social networks that can improve the performance of current P2P systems considerably, by increasing content availability, trust and the realization of proper incentives to exchange content. This paper presents a novel scheme, called BuddyCast, that builds such a social network for a user by exchanging user interest profiles using exploitation and exploration principles. Additionally, we show how the interest of a user in TV programs can be predicted from the zapping behavior by the introduced user-item relevance models, thereby avoiding the explicit rating of TV programs. Further, we present how the social network of a user can be used to realize a truly distributed recommendation of TV programs. Finally, we demonstrate a novel user interface for the personalized peer-to-peer television system that encompasses a personalized tag-based navigation to browse the available distributed content. The user interface also visualizes the social network of a user, thereby increasing community feeling which increases trust amongst users and within available content and creates incentives of to exchange content within the community.     

An MHP framework to provide intelligent personalized recommendations about digital TV contents

Digital Television will bring a significant increase in the amount of channels and programs available to end users, with many more difficulties to find contents appealing to them among a myriad of irrelevant information. Thus, automatic content recommenders should receive special attention in the following years to improve their assistance to users. The current content recommenders have important deficiencies that hamper their wide acceptance. In this paper, we present a new approach for automatic content recommendation that significantly reduces those deficiencies. This approach, based on Semantic Web technologies, has been implemented in the AdVAnced Telematic search of Audiovisual contents by semantic Reasoning tool, a hybrid content recommender that makes extensive use of well‐known standards, such as Multimedia Home Platform, TV‐Anytime and OWL. Also, we have carried out an experimental evaluation, the results of which show that our proposal performs better than other existing approaches. Copyright © 2007 John Wiley & Sons, Ltd.     

Mining affective needs of automotive industry customers for building a mass-customization recommender system

Mass customization systems aim to receive customer preferences in order to facilitate personalization of products and services. Current online configuration systems are unable to efficiently identify real customer affective needs because they offer an excess variety of products that usually confuse customers. On the other hand, mining affective customer needs may result in recommender systems, which can enhance existing configuration systems by recommending initial configurations according to customer affective needs. This paper introduces a mass customization recommender system that exploits data mining techniques on automotive industry customer data aiming at revealing associations between user affective needs and the design parameters of automotive products. One key novelty of the presented approach is that it deploys the Citarasa engineering, a methodology that focuses on the provision of the appropriate characterizations on customer data in order to associate them with customer affective needs. Based on the application of classification techniques we build a recommendation engine, which is evaluated in terms of user satisfaction, tool’s effectiveness, usefulness and reliability among other parameters.     

Automatic metadata expansion and indirect collaborative filtering for TV program recommendation system

TV Program recommendation is a good example of a novel application of networked appliances using personalization technologies. The aim of this paper is to propose methods to improve the accuracy of TV program recommendation. Automatic metadata expansion (AME) is a method to enhance TV program metadata from electronic program guide (EPG) data, and indirect collaborative filtering (ICF) is a method to recommend non-persistent items such as TV programs based on the preferences of other members in a community. In this paper, the effectiveness of these methods is confirmed through experiments. This online TV recommendation system is currently being used by 230,000 members in Japan. The result of the actual operation is also discussed.     

A hybrid content-based and item-based collaborative filtering approach to recommend TV programs enhanced with singular value decomposition

With the advent of new cable and satellite services, and the next generation of digital TV systems, people are faced with an unprecedented level of program choice. This often means that viewers receive much more information than they can actually manage, which may lead them to believe that they are missing programs that could likely interest them. In this context, TV program recommendation systems allow us to cope with this problem by automatically matching user’s likes to TV programs and recommending the ones with higher user preference.This paper describes the design, development, and startup of queveo.tv: a Web 2.0 TV program recommendation system. The proposed hybrid approach (which combines content-filtering techniques with those based on collaborative filtering) also provides all typical advantages of any social network, such as supporting communication among users as well as allowing users to add and tag contents, rate and comment the items, etc. To eliminate the most serious limitations of collaborative filtering, we have resorted to a well-known matrix factorization technique in the implementation of the item-based collaborative filtering algorithm, which has shown a good behavior in the TV domain. Every step in the development of this application was taken keeping always in mind the main goal: to simplify as much as possible the user task of selecting what program to watch on TV.     

A semantic approach to improve neighborhood formation in collaborative recommender systems

Automatic recommenders are now omnipresent in e-commerce websites, as selecting and offering to users products they may be interested in can considerably increase sales revenue. The most popular recommendation strategy is currently considered to be the collaborative filtering technique, based on offering to the user who will receive the recommendation items that were appealing to other individuals with similar preferences (the so-called neighbors). On the other hand, its principal obstacle is the sparsity problem, related to the difficulty to find overlappings in ratings when there are many items. As the product catalogue of these sites gets more and more diverse, a new problem has arisen that happens when users share likings for lots of products (for which they are reckoned to be neighbors) but they differ in products similar to the one that is being considered for recommendation. They are fake neighbors. Narrowing the range of products on which similarities between users are sought can help to avoid this, but it usually causes a worsening of the sparsity problem because the chances of finding overlappings gets lower. In this paper, a new strategy is proposed based on semantic reasoning that aims to improve the neighborhood formation in order to overcome the aforementioned fake neighborhood problem. Our approach is aimed at making more flexible the search for semantic similarities between different products, and thus not require users to rate the same products in order to be compared.     

Incentivized provision of metadata, semantic reasoning and time-driven filtering: Making a puzzle of personalized e-commerce

e-Commerce recommender systems select potentially interesting products for users by looking at their purchase histories and preferences. In order to compare the available products against those included in the user’s profile, semantics-based recommendation strategies consider metadata annotations that describe their main attributes. Besides, to ensure successful suggestions of products, these strategies adapt the recommendations as the user’s preferences evolve over time. Traditional approaches face two limitations related to the aforementioned features. First, product providers are not typically willing to take on the tedious task of annotating accurately a huge diversity of commercial items, thus leading to a substantial impoverishment of the personalization quality. Second, the adaptation process of the recommendations misses the time elapsed since the user has bought an item, which is an essential parameter that affects differently to each purchased product. This results in some pointless recommendations, e.g. including regularly items that the users are only willing to buy sporadically. In order to fight both limitations, we propose a personalized e-commerce system with two main features. On the one hand, we incentivize the users to provide high-quality metadata for commercial products; on the other, we explore a strategy that offers time-aware recommendations by combining semantic reasoning about these annotations with item-specific time functions. The synergetic effects derived from this combination lead to suggestions adapted to the particular needs of the users at any time. This approach has been experimentally validated with a set of users who accessed our personalized e-commerce system through a range of fixed and handheld consumer devices.     

Topic-tracking-based dynamic user modeling with TV recommendation applications

One of the challenging issues in TV recommendation applications based on implicit rating data is how to make robust recommendation for the users who irregularly watch TV programs and for the users who have their time-varying preferences on watching TV programs. To achieve the robust recommendation for such users, it is important to capture dynamic behaviors of user preference on watched TV programs over time. In this paper, we propose a topic tracking based dynamic user model (TDUM) that extends the previous multi-scale dynamic topic model (MDTM) by incorporating topic-tracking into dynamic user modeling. In the proposed TDUM, the prior of the current user preference is estimated as a weighted combination of the previously learned preferences of a TV user in multi-time spans where the optimal weight set is found in the sense of the evidence maximization of the Bayesian probability. So, the proposed TDUM supports the dynamics of public users’ preferences on TV programs for collaborative filtering based TV program recommendation and the highly ranked TV programs by similar watching taste user group (topic) can be traced with the same topic labels epoch by epoch. We also propose a rank model for TV program recommendation. In order to verify the effectiveness of the proposed TDUM and rank model, we use a real data set of the TV programs watched by 1,999 TV users for 7 months. The experiment results demonstrate that the proposed TDUM outperforms the Latent Dirichlet Allocation (LDA) model and the MDTM in log-likelihood for the topic modeling performance, and also shows its superiority compared to LDA, MDTM and Bayesian Personalized Rank Matrix Factorization (BPRMF) for TV program recommendation performance in terms of top-N precision-recall.     

Magpie: Experiences in supporting Semantic Web browsing

Magpie has been one of the first truly effective approaches to bringing semantics into the web browsing experience. The key innovation brought by Magpie was the replacement of a manual annotation process by an automatically associated ontology-based semantic layer over web resources, which ensured added value at no cost for the user. Magpie also differs from older open hypermedia systems: its associations between entities in a web page and semantic concepts from an ontology enable link typing and subsequent interpretation of the resource. The semantic layer in Magpie also facilitates locating semantic services and making them available to the user, so that they can be manually activated by a user or opportunistically triggered when appropriate patterns are encountered during browsing. In this paper we track the evolution of Magpie as a technology for developing open and flexible Semantic Web applications. Magpie emerged from our research into user-accessible Semantic Web, and we use this viewpoint to assess the role of tools like Magpie in making semantic content useful for ordinary users. We see such tools as crucial in bootstrapping the Semantic Web through the automation of the knowledge generation process.     

A hybrid collaborative filtering method for multiple-interests and multiple-content recommendation in E-Commerce

Recommender systems apply knowledge discovery techniques to the problem of making personalized recommendations for products or services during a live interaction. These systems, especially collaborative filtering based on user, are achieving widespread success on the Web. The tremendous growth in the amount of available information and the kinds of commodity to Web sites in recent years poses some key challenges for recommender systems. One of these challenges is ability of recommender systems to be adaptive to environment where users have many completely different interests or items have completely different content (We called it as Multiple interests and Multiple-content problem). Unfortunately, the traditional collaborative filtering systems can not make accurate recommendation for the two cases because the predicted item for active user is not consist with the common interests of his neighbor users. To address this issue we have explored a hybrid collaborative filtering method, collaborative filtering based on item and user techniques, by combining collaborative filtering based on item and collaborative filtering based on user together. Collaborative filtering based on item and user analyze the user-item matrix to identify similarity of target item to other items, generate similar items of target item, and determine neighbor users of active user for target item according to similarity of other users to active user based on similar items of target item.In this paper we firstly analyze limitation of collaborative filtering based on user and collaborative filtering based on item algorithms respectively and emphatically make explain why collaborative filtering based on user is not adaptive to Multiple-interests and Multiple-content recommendation. Based on analysis, we present collaborative filtering based on item and user for Multiple-interests and Multiple-content recommendation. Finally, we experimentally evaluate the results and compare them with collaborative filtering based on user and collaborative filtering based on item, respectively. The experiments suggest that collaborative filtering based on item and user provide better recommendation quality than collaborative filtering based on user and collaborative filtering based on item dramatically.     

Facebook single and cross domain data for recommendation systems

The emergence of social networks and the vast amount of data that they contain about their users make them a valuable source for personal information about users for recommender systems. In this paper we investigate the feasibility and effectiveness of utilizing existing available data from social networks for the recommendation process, specifically from Facebook. The data may replace or enrich explicit user ratings. We extract from Facebook content published by users on their personal pages about their favorite items and preferences in the domain of recommendation, and data about preferences related to other domains to allow cross-domain recommendation. We study several methods for integrating Facebook data with the recommendation process and compare the performance of these methods with that of traditional collaborative filtering that utilizes user ratings. In a field study that we conducted, recommendations obtained using Facebook data were tested and compared for 95 subjects and their crawled Facebook friends. Encouraging results show that when data is sparse or not available for a new user, recommendation results relying solely on Facebook data are at least equally as accurate as results obtained from user ratings. The experimental study also indicates that enriching sparse rating data by adding Facebook data can significantly improve results. Moreover, our findings highlight the benefits of utilizing cross domain Facebook data to achieve improvement in recommendation performance.     

On analyzing user preference dynamics with temporal social networks

The preferences adopted by individuals are constantly modified as these are driven by new experiences, natural life evolution and, mainly, influence from friends. Studying these temporal dynamics of user preferences has become increasingly important for personalization tasks in information retrieval and recommendation systems domains. However, existing models are too constrained for capturing the complexity of the underlying phenomenon. Online social networks contain rich information about social interactions and relations. Thus, these become an essential source of knowledge for the understanding of user preferences evolution. In this work, we investigate the interplay between user preferences and social networks over time. First, we propose a temporal preference model able to detect preference change events of a given user. Following this, we use temporal networks concepts to analyze the evolution of social relationships and propose strategies to detect changes in the network structure based on node centrality. Finally, we look for a correlation between preference change events and node centrality change events over Twitter and Jam social music datasets. Our findings show that there is a strong correlation between both change events, specially when modeling social interactions by means of a temporal network.     

Efficient Adaptive-Support Association Rule Mining for Recommender Systems

Collaborative recommender systems allow personalization for e-commerce by exploiting similarities and dissimilarities among customers' preferences. We investigate the use of association rule mining as an underlying technology for collaborative recommender systems. Association rules have been used with success in other domains. However, most currently existing association rule mining algorithms were designed with market basket analysis in mind. Such algorithms are inefficient for collaborative recommendation because they mine many rules that are not relevant to a given user. Also, it is necessary to specify the minimum support of the mined rules in advance, often leading to either too many or too few rules; this negatively impacts the performance of the overall system. We describe a collaborative recommendation technique based on a new algorithm specifically designed to mine association rules for this purpose. Our algorithm does not require the minimum support to be specified in advance. Rather, a target range is given for the number of rules, and the algorithm adjusts the minimum support for each user in order to obtain a ruleset whose size is in the desired range. Rules are mined for a specific target user, reducing the time required for the mining process. We employ associations between users as well as associations between items in making recommendations. Experimental evaluation of a system based on our algorithm reveals performance that is significantly better than that of traditional correlation-based approaches.     

Property-based collaborative filtering for health-aware recommender systems

Recommender systems aim at solving the problem of information overload by selecting items (commercial products, educational assets, TV programs, etc.) that match the consumers’ interests and preferences. Recently, there have been approaches to drive the recommendations by the information stored in electronic health records, for which the traditional strategies applied in online shopping, e-learning, entertainment and other areas have several pitfalls. This paper addresses those problems by introducing a new filtering strategy, centered on the properties that characterize the items and the users. Preliminary experiments with real users have proved that this approach outperforms previous ones in terms of consumers’ satisfaction with the recommended items. The benefits are especially apparent among people with specific health concerns.