Abstract: Several approaches to collaborative filtering have been studied but seldom have studies been reported for large (several millionusers and items) and dynamic (the underlying item set is continually changing) settings. In this paper we describe our approach to collaborative filtering for generating personalized recommendations for users of Google News. We generate recommendations using three approaches: collaborative filtering using MinHash clustering, Probabilistic Latent Semantic Indexing (PLSI), and covisitation counts. We combine recommendations from different algorithms using a linear model. Our approach is content agnostic and consequently domain independent, making it easily adaptable for other applications and languages with minimal effort. This paper will describe our algorithms and system setup in detail, and report results of running the recommendations engine on Google News.

Abstract: I. Modeling Technologies.- User Models for Adaptive Hypermedia and Adaptive Educational Systems.- User Profiles for Personalized Information Access.- Data Mining for Web Personalization.- Generic User Modeling Systems.- Web Document Modeling.- II. Adaptation Technologies.- Personalized Search on the World Wide Web.- Adaptive Focused Crawling.- Adaptive Navigation Support.- Collaborative Filtering Recommender Systems.- Content-Based Recommendation Systems.- Case-Based Recommendation.- Hybrid Web Recommender Systems.- Adaptive Content Presentation for the Web.- Adaptive 3D Web Sites.- III. Applications.- Adaptive Information for Consumers of Healthcare.- Personalization in E-Commerce Applications.- Adaptive Mobile Guides.- Adaptive News Access.- IV. Challenges.- Adaptive Support for Distributed Collaboration.- Recommendation to Groups.- Privacy-Enhanced Web Personalization.- Open Corpus Adaptive Educational Hypermedia.- Semantic Web Technologies for the Adaptive Web.- Usability Engineering for the Adaptive Web.

Abstract: Although personalized search has been proposed for many years and many personalization strategies have been investigated, it is still unclear whether personalization is consistently effective on different queries for different users, and under different search contexts. In this paper, we study this problem and get some preliminary conclusions. We present a large-scale evaluation framework for personalized search based on query logs, and then evaluate five personalized search strategies (including two click-based and three profile-based ones) using 12-day MSN query logs. By analyzing the results, we reveal that personalized search has significant improvement over common web search on some queries but it also has little effect on other queries (e.g., queries with small click entropy). It even harms search accuracy under some situations. Furthermore, we show that straightforward click-based personalization strategies perform consistently and considerably well, while profile-based ones are unstable in our experiments. We also reveal that both long-term and short-term contexts are very important in improving search performance for profile-based personalized search strategies.

Abstract: Personalization technologies and recommender systems help online consumers avoid information overload by making suggestions regarding which information is most relevant to them. Most online shopping sites and many other applications now use recommender systems. Two new recommendation techniques leverage multicriteria ratings and improve recommendation accuracy as compared with single-rating recommendation approaches. Taking full advantage of multicriteria ratings in personalization applications requires new recommendation techniques. In this article, we propose several new techniques for extending recommendation technologies to incorporate and leverage multicriteria rating information.

Abstract: Personalized services are increasingly popular in the Internet world This study identifies theories related to the use of personalized content services and their effect on user satisfaction Three major theories have been identified-information overload, uses and gratifications, and user involvement The information overload theory implies that user satisfaction increases when the recommended content fits user interests (ie, the recommendation accuracy increases) The uses and gratifications theory indicates that motivations for information access affect user satisfaction The user involvement theory implies that users prefer content recommended by a process in which they have explicit involvement In this research, a research model was proposed to integrate these theories and two experiments were conducted to examine the theoretical relationships Our findings indicate that information overload and uses and gratifications are two major theories for explaining user satisfaction with personalized services Personalized services can reduce information overload and, hence, increase user satisfaction, but their effects may be moderated by the motivation for information access The effect is stronger for users whose motivation is in searching for a specific target This implies that content recommendation would be more useful for knowledge management systems, where users are often looking for specific knowledge, rather than for general purpose Web sites, whose customers often come for scanning Explicit user involvement in the personalization process may affect a user's perception of customization, but has no significant effect on overall satisfaction

Abstract: Destination marketing organizations invest considerable amounts of money in the development of Web sites as part of their overall promotion efforts. With increasing pressure on their budgets, it becomes ever more important for these organizations to assess the effectiveness of their Web sites, evaluate the return on their investments, and derive feedback on necessary improvements. Web site evaluation measures have been proposed in many ways and various contexts over the past decade. The study presented in this article used a qualitative meta-analysis methodology to synthesize the diverse findings. A unified framework of commonly used Web site success factors emerged from the analysis and included a total of nine factors: (1) information quality; (2) ease of use; (3) responsiveness; (4) security/privacy; (5) visual appearance; (6) trust; (7) interactivity; (8) personalization; and (9) fulfillment. Additional factors to further inform Web evaluation efforts were identified based on Werthner and Klein's dime...

Abstract: Every user has a distinct background and a specific goal when searching for information on the Web. The goal of Web search personalization is to tailor search results to a particular user based on that user's interests and preferences. Effective personalization of information access involves two important challenges: accurately identifying the user context and organizing the information in such a way that matches the particular context. We present an approach to personalized search that involves building models of user context as ontological profiles by assigning implicitly derived interest scores to existing concepts in a domain ontology. A spreading activation algorithm is used to maintain the interest scores based on the user's ongoing behavior. Our experiments show that re-ranking the search results based on the interest scores and the semantic evidence in an ontological user profile is effective in presenting the most relevant results to the user.

Abstract: Current systems used in education follow a consistent design pattern, one that is not supportive of lifelong learning or personalization, is asymmetric in terms of user capability, and which is disconnected from the global ecology of Internet services. In this paper we propose an alternative design pattern for educational systems that emphasizes symmetric connections with a range of services both in formal and informal learning, work, and leisure, and identify strategies for implementation and experimentation.

Abstract: Purpose – The object of this paper is to help to understand what it is all about in question when talking about personalization.Design/methodology/approach – A conceptual framework of personalization is presented, based on the literature.Findings – Marketers are looking increasingly at personalization to help them improve the performance of their efforts. However, personalization seems to be hard to apply. Some of these problems are caused by the fact that personalization means something different to each business and to the different actors in the value chain. This lack of agreement regarding the meaning of personalization limits successful communication between the different actors who produce or buy services and products that are connection with personalized marketing. This hinders co‐operation between service providers and marketers who are willing to apply personalization.Originality/value – It is hoped that the framework is useful when discussing and developing the idea of personalization further.

Abstract: Enhancements to customer care capabilities can be prioritized and presented using a repeatable methodology which allows information to be collected, processed, and utilized in a uniform fashion across engagements. Such a methodology can be designed so as to be flexible enough for any customization which is required in particular circumstances. Various tools which can be used in such a methodology include computerized surveys, evaluation formulae, prioritization graphs, and weighing scales.

Abstract: Business and operations strategists have long sought to formulate strategies that would serve profitably for a market of one. Two decades after its conception, there is growing evidence that mass customization strategy is transforming into a mass personalization strategy, making the market of one a reality, at least in select industries. The degree of transformation of a company depends on the extent to which its product is soft, i.e., can be produced electronically. Thus, at the lower end of the personalization spectrum are manufacturing companies engaged in producing hard, configurable products, while on the high end of the spectrum are service companies whose product can be totally configured and delivered electronically. The underlying factors that are enabling this transformation, in our view, are: (1) development of information technologies such as peer to peer (P2P), business to consumer (B2C), and Web 2.0, (2) near-universal availability of the Internet, (3) customer willingness and preparedness to be integrated into the process of product co-design and co-creation, (4) modern manufacturing systems, such as flexible manufacturing and, of course, (5) mass customization tools such as modularity and delayed differentiation, which help reduce manufacturing cost and cycle times and (6) deployment of customer-satisfaction-specific software called customer relationship management (CRM) to engender customer retention. Due to the importance and strategic success of affordable personalization, this issue is dedicated to that theme. The articles included in this issue would, I believe, serve as significant decision support mechanisms for companies pursuing a mass customization and personalization strategy. In addition to providing a brief perspective on articles included in this issue, we also summarize the state of the art of mass customization research.

Abstract: Multi-pronged strategies are needed to reconcile the tension between personalization and privacy.

Abstract: The study of intelligent user interfaces and user modeling and adaptation is well suited for augmenting educational visits to museums. We have defined a novel integrated framework for museum visits and claim that such a framework is essential in such a vast domain that inherently implies complex interactivity. We found that it requires a significant investment in software and hardware infrastructure, design and implementation of intelligent interfaces, and a systematic and iterative evaluation of the design and functionality of user interfaces, involving actual visitors at every stage. We defined and built a suite of interactive and user-adaptive technologies for museum visitors, which was then evaluated at the Buonconsiglio Castle in Trento, Italy: (1) animated agents that help motivate visitors and focus their attention when necessary, (2) automatically generated, adaptive video documentaries on mobile devices, and (3) automatically generated post-visit summaries that reflect the individual interests of visitors as determined by their behavior and choices during their visit. These components are supported by underlying user modeling and inference mechanisms that allow for adaptivity and personalization. Novel software infrastructure allows for agent connectivity and fusion of multiple positioning data streams in the museum space. We conducted several experiments, focusing on various aspects of PEACH. In one, conducted with 110 visitors, we found evidence that even older users are comfortable interacting with a major component of the system.

Abstract: Natalia Stash received her PhD from the Eindhoven University of Technology (TU/e), The Netherlands. The title of her thesis is "Incorporating Cognitive/Learning Styles in a General-Purpose Adaptive Hypermedia System". She currently participates in the CHIP project (Cultural Heritage Information Personalization) located at the Rijksmuseum in Amsterdam. Her research interests include adaptive web-based systems, semantic web technologies, learning styles, e-culture applications.

Abstract: Consumer studies demonstrate that online users value personalized content. At the same time, providing personalization on websites seems quite profitable for web vendors. This win-win situation is however marred by privacy concerns since personalizing people's interaction entails gathering considerable amounts of data about them. As numerous recent surveys have consistently demonstrated, computer users are very concerned about their privacy on the Internet. Moreover, the collection of personal data is also subject to legal regulations in many countries and states. Both user concerns and privacy regulations impact frequently used personalization methods. This article analyzes the tension between personalization and privacy, and presents approaches to reconcile the both.

Abstract: The present invention relates to a system and methodology providing a user interface that can be employed by contactors and contactees in conjunction with a communications architecture for identifying and establishing an optimal communication based on preferences, capabilities, contexts and goals of the parties to engage in the communication. The user interface can include a graphical display having a plurality of display objects and associated input fields operable by one or more parties to a communication in order to facilitate convenient access, control, personalization and communications via the communications architecture. For example, configuration capabilities are provided in the user interface to enable operational adjustments to one or more operating parameters, communications groupings, policies and/or context preferences relating to a preferred modality of communication and to potential parties of communication between the contactors and contactees. User interface controls are also provided for defining deterministic policies and for encoding preferences for cost-benefit analyses.

Abstract: The first generation of the World Wide Web has been characterized by the interaction between the user and the medium: Web sites offer information and services; new applications and even new business models emerged for institutions that offer a better information search experience, more well-informed purchase decisions and, more recently, for the sharing and the collaborative treatment of content. The next generation of the Web is reflected in the proliferating platforms for sharing and collaboration and in the design of Web 2.0, which is proactively oriented towards social activities in the Web. The social flair of the Web poses new challenges for the data mining community. Social networking in the Web is a phenomenon of scientific interest per se; there is demand for flexible and robust community discovery technologies but also for interdisciplinary research on the rules and behavioral patterns that emerge and characterize community formation and evolution. Further, the social Web poses challenges for the individual; assistance and ultimately, personalization broad scope of activities, including the traditional search for documents, the less traditional search for multimedia content and the search for similar people and for answers to poorly articulated information needs. Moreover, the misuse potential of social formations cannot be stressed enough: People are confronted with unreliable or even malicious content, with surveillance and even stealth of information and of personal data; detection and protection mechanisms are needed here, based on a deep understanding of patterns of misuse and misbehavior. Finally, the diversity of social structures in the Web must be kept in mind: Social structures in the Web take many forms, including wikis and folksonomies where people contribute semantically rich content, platforms for collaborative annotations where people enrich existing content, bulletin boards and similar fora where people seek for advice but also establish new contacts, but also the implicit communities to be found in auction platforms and among the reviewers of products and services; these are communities where reputation and trust play a mission-critical role. Data miners are expected to deliver solutions for the challenges in searching, personalizing, understanding and protecting those social structures. In addition to online communities, this joint workshop will also invite submissions on generic social network systems, including social network modeling, growth and evolution dynamics of social networks, graph-related algorithms, multi-agent based social network simulation, trend prediction of social network evolution, and applications in related domains. The joint workshop of WEBKDD and SNA-KDD '2007 aims to bring together practitioners and researchers with a specific focus on the emerging trends and industry needs associated with the traditional Web, the social Web, and other forms of social networking systems. This includes (1) data mining advances on the discovery and analysis of communities, on personalization for solitary activities (like search) and social activities (like discovery of potential friends), on the analysis of user behavior in open fora (like conventional sites, blogs and fora) and in commercial platforms (like e-auctions) and on the associated security and privacy-preservation challenges; (2) social network modeling, scalable, customizable social network infrastructure construction , dynamic growth and evolution patterns identification and discovery using machine learning approaches or multi-agent based simulation.

Abstract: It has been recognized that e-commerce and mass customization will emerge as a primary style of manufacturing. The main challenge for such a paradigm originates from difficulties in personalization - providing support for customers to find the most valuable products that match their heterogeneous needs. Traditional approaches to the personalization problem adopt pre-defined formats to describe the customer requirements. This always leads to distortion in eliciting requirement information and thus inaccurate recommendations. Knowledge discovery lends itself to dealing with semi-structured data and makes it possible to capture customer requirements more accurately. This paper proposes an associative classification-based recommendation system for personalization in B2C e-commerce applications. Knowledge discovery techniques are applied to support personalization according to an inner established model that anticipates customer heterogeneous requirements. The framework and methodology of the associative classification-based recommendation system have been addressed. The system analysis, design, and implementation issues in an Internet programming environment are presented. The feasibility of the proposed recommendation system has been validated with a prototype for personalization in mobile phone B2C e-commerce applications.

Abstract: A novel online recommender system builds profiling models and offers suggestions without the user taking the lead.

Abstract: List of Figures. List of Tables. Preface. 1 Introduction. 1.1 A paradigm shift. 1.2 Electronic commerce. 1.3 Agents and e-commerce. 1.4 Further reading. 1.5 Exercises and topics for discussion. 2 Software agents. 2.1 Characteristics of agents. 2.2 Agents as intentional systems. 2.3 Making decisions. 2.4 Planning. 2.5 Learning. 2.6 Agent architectures. 2.7 Agents in perspective. 2.8 Methodologies and languages. 2.9 Further reading. 2.10 Exercises and topics for discussion. 3 Multi-agent systems. 3.1 Characteristics of multi-agent systems. 3.2 Interaction. 3.3 Agent communication. 3.4 Ontologies. 3.5 Cooperative problem solving. 3.6 Virtual organisations as multi-agent systems. 3.7 Infrastructure requirements for open multi-agent systems. 3.8 Further reading. 3.9 Exercises and topics for discussion. 4 Shopping Agents. 4.1 Consumer buying behaviour model. 4.2 Comparison shopping. 4.3 Working for the user. 4.4 How shopping agents work. 4.5 Limitations and issues. 4.6 Further reading. 4.7 Exercises and topics for discussion. 5 Middle agents. 5.1 Matching. 5.2 Classification of middle agents. 5.3 Describing capabilities. 5.4 LARKS. 5.5 OWL-S. 5.6 Further reading. 5.7 Exercises and topics for discussion. 6 Recommender systems. 6.1 Information needed. 6.2 Providing recommendations. 6.3 Recommendation technologies. 6.4 Content-based filtering. 6.5 Collaborative filtering. 6.6 Combining content and collaborative filtering. 6.7 Recommender systems in e-commerce. 6.8 A note on personalization. 6.9 Further reading. 6.10 Exercises and topics for discussion. 7 Elements of strategic interaction. 7.1 Elements of Economics. 7.2 Elements of Game Theory. 7.3 Further reading. 7.4 Exercises and topics for discussion. 8 Negotiation I. 8.1 Negotiation protocols. 8.2 Desired properties of negotiation protocols. 8.3 Abstract architecture for negotiating agents. 8.4 Auctions. 8.5 Classification of auctions. 8.6 Basic auction formats. 8.7 Double auctions. 8.8 Multi-attribute auctions. 8.9 Combinatorial auctions. 8.10 Auction platforms. 8.11 Issues in practical auction design. 8.12 Further reading. 8.13 Exercises and topics for discussion. 9 Negotiation II. 9.1 Bargaining. 9.2 Negotiation in different domains. 9.3 Coalitions. 9.4 Applications of coalition formation. 9.5 Social choice problems. 9.6 Argumentation. 9.7 Further reading. 9.8 Exercises and topics for discussion. 10 Mechanism design. 10.1 The mechanism design problem. 10.2 Dominant strategy implementation. 10.3 The Gibbard-Satterthwaite Impossibility Theorem. 10.4 The Groves-Clarke mechanisms. 10.5 Mechanism design and computational issues. 10.6 Further reading. 10.7 Exercises and topics for discussion. 11 Mobile agents. 11.1 Introducing mobility. 11.2 Facilitating mobility. 11.3 Mobile agent systems. 11.4 Aglets. 11.5 Mobile agent security. 11.6 Issues on mobile agents. 11.7 Further reading. 11.8 Exercises and topics for discussion. 12 Trust, security and legal issues. 12.1 Perceived risks. 12.2 Trust. 12.3 Trust in e-commerce. 12.4 Electronic institutions. 12.5 Reputation systems. 12.6 Security. 12.7 Cryptography. 12.8 Privacy, anonymity and agents. 12.9 Agents and the law. 12.10 Agents as legal persons. 12.11 Closing remarks. 12.12 Further reading. 12.13 Exercises and topics for discussion. A Introduction to decision theory. A.2 Making decisions. A.3 Utilities. A.4 Further reading. Bibliography. Index.

Abstract: The recommendation system is one of the core technologies for implementing personalization services Recommendation systems in ubiquitous computing environment should have the capability of context-awareness In this research, we developed a music recommendation system, which we shall call C2_Music, which utilizes not only the user's demographics and behavioral patterns but also the user's context For a specific user in a specific context, the C2_Music recommends the music that the similar users listened most in the similar context In evaluating the performance of C2_Music using a real world data, it outperforms the comparative system that utilizes the user's demographics and behavioral patterns only

Abstract: A demanding task for many companies today is that of learning to regard customers as individuals, of proactively developing products and services according to the individual customer preferences, and of subsequently producing and distributing these offerings Over the last decade, mass customization has emerged as an effective approach for tackling precisely this task In this paper, I discuss the background of mass customization and the elements of this strategy I will then comment on the implementation of mass customization in practice I will end with a brief discussion of alternative strategies in this domain, namely personalization and matching services

Abstract: The potential of summary personalization is high, because a summary that would be useless to decide the relevance of a document if summarized in a generic manner, may be useful if the right sentences are selected that match the user interest. In this paper we defend the use of a personalized summarization facility to maximize the density of relevance of selections sent by a personalized information system to a given user. The personalization is applied to the digital newspaper domain and it used a user-model that stores long and short term interests using four reference systems: sections, categories, keywords and feedback terms. On the other side, it is crucial to measure how much information is lost during the summarization process, and how this information loss may affect the ability of the user to judge the relevance of a given document. The results obtained in two personalization systems show that personalized summaries perform better than generic and generic-personalized summaries in terms of identifying documents that satisfy user preferences. We also considered a user-centred direct evaluation that showed a high level of user satisfaction with the summaries.