User profiling is an important part of the Semantic Web as it integrates the user into the concept of Web data with machine-readable semantics. In this paper, user profiling is presented as a way of providing the user with his/her interest-focused browsing history. We present a system that is incorporated into the Internet Explorer and maintains a dynamic user profile in a form of automatically constructed topic ontology. A subset of previously visited Web pages is associated with each topic in the ontology. By selecting a topic, the user can view the set of associated pages and choose to navigate to the page of his/her interest. Each topic can be seen as an interest of the user (hence the term interest-focused browsing history). The ontology is constructed by transforming the textual contents of the pages into sparse word-vectors and applying bisecting k-means clustering (i.e. a form of hierarchical clustering) on the set of sparse vectors. The most recently visited pages are used to identify the user’s current interest and map it to the ontology. The user can clearly see which topics, and their corresponding pages, are related (or are not related, for that matter) to his/her current interest. We see this as a useful way of organizing the user’s browsing history. To illustrate the functioning of the system, we demonstrate its behavior in one particular real-life scenario. 1

In this paper we proposed to automatically classify documents based on the meanings of words and the relationships between groups of meanings or concepts. Our proposed classification algorithm builds on the word structures provided by WordNet, which not only arranges words into groups of synonyms, called Synsets, but also arranges the Synsets into hierarchies representing the relationships between concepts. Most existing methods classify text documents based on the number of occurrences of words and some based on Synsets. Our approach goes one step further by using not only word occurrences and Synsets but also the relationships between Synsets. We also proposed a sense-based document representation based on the semantic hierarchies provided by WordNet. To classify a document, our approach extracts words occurred in the document and uses them to increase the weight of the Synsets corresponding to the words. Words with same meanings will increase the weight of their corresponding Synsets. As a result, we count the occurrences of senses. We also propagate the weight of a Synset upward to its related Synsets in the hierarchies and thus capture the relationships between concepts. In comparing to previous research, our approach increases the classification accuracy by 14%.

People frequently must sort through and identify relevant materials from a large set of documents, such as looking through the results of a web search. During this process of document triage there is reading and organizing activity. Moreover, these tasks can occur in different applications. A user’s interests can be identified from reading and organizing activity and used as a basis for providing cues to other potential documents of interest in the set. To most effectively identify related documents of interest, activity data must be collected from all applications used in document triage. In this paper we present a common framework (the Interest Profile Manager) for collecting and analyzing user interest. We also present models for identifying user interest based only on reading activity, only on organizing activity, and models incorporating both reading and organizing activity. A study comparing document values calculated using the different models shows that incorporating interest information from both reading and organizing activity more accurately estimates users’ valuation of documents than using either type of activity alone.

Automatic classification of web pages is an effective way to deal with the difficulty of retrieving information from the Internet. Although there are many automatic classification algorithms and systems that have been proposed, most of them ignore the conflict between the fixed number of categories and the growing number of web pages going into the system. They also require searching through all existing categories to make any classification. We propose a dynamic and hierarchical classification system that is capable of adding new categories as required, organizing the web pages into a tree structure, and classifying web pages by searching through only one path of the tree structure. Our test results show that our proposed single-path search technique reduces the search complexity and increases the accuracy by 6 % comparing to related algorithms. Our dynamic-category expansion technique also achieves satisfying results on adding new categories into our system as required. 1.

This paper proposes a document logistics approach for cooperative research based on the Web and Knowledge Grid. The approach realizes effective research document collection, organization and provision as well as knowledge sharing by incorporating the following functions: construction of semantic profiles representing interests, continuous discovery and collection of potentially relevant documents, synthesis of evaluation feedbacks, and support of flexible management operations and document recommendation services. The prototype has been implemented and is available for use online. Experiments show that the proposed approach is feasible and effective. © 2003 Elsevier B.V. All rights reserved.

Finding meaningful phrases in a document has been studied in various information retrieval systems in order to improve the performance. Many previous statistical phrase-finding methods had a different aim such as document classification. Some are hybridized with statistical and syntactic grammatical methods; others use correlation heuristics between words. We propose a new phrase-finding algorithm that adds correlated words one by one to the phrases found in the previous stage, maintaining high correlation within a phrase. Our results indicate that our algorithm finds more meaningful phrases than an existing algorithm. Furthermore, the previous algorithm could be improved by applying different correlation functions. 1.

Recommender systems, collaborative filtering, analysis of usage, statistical language model, resource indexing Due to the huge amount of available information via Internet, the identification of reliable and interesting items becomes more and more difficult and time consuming. This paper is a position paper describing our intended work in the framework of multimedia information retrieval by browsing techniques within web navigation. It relies on a usage-based indexing of resources: we ignore the nature, the content and the structure of resources. We describe a new approach taking advantage of the similarity between statistical modeling of language and document retrieval systems. A syntax of usage is computed that designs a Statistical Grammar of Usage (SGU). A SGU enables resources classification to perform a personalized navigation assistant tool. It relies both on collaborative filtering to compute virtual communities of users and a new distance dependent trigger model. The resulting SGU is a community dependent SGU. 1

Personalization is a key factor for differentiating services and retaining customers in World Wide Web sites. On the other hand, designing and implementing an efficient personalization strategy is still a challenge, because of the complexity of the techniques used and the variety of sites and customers, which are always evolving. This paper presents a functional model of personalization strategies that allows not only a simple and concise specification of those strategies, but also their simulation and validation. We demonstrate our model through e-Personal, a framework for estimating the effectiveness of personalization strategies. The framework guides the user through the process of specifying a strategy and estimates its impact based on previous interactions of customers with the site. It is based on our functional model and we illustrate its utilization for designing personalization strategies for a web portal. Our experiments are based on actual logs and show that the proposed framework enhances significantly the personalization process, indicating the goodness of the strategy design, the reliability of input data, and the impact of implementation decisions on the effectiveness of personalized sites.

This paper proposes a system for personalization of web portals. A specific implementation is discussed in reference to a web portal containing a news feed service. Techniques are proposed for effective categorization, management, and personalization of news feeds obtained from a live news wire service. The process consists of two steps: first manual input is required to build the domain knowledge which could be site-specific; then the automated component uses this domain knowledge in order to perform the personalization, categorization and presentation. Effective schemes for advertising are proposed, where the targeting is done using both the information about the user and the content of the web page on which the advertising icon appears. Automated techniques for identifying sudden variations in news patterns are described; these may be used for supporting news-alerts. A description of a version of this software for our customer web site is provided.

In this paper we propose an XML-based adaptive multiagent system for handling e-commerce activities. More specifically, our system aims at supporting a customer, visiting an e-commerce site, in the search of products and/or services present therein and appearing to be appealing according to her/his past interests and behaviour. The system is adaptive w.r.t. the profile of both the customer and the device she/he is exploiting for visiting the site. Finally, the system is XML-based since XML is exploited for both storing the agent ontologies and handling the agent communication.