There has been an increased demand for characterizing user access patterns using web mining techniques since the informative knowledge extracted from web server log files can not only offer benefits for web site structure improvement but also for better understanding of user navigational behavior. In this paper, we present a web usage mining method, which utilize web user usage and page linkage information to capture user access pattern based on Probabilistic Latent Semantic Analysis (PLSA) model. A specific probabilistic model analysis algorithm, EM algorithm, is applied to the integrated usage data to infer the latent semantic factors as well as generate user session clusters for revealing user access patterns. Experiments have been conducted on real world data set to validate the effectiveness of the proposed approach. The results have shown that the presented method is capable of characterizing the latent semantic factors and generating user profile in terms of weighted page vectors, which may reflect the common access interest exhibited by users among same session cluster.

We propose a PageRate method to give Web pages on a Web site ratings based on the Web link structure and user usage data, which are both recorded in the Web log files. The method is an improvement over PageRank [1, 6]. PageRate can be used to objectively evaluate the importance of pages. A PageClustering algorithm is proposed to cluster Web pages with similar incoming links and ratings. The results are used to integrate with search results returned by search engines.

It is generally recognized that information systems are becoming more complex and, therefore, intelligent user interfaces are needed to improve user interaction with these systems. Furthermore, the exponential growth of the Internet makes it difficult for the users to cope with the huge amount of available on-line information. The challenge

One important class of Data Mining applications is the so-called "Web Mining" that analyzes and extracts important and non-trivial knowledge from Web related data. Typical applications of Web Mining are represented by the personalization or recommender systems. These systems are aimed to extract knowledge from the analysis of historical information of a web server in order to improve the web site expressiveness in terms of readability and content availability. Typically, these systems are made up of two components. One, that is usually executed off-line with respect to the Web server normal operations, analyzes the server access logs in order to find a suitable categorization of users, the other, that is usually executed on-line with respect to the Web server normal operations, classifies the active requests according to the previous off-line analysis. In this paper we propose SUGGEST 2.0 a recommender system that, differently from those proposed so far, does not make use of any off-line component. Moreover, in the last part of the paper, we analyze the quality of the suggestions generated and the performance of our solution. To this purpose we also introduce a novel quality metric that tries to estimate the effectiveness of a recommender system as the capacity to anticipate user requests that could be issued farther in the future.

The locality of web pages within a web site is initially determined by the designer’s expectation. Web usage mining can discover the patterns in the navigational behaviour of web visitors, in turn, improve web site functionality and service designing by considering users ’ actual opinion. Conventional web page clustering technique is often utilized to reveal the functional similarity of web pages. However, high-dimensional computation problem will be incurred due to taking user transaction as dimension. In this paper, we propose a new web page grouping approach based on Probabilistic Latent Semantic Analysis (PLSA) model. An iterative algorithm based on maximum likelihood principle is employed to overcome the aforementioned computational shortcoming. The web pages are classified into various groups according to user access patterns. Meanwhile, the semantic latent factors or tasks are characterized by extracting the content of “dominant ” pages related to the factors. We demonstrate the effectiveness of our approach by conducting experiments on real world data sets. 1.

This article addresses the problem to predict user behaviours on a Web site which is very known to be an important way for improving the effectiveness of Web sites. Our objective is to evaluate our collaborative ltering approach of recommendation computation called the Broadway approach, according to the prediction feature. The main assumption of your approach is to take the sequence of user actions of a group into account for recommendation computation. For the prediction evaluation, we use the log les containing two months of usage from the site http://www.hyperreald.,org/music/machines/. We develop a prediction system based on our approach for that site and implement two others Web mining algorithms (statistics, Markov) in order to compare our work with them. This paper reports the main results issued from our different experiments.

The objective of the I-KnowUMine project (IKUM) 1 is to develop an integrated platform (referred to in the paper as the “IKUM system”) that uses state of the art technology and research results from different application domains in order to provide the basis for the development of online services in a wide range of application areas, presenting personalized content, services and applications to users in a structure more suited to their needs. The benefits provided by the IKUM system result mainly from the combination and integration of technology advances in spaces such as Web Mining, Content Management, Personalization and Portals. As a result of this novel combination of these technologies, users of the IKUM system will benefit from the optimal logical structure of information/content provided by the system, allowing them to efficiently execute their processes and to reach their information targets. 1

Web servers log how a user interacts with a website. This can provide the website author with valuable information about the `audience' of the site. However with dynamically generated pages, such an analysis has become more difficult. In this paper we present some ideas about how machine learning techniques can be used to analyse these data. We apply these techniques to real world data and present preliminary results.

heir strengths and limitations. The discussion will be illustrated throughout with reference to concrete system examples. 2 Detailed Outline 2.0 Introduction and Motivation Goals Define terms and clarify the scope of the tutorial Stimulate the interest of the participants This description was written in October 2000 for submission to the IJCAI 01Tutorial Chair. Because of rapid developments in the field, the final structure of the tutorial may differ in some details from the structure described here. Questions Addressed What are "user-adaptive systems"? Why are such systems both theoretically and practically important? What can be expected in the rest of this tutorial? 2.1 Functions of User-Adaptive Systems Goals Make participants aware of all important types of useradaptive systems Introduce example systems that can be referred back to later in the tutorial Functions Discussed

In this paper we present an approach to the discovery of trends in the usage of large Web-based information systems. This approach is based on the empirical analysis of the users interaction with the system and the construction of user groups with common interests (user communities). The empirical analysis is achieved with the use of cluster mining, a technique that process data collected from the users' interaction with the Web site. Our main concern is the construction of meaningful communities, which can be used for improving the structure of the site as well as for making suggestions to the users at a personal level. Our case study on a site providing information for researchers in Chemistry shows that the proposed method provides effective mining of large usage databases.