The growth of World Wide Web is incredible as it can be seen in present days. Users find it very difficult to extract useful and relevant information from the huge amount of information. The problems can be solved by Web Usage Mining which involves preprocessing, pattern discovery and pattern analysis. Preprocessing is an important process which converts raw web log data into transactions. Application of mining techniques to group user‟s behavior for personalization is effectively done on transactions constructed from sessions. Sessionization is the identification of sessions and is defined as a set of pages visited by the same user within the duration of one particular visit to a web-site. In this research paper, a new technique for identifying sessions is being proposed for extraction of user patterns. The experimental results show that the proposed Session Identification technique is an effective one to construct sessions accurately.

The continuous growth in the size of the World Wide Web has resulted in intricate Web sites, demanding enhanced user skills and more sophisticated tools to help the Web user to find the desired information. In order to make Web more user friendly, it is necessary to provide personalized services and recommendations to the Web user. For discovering interesting and frequent navigation patterns from Web server logs many Web usage mining techniques have been applied. The recommendation accuracy of usage based techniques can be improved by integrating Web site content and site structure in the personalization process. Herein, we propose semantically enriched Web Usage Mining method for Personalization (SWUMP), an extension to solely usage based technique. This approach is a combination of the fields of Web Usage Mining and Semantic Web. In the proposed method, we envisage enriching the undirected graph derived from usage data with rich semantic information extracted from the Web pages and the Web site structure. The experimental results show that the SWUMP generates accurate recommendations and is able to achieve 10-20% better accuracy than the solely usage based model. The SWUMP addresses the new item problem inherent to solely usage based techniques. Keywords—Prediction, Recommendation, Semantic Web Usage Mining, Web Usage Mining.

It is estimated that over seven billion static pages exist in the Web today, and backend databases can potentially produce at least three times as many dynamic pages. However, the best search engines index only approximately 20% of the static pages. So the real question is: While the Web is certainly the most amazing and comprehensive information source ever created, are you really getting all the information you need for your specific purpose? The answer to this question is mostly “yes” for the individual user, who uses the Web as an information source for casual purposes. However, for an individual who uses the Web as an essential and comprehensive source of information—for business or research—the answer is quite the opposite. Even a sophisticated Web user requires a significant amount of time and effort to find all of the information needed for a given task. In this paper the concept of Web Business Intelligence (WBI) is introduced, an emerging class of software that leverages the unprecedented content on the Web to extract actionable knowledge in an organizational setting. The contributions include an architecture for WBI, a survey of technologies relevant to the various components of the architecture, and illustration of the value of WBI by means of a detailed example from the e-finance domain. This article concludes with a discussion on the future of WBI.

The discipline of Web Usage Mining has grown rapidly in the past few years, despite the crash of the e-commerce boom of the late 1990s. Web Usage Mining is the application of data mining techniques to Web clickstream data in order to extract usage patterns. Yet, with all of the resources put into the problem, claims of success have been limited and are often tied to specific Web site properties that are not found in general. One reason for the limited success has been a component of Web Usage Mining that is often overlooked---the need to understand the content and structure of a Web site. The processing and quantification of a Web sites content and structure for all but completely static and single frame Web sites is arguably one of the most difficult tasks to automate in the Web Usage Mining process. This article shows that, not only is the Web Usage Mining process enhanced by content and structure, it cannot be completed without it. The results of experiments run on data from a large e-commerce site are presented to show that proper preprocessing cannot be completed without the use of Web site content and structure, and that the effectiveness of pattern analysis is greatly enhanced.

Web Usage Mining is the application of data mining techniques to large Web data repositories in order to extract usage patterns. As with many data mining application domains, the identification of patterns that are considered interesting is a problem that must be solved in addition to simply generating them. Aneces sary step in identifying interesting results is quantifying what is considered uninteresting in order to form a basis for comparison. Several research efforts have relied on manually generated sets of uninteresting rules. However, manual generation of a comprehensive set of evidence about beliefs for a particular domain is impractical in many cases. Generally, domain knowledge can be used to automatically create evidence for or against a set of beliefs. This paper develops a quantitative model based on support logic for determining the interestingness of discovered patterns. For Web Usage Mining, there are three types of domain information available; usage, content, and structure. This paper also describes algorithms for using these three types of information to automatically identify interesting knowledge. These algorithms have been incorporated into the Web Site Information Filter (WebSIFT) system and examples of interesting frequent itemsets automatically discovered from real Web data are presented.

The World Wide Web (WWW) continues to grow at an astounding rate in both the sheer volume of traffic and the size and complexity of Web sites. The complexity of tasks such as Web site design, Web server design, and of simply navigating through a Web site have increased along with this growth. An important input to these design tasks is the analysis of how a Web site is being used. Usage analysis includes straightforward statistics, such as page access frequency, as well as more sophisticated forms of analysis, such as finding the common traversal paths through a Web site. Web Usage Mining is the application of data mining techniques to usage logs of large Web data repositories in order to produce results that can be used in the design tasks mentioned above. However, there are several preprocessing tasks that must be performed prior to applying data mining algorithms to the data collected from server logs. This paper presents several data preparation techniques in order to identify unique users and user sessions. Also, a method to divide user sessions into semantically meaningful transactions is defined and successfully tested against two other methods. Transactions identified by the proposed methods are used to discover association rules from real world data using the WEBMINER system [15].

Much of the data we deal with every day is organized hierarchically: file systems, library classification schemes and yellow page categories are salient examples. Business data too, benefits from a hierarchical organization, and indeed the hierarchical ...

Given a data set and a data mining task such as classiication, there are two main reasons for performing feature space reduction. The rst is to improve the accuracy of the algorithm. In a domain such as text mining, the common technique of parameterizing each document as a vector of words results in thousands of dimensions. The performance of many learning algorithms decreases as the dimensionality of the input space increases. Support Vector Machines (SVMs) Vap95], which are based on Vapnik's statistical learning theory, can be used as a clas-siication technique and have been shown by Joachims Joa98] to be reasonably immune to the high dimensionality of text feature spaces. The second reason for performing feature space reduction is to decrease the overall size of the data set in order to conserve storage space and minimize the amount of time required to handle the data and run the mining algorithms. Even with SVMs, very large data sets may warrant feature space reduction because of this second class of problems. This paper describes the results of an experiment to train SVMs to classify print, television, and radio news sources. Tests were performed to compare full text versus feature space reduction using a natural language processing technique and reduction using information gain. The results show that while the size of the data set can be reduced by an order of magnitude with natural language processing, this results in a signiicant loss in both recall and precision. However, both the precision and recall achieved with the SVMs trained with the full text and information gain representations were higher than what was achieved with the K-nearest-neighbors algorithm. Also, three term weighting methods, TFIDF, TF, and binary are compared for use with the SVMs. Representations with TFIDF and TF weights produced similar results, while the binary weighting method resulted in a signiicant loss in recall.

TopCat (Topic Categories) is a technique for identifying topics that recur in articles in a text corpus. Natural language processing techniques are used to identify key entities in individual articles, allowing us to represent an article as a set of items. This allows us to view the problem in a database/data mining context: Identifying related groups of items. This paper presents a novel method for identifying related items based on “traditional” data mining techniques. Frequent itemsets are generated from the groups of items, followed by clusters formed with a hypergraph partitioning scheme. We present an evaluation against a manually-categorized “ground truth” news corpus showing this technique is effective in identifying topics in collections of news articles.

We describe an approach to usage based Web personalization taking into account both the offline tasks related to the mining of usage data, and the online process of automatic Web page customization based on the mined knowledge. Specifically, we propose an effective technique for capturing common user profiles based on association rule discovery and usage based clustering. We also propose techniques for combining this knowledge with the current status of an ongoing Web activity to perform real time personalization. Finally, we provide an experimental evaluation of the proposed techniques using real Web usage data.

This chapter discusses a multimedia synchronization toolkit, called Nsync, to address the complicated issues inherent in designing flexible, interactive multimedia presentations. The toolkit consists of two primary components, a declarative synchronization definition language, and a run-time presentation management system. The synchronization definition language supports the specification of synchronous interaction, asynchronous interaction, fine-grained relationships, and combinations of each through the use of conjunctive and disjunctive operators. Precomputed playout schedules are too inflexible to deal with asynchronous interaction, and a more adaptive presentation management system is required. Nsync's run-time system uses a novel predictive logic to predict the future behavior of a presentation. As the viewer makes decisions, the presentation is updated and new predictions are made to maintain consistency with the viewer's wishes and the integrity of the presentation's message. The Nsync toolkit has been completely implemented in the Tcl/Tk scripting language. The total implementation effort was about 3,500 lines of Tel code extending over a 6 months period. Although, Nsync can model any granularity of skew relationship, it cannot currently enforce them. To address this issue, some parts of the system would need to be reimplemented in a lower-level programming language, such as C or C++.

Web-based organizations often generate and collect large volumes of data in their daily operations. Analyzing such data involves the discovery of meaningful relationships from a large collection of primarily unstructured data, often stored in Web server access logs. While traditional domains for data mining, such as point of sale databases, have naturally defined transactions, there is no convenient method of clustering web references into transactions. This paper identifies a model of user browsing behavior that separates web page references into those made for navigation purposes and those for information content purposes. A transaction identification method based on the browsing model is defined and successfully tested against other methods, such as the maximal forward reference algorithm proposed in (Chen et al., 1996). Transactions identified by the proposed methods are used to discover association rules from real world data using the WEBMINER system.

Application of data mining techniques to the World Wide Web, referred to as Web mining, has been the focus of several recent research projects and papers. However, there is no established vocabulary, leading to confusion when comparing research efforts. The term Web mining has been used in two distinct ways. The first, called Web content mining in this paper, is the process of information discovery from sources across the World Wide Web. The second, called Web usage mining, is the process of mining for user browsing and access patterns. We define Web mining and present an overview of the various research issues, techniques, and development efforts. We briefly describe WEBMINER, a system for Web usage mining, and conclude the paper by listing research issues.

With the rapid technological advances in computer hardware and presentation devices thatare occurring, the development of multimedia presentations is quickly expanding from the realmof professional studios to small offices and homes. Along with the hardware advances, mucheffort has been put into creating the necessary tools to convert raw data streams into polishedpresentations, including the specification of temporal relations between media objects (synchronization). Many models have been ...