Effectiveness of Web Usage Mining Techniques in Business Application

Web usage mining techniques and applications across industries is still exploratory and, despite an increase in academic research, there are challenge of analyze web which quantitatively capture web users' common interests and characterize their underlying tasks. This chapter addresses the problem of how to support web usage mining techniques and applications across industries by combining language of web pages and algorithms that used in web data mining. Existing research in web usage mining techniques tend to focus on finding out how each techniques can apply in different industries fields. However, there is little evidence that researchers have approached the issue of web usage mining across industries. Consequently, the aim of this chapter is to provide an overview of how the web usage mining techniques and applications across industries can be supported.

Methodologies and Techniques of Web Usage Mining

Web usage mining attempts to discover useful knowledge from the secondary data obtained from the interactions of the users with the Web. It is the type of Web mining activity that involves the automatic discovery of out what users are looking for on the Internet. In this chapter methodology of web usage mining explained in detail which are data collection, data preprocessing, knowledge discovery and pattern analysis. The different Web Usage Mining techniques are described, which are used for knowledge and pattern discovery. These are statistical analysis, sequential patterns, classification, association rule mining, clustering, dependency modeling. Pattern analysis is needed to filter out uninterested rules or patterns from the set found in the pattern discovery phase.

Enhancing Web Data Mining

An enormous production of databases in almost every area of human endeavor particularly through web has created a great demand for new, powerful tools for turning data into useful, task-oriented knowledge. The aim of this study is to study the predictive ability of Factor Analysis a web mining technique to prevent voting, averaging, stack generalization, meta- learning and thus saving much of our time in choosing the right technique for right kind of underlying dataset. This chapter compares the three factor based techniques viz. principal component regression (PCR), Generalized Least Square (GLS) Regression, and Maximum Likelihood Regression (MLR) method and explores their predictive ability on theoretical as well as on experimental basis. All the three factor based techniques have been compared using the necessary conditions for forecasting like R-Square, Adjusted R-Square, F-Test, JB (Jarque-Bera) test of normality. This study can be further explored and enhanced using sufficient conditions for forecasting like Theil's Inequality coefficient (TIC), and Janur Quotient (JQ).

Mastering Web Mining and Information Retrieval in the Digital Age

This chapter aims to master web mining and Information Retrieval (IR) in the digital age, thus describing the overviews of web mining and web usage mining; the significance of web mining in the digital age; the overview of IR; the concept of Collaborative Information Retrieval (CIR); the evaluation of IR systems; and the significance of IR in the digital age. Web mining can contribute to the increase in profits by selling more products and by minimizing costs. Web mining is the application of data mining techniques to discover the interesting patterns from web data in order to better serve the needs of web-based multifaceted applications. Mining web data can improve the personalization, create the selling opportunities, and lead to more profitable relationships with customers in global business. Web mining techniques can be applied with the effective analysis of the clearly understood business needs and requirements. Web mining builds the detailed customer profiles based on the transactional data. Web mining is used to create the personalized search engines which can recognize the individuals' search queries by analyzing and profiling the web user's search behavior. IR is the process of obtaining relevant information from a collection of informational resources. IR has considerably changed with the expansion of the Internet and the advent of modern and inexpensive graphical user interfaces and mass storage devices. The effective IR system, including an active indexing system, not only decreases the chances that information will be misfiled but also expedites the retrieval of information. Regarding IR utilization, the resulting time-saving benefit increases office efficiency and productivity while decreasing stress and anxiety. Most IR systems provide the advanced searching capabilities that allow users to create the sophisticated queries. The chapter argues that applying web mining and IR has the potential to enhance organizational performance and reach strategic goals in the digital age.

Web Harvesting

Web mining is done on huge amounts of data extracted from WWW. Many researchers have developed several state-of-the-art approaches for web data extraction. So far in the literature, the focus is mainly on the techniques used for data region extraction. Applications which are fed with the extracted data, require fetching data spread across multiple web pages which should be crawled automatically. For this to happen, we need to extract not only data regions, but also the navigation links. Data extraction techniques are designed for specific HTML tags; which questions their universal applicability for carrying out information extraction from differently formatted web pages. This chapter focuses on various web data extraction techniques available for different kinds of data rich pages, classification of web data extraction techniques and comparison of those techniques across many useful dimensions.

Web Mining and Analytics for Improving E-Government Services in India

The ever increasing technology usage and the globalization have given rise to the need of quick, accurate and smarter handling of information by organizations, states, nations and the entire globe. For every nation to be under any form of government, it became mandatory to have shorter turnaround time for their interactions with citizens. This pressure gave rise to the concept of e-Governance. It has been implemented by various nations and even UN reported an increase in E-Governance activities around the world. However, the major problems that need to be addressed by developing nations are digital divide and lack of e-Infrastructure. India started its e-Governance plan through a proposal in 2006 with establishment of National e-Governance Plan popularly known as NeGP headed by Ministry of Communications and Information Technology, Government of India. As per the Electronic Transaction and Aggregation Layer, millions of transactions are taking place on regular basis. Within 2015 itself, over 2 billion transactions have been carried out by the Indian citizens in various categories and sectors like agriculture, health, and the likes. For central government projects alone, around 980 million electronic transactions have taken place, while for state government projects, the combined total of all the states is close to 1.2 billion. With the kind of data getting generated through e-Governance initiative in India, it will open up lot of opportunities for data analysts & mining experts to explore this data and generate insights out of them. The aim of this chapter is to introduce various areas and sectors in India where analytics can be applied for e-Governance related entities like citizens, corporate and government departments. It will be useful for researchers, academicians and students to understand various areas in E-Governance where web mining and data analysis can be applied. The theoretical background has been supported by practical case study for better understanding of the concepts of web analysis and mining in the area of E-Governance.

Search Query Recommendations in Web Information Retrieval Using Query Logs

Web is the largest and voluminous data source in the world. The inconceivable boom of information available in the web simultaneously throws the challenge of retrieving the precise and appropriate information at the time of need. The unpredictable amount of web information available becomes a menace of experiencing ambiguity in the web search. In this scenario, Search engine retrieves significant information from the web, based on the query term given by the user. The search queries given by the user are always short and ambiguous and the queries may not produce the appropriate results. The retrieved result may not be relevant all the time. At times irrelevant and redundant results are also retrieved because of the short and ambiguous query keywords. Query Recommendation is a technique to provide the alternate queries as a substitute of the input query to the user to frame the queries in future. A methodology was framed to identify the similar queries and they are clustered; this cluster contains the similar queries which are used to provide the recommendations.

Application of Conventional Data Mining Techniques and Web Mining to Aid Disaster Management

Data mining techniques have potential to unveil the complexity of an event and yields knowledge that can create a difference. They can be employed to investigate natural phenomena; since these events are complex in nature and are difficult to characterize as there are elements of uncertainty involved in their functionality. Therefore, techniques that are compatible with uncertain elements can be employed to study them. This chapter explains the concepts of data mining and discusses at length about the landslide event. Further, the utility of data mining techniques in disaster management using a previous work was explained and provides a brief note on the efficiency of web mining in creating awareness about natural hazard by providing refined information. Finally, a conceptual framework for landslide hazard assessment using data mining techniques such as Artificial Neural Network (ANN), Fuzzy Geometric Mean Model (FGMM), etc. were chosen for description. It was quite clear from the study that data mining techniques are useful in assessing and modelling different aspects of landslide event.

Applications of Web Usage Mining across Industries

Web Usage Mining (WUM) is the process of discovery and analysis of useful information from the World Wide Web (WWW) by applying data mining techniques. The main research area in Web mining is focused on learning about Web users and their interactions with Web sites by analysing the log entries from the user log file. The motive of mining is to find users' access models automatically and quickly from the vast Web log data, such as similar queries imposed by the various users, frequent queries applied by the user, frequent web sites visited by the users, clustering of users with similar intent etc. This chapter deals with Web mining, Categories of Web mining, Web usage mining and its process, Applications of Web usage mining across the industries and its related works. This Chapter offers a general knowledge about Web usage mining and its applications for the benefits of researchers those performing research activities in WUM.

Analysis of User's Browsing Behavior and Their Categorization Using Markov Chain Model

Web server log file contains information about every access to the web pages hosted on a server like when they were requested, the Internet Protocol (IP) address of the request, the error code, the number of bytes sent to the user, and the type of browser used. Web servers can also capture referrer logs, which show the page from which a visitor makes the next request. As the visit to web site is increasing exponentially the web logs are becoming huge data repository which can be mined to extract useful information for decision making. In this chapter, we proposed a Markov chain based method to categorize the users into faithful, Partially Impatient and Completely Impatient user. And further, their browsing behavior is analyzed. We also derived some theorems to study the browsing behavior of each user type and then some numerical illustrations are added to show how their behavior differs as per categorization. At the end we extended this work by approximating the theorems.