08-10-2010, 03:30 PM
Open Web APIs in Teaching Web Mining
ABSTRACT
With the advent of the World Wide Web, many business applications that utilize data mining and text mining techniques to extract useful business information on the Web have evolved from Web searching to Web mining. It is important for students to acquire knowledge and hands-on experience in Web mining during their education in information systems curricula. This paper reports on an experience using open Web Application Programming Interfaces (APIs) that have been made available by major Internet companies (e.g., Google, Amazon, and eBay) in a class project to teach Web mining applications. The instructor’s observations of the students’ performance and a survey of the students’ opinions show that the class project achieved its objectives and students acquired valuable experience in leveraging the APIs to build interesting Web mining applications.
INTRODUCTION
THE Worldwide Web has become an indispensable part of many business organizations. In order to effectively utilize the power of the Web, information technology (IT) professionals need to have sufficient knowledge and experience in various Web technologies and applications. In recent years, courses in Internet- and Web-related topics have been offered in many universities to equip students with such knowledge. In addition to basic courses such as Internet networking and Internet application development, more advanced topics, such as Web mining, are becoming increasingly important. Web mining has been frequently used in real world applications such as business intelligence ,Website design , and customer opinion analysis. It is imperative that students acquire knowledge and hands-on experience in applying Web mining techniques. However, building a Web mining application from scratch is not an easy task that every student can complete in a semester. Recently, many large companies such as Google, Microsoft, Amazon, and eBay have opened access to their services and data through Application Programming Interfaces (APIs). In education, these APIs provide an ideal playground for students to gain some practical skills in Web application development and experiment with the Web mining techniques they learn in class. This paper reports on an experience designing a Web mining class project based on open Web APIs for students in a graduate Since the advent of the Internet, many studies have investigated the possibility of extracting knowledge and patterns from the Web, because it is publicly available and contains a rich set of resources. Many Web mining techniques are adopted from data mining, text mining, and information retrieval research . Most of these studies aimed to discover resources, patterns, and knowledge from the Web and Web-related data (such as Web server logs). Web mining research can be classified into three categories: Web content mining, Web structure mining, and Web usage mining . Web content mining refers to the discovery of useful information from Web contents, including text, images, audio, video, etc. Resource discovery from the Web, Web document categorization and clustering and information extraction from Web pages are important Web content mining topics. Web structure mining studies the model underlying the page link structures of the Web. Such models have been widely used to infer important information about Web pages. Hyperlinks among Web pages are usually indicators of high relevance or good quality. Web structure mining has been used for search engine result ranking, with Page Rank and HITS being the most widely used, and has also been applied to analyze online activities of different social groups. Web usage mining focuses on using data mining techniques to analyze search logs or other activity logs to find interesting patterns. A Web server log contains information about every visit to the pages hosted on the server, such as files requested, user’s IP address, and timestamp. By performing analysis on Web usage log data, Web mining systems can discover knowledge about a system’s usage characteristics and the users’ interests. Such knowledge can be used for personalized Web applications, marketing, Website evaluation, and decision support
For more information about this article,please follow the link:
http://googleurl?sa=t&source=web&cd=1&ve....1.88.3564%26rep%3Drep1%26type%3Dpdf&ei=t-muTJqLBIT6lwfz5ZDlDw&usg=AFQjCNHX2JwvHE7y66t-UqybjK9qQYeg7Q
