Course Description

The Web as a vast, variegated and growing resource interconnects our world in many interesting ways. One area of study that has emerged somewhat recently is that of "web mining".  Research and development in web mining span a spectrum of goals from methods for high quality retrieval, to monitoring information sites and streams, to distilling and summarizing web
information to identifying social networks and discovering new opportunities and ideas. This course will study the web mining landscape through papers, assignments and a term project. Exposure to perl is preferred though we will have sufficient opportunity to go over some of the key perl libraries as for example to build web crawlers. Likewise exposure to database technology is also preferred.

The course has the following specific goals:

• Through weekly paper readings learn the state-of-the-art in web-based information technology
• Study specific applications such as product sentiment monitoring; news filters; social networks; monitoring changes in
  web sites
• Become familiar with the essentials of programming Perl scripts, CGI applications, and connecting them to SQL databases
• Through select cases and discussions, identify the business applications frontier and discover opportunities for new so
  lutions.
• Learn about current research in web mining and interesting challenges that lay ahead by reading conference and journal papers.
• Through a term project be able to work hands-on with a web mining project from design to implementation.
• Appreciate the benefits and opportunities while also realizing the limitations of current information technology.