CSEN 1085 Web Analytics

Course Information


  • In this course we explore the concepts and tools necessary for a data scientist to analyze the web with its structural, visual and verbal content. In 2018, 4 billion people use the internet, with more than 3 billion social media users. Much of this data on the web today is structured as large scale graphs. For example, ocial networks are graphs of users connected via a “follow” or “friend” relation. In commercial sites, users have similar tastes if they are connected to the same product nodes. The course is structured into two parts: the first part discusses graph analysis for the purpose of identifying communities, influencers, maximizing the diffusion of viral content and identifying credible versus fake content. The second part of the course applies advanced machine learning tools to webmedia with applications to 1) learning from encrypted data 2) language generation 3) image similarity search.