[ Formal Data | Syllabus | Readings | Course Materials | Course Tools ]
Information systems suffer from an inability to satisfy the heterogeneous needs of many users. For example, Web courses present the same static learning material to students with widely differing knowledge of the subject. Most online stores still offer the same selection of "featured items" to customers with different needs and preferences. Virtual museums on the web offer the same "guided tour'' to visitors with very different goals and interests. Health information sites present the same information to readers with different health problems. A remedy for the negative effects of the traditional "one-size-fits-all'' approach is to develop systems with an ability to adapt their behavior to the goals, tasks, interests, and other features of individual users and groups of users. While Adaptive Information systems is a relatively young area, it evolves very fast. More and more commercial Adaptive Information systems become available each year. Starting with a handful or research teams worldwide and a few industrial pioneers such as Amazon.com, adaptation and personalization is now in focus of hundreds of researchers and practitioners.
The goal of the course is to get immersed into the world of the Adaptive Information Systems (AIS). The students in this class will learn about many aspects of AIS, get familiar with key Adaptive Web technologies, and study many examples of modern AIS. They will work in group to develop their own AIS and will have a chance to apply modern adaptation and personalization technologies in the context of larger projects. Those who will successfully complete the seminar will join a small cohort of experts on adaptivity and personalization.
The Web personalization industry is on the rise. In the comingyears universities, research labs, and companies will need hundreds of experts who understand adaptive systems and personalization to lead various exciting projects. Leading internet companies such as Google, Yahoo, IBM, Microsoft, Ebay, AOL and others are now already engaged in research and development of various adaptive Web systems and seek to hire knowlegeable workers.This is your chance to be among the leaders of the new and exciting field.
Here is the list of topics we may cover during the course
I. Modeling Technologies
II. Adaptation Technologies
The course will include several small assignments and a large group project. While the group project will be programming-oriented, it is not expected that each students who is taking this course has strong programming skills. Development of AIS requires a range of different skills such as domain analysis, algoritm design, modeling, etc. Each project team will required a range of expertise beyond programming. Students with knowledge of mathematics, statistics, education, psychology, artificial intelligence, etc. are encouraged to take the course to attend regardless of their programming skills.
Course assessment includes attendance, weekly coursework and projects. Each assignment and project bears certain number of points. The instructor also reserves the right to administer unannounced quizzes for up to 5 points each if he feels that the students are not pursuing a resonable amount of assigned reading. Your final grade depends on the percentage of points you have earned. Score < 50% corresponds to F, 50-62.5 is D range, 65.5-75 is C range, 75-87.5 is B range, and 87.5-100 is A range.
After a brief introduction into the field provided by the instructor we will switch to a regular work mode. Every week we focus on one or two topics. Each topic will be presented in the lecture followed by relevant student presentations and a discussion. The instructor, the assistant instructors, and doctoral students taking the course will alternate in giving a lecture and leading discussions for each of these topics. To complement the "reading part", the students will perform a range of weekly activities. The practical part of the course include two research paper reading projects, one presentation project and one large final project, which should be peformed in groups or, as an exception, individually.
Read all assigned chapters (one or two per week). It is your choice whether to read it before or after the lecture, but it should be done no more than 4 days after the class to allow space for discussion. Since reading is not very interactive and hard to measure activity, several additional activities are focused on your readings.
Follow research seminars relevant to the topic at Pitt and Carnegie Mellon. Attend two over the course duration. Post a summary to the course discussion group.
Choose one the core course topic (topic selection should be done by the third lectture). Select a paper on that topic, read, summarize, and present it in class. Topics will be assigned by request on FIFO basis. This project will include several activities for each paper:
Research a specific topic and present it in class (about 30-40 min. presentation). PhD students are expected to pick up one of the core course topics relevant to their reseacrh and and deliver it as one of the shorter core presentation. MS students are encouraged to work in pairs or larger groups and research one of commercial adaptive systems or groups of these systems (Amazon.com, Last.fm, Netflix, etc). In either case you should:
The goal of the final project is to convert the theory you learned in the course into practice. Work in groups or individually to develop a small, but complete adaptive system, which you will present at the end of the course. It is expected that you will start your work on the final project very early, not complete it in a haste over the last week. To motivate your regular work on the project, the work will include two additional activities, which will be graded separately (as a component of 50pts project grade)
Copyright © 2012 Peter Brusilovsky