Social Media Analysis 10-802 in Spring 2011
- 2/1. First draft of your project proposals are due - please link to them from here
- 1/19. My office hours will be Thursday afternoons, 1-2pm, starting on 1/28. This week I will have office hours on Friday, 1/21 from 4-5pm.
- 1/17. To get a wiki account (which you'll need for the first assignment), just send an email message to Katie Rivard (email@example.com) asking for one. Please let her know your andrew id - we'll use that as your username.
- 1/5. This syllabus is now a reasonably close approximation to what the course is about.
- 12/28. This syllabus is under construction.
Instructor and Venue
- Instructor: William Cohen, Machine Learning Dept and LTI
- Course secretary: Sharon Cavlovich, firstname.lastname@example.org, 412-268-5196
- When/where: Tues & Thursday 10:30-11:50, GHC 4303
- Course Number: MLD 10-802, cross-listed as LTI 11-772
- Prerequisites: a machine learning course (e.g., 10-701 or 10-601) or consent of the instructor.
- TA: Bhavana Dalvi
- Syllabus: Syllabus for Analysis of Social Media 10-802 in Spring 2011
- Office hours: 1-2pm Thursday.
Clarification/announcement: This will be a regular 12-credit course (despite the some listings of it as a 6-credit course).
The most actively growing part of the web is "social media" - e.g.. wikis, blogs, bboards, and collaboratively-developed community sites like Flikr and YouTube. This course will review selected papers from the recent research literature that address the problem of analyzing and understanding social media. Topics that will be covered include:
- Text analysis techniques for sentiment analysis, analysis of figurative language, authorship attribution, and inference of demographic information about authors (e.g., age or sex).
- Community analysis techniques for detecting communities, predicting authority, assessing influence (e.g. in viral marketing), or detecting spam.
- Visualization techniques for understanding the interactions within and between communities.
- Learning techniques for modeling and predicting trends in social media, or predicting other properties of media (e.g., user-provided content tags.)
Students should have a machine learning course (e.g., 10-601 or similar) or consent of the instructor. Readings will be based on research papers. Grades will be based on class participation, paper presentations, and a project. More specifically, students will be expected to:
- Prepare summaries of the papers discussed in class. Summaries will be posted on this wiki.
- Present and summarize one or more "optional" papers from the syllabus (or some other mutually agreeable paper) to the class.
- Do a course project in a group of 2-3 people. The end result of the project will be a written report, with format and length appropriate for a conference publication.
Syllabus and Readings
- Syllabus for Analysis of Social Media 10-802 in Spring 2010
- Syllabus from the Fall 2007 version of the course
The first half of the course, roughly, will be presentations of background material. Luckily there are some very good recent surveys on this.
- Opinion mining and sentiment analysis, by Bo Pang and Lillian Lee, in Foundations and Trends in Information Retrieval 2(1-2), pp. 1–135, 2008. Also available as a book or e-book.
- Networks, Crowds, and Markets, by David Easley and Jon Kleinberg. This very readable text has been recently published, as a textbook for an undergrad class. PDF is still available free on-line.
- A survey of statistical network models, Goldenberg, Zheng, Fienberg, and Airoldi. A soon-to-be-published survey article.
The second half of the course will be presentations of recent research papers.
- Important terms used in Analysis of Social Media
- Problems frequently addressed in Analysis of Social Media
- Computational methods frequently used in Analysis of Social Media
- Datasets studied in Analysis of Social Media
- Recent or influential technical papers in Analysis of Social Media
Grades are based on:
- The paper presentation
- The project (writeup and presentation).
- Class participation.
I use some discretion in assigning grades but my guidelines for grading are announced in the overview talk.