Social Media Analysis 10-802 in Fall 2012

From Cohen Courses
Revision as of 15:13, 25 October 2012 by Bbd (talk | contribs) (→‎Assignments)
Jump to navigationJump to search

Announcements

  • William will be out of town (so no office hours) Fri 10/26 and Fri 11/2.
  • The first class is Tuesday 9/11.
  • William's office hours will be 1-2pm Friday (except when otherwise noted).
    • William will be out of town Friday 9/21.

Instructor and Venue

  • Instructor: William Cohen, Machine Learning Dept and LTI
  • Course secretary: Sharon Cavlovich, sharonw+@cs.cmu.edu, 412-268-5196
  • When/where: T/R 10:30-11:50, 4303 GHC, starting after the IC has finished. The first class will be Tuesday 9/11.
    • Note: the room has been moved!
  • 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.
  • TAs: Bhavana Dalvi and Aasish Pappu
  • Syllabus: To best posted, but will approximately follow the syllabus I used last time
  • Office hours:
    • William: 1-2pm Fri
    • Aasish: 2-3pm Thu [GHC 6223]
    • Bhavana: 12-1pm Tue [GHC 5509]
  • Assignment submission / any course related queries should be directed to sma-instructors@cs.cmu.edu for timely response.
  • Course mailing list for announcements: 10802-announce@cs.cmu.edu

Clarification/announcement: This will be a regular 12-credit course (despite the some listings of it as a 6-credit course).

Description

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.

Sample Projects

Here are some projects from previous years, so you can get some ideas of the scope.

.

Syllabus and Readings

Older syllabi:

The first half of the course, roughly, will be presentations of background material. Luckily there are some very good recent surveys on this.

The second half of the course will be presentations of recent research papers.

Other Resources

Assignments

Assignment 1: Due 10:30 AM Tuesday, Sep 25

Send to me (William Cohen), Aasish, and Bhavana an email listing 3 papers you plan to summarize with title, authors, link to on-line version

Any not-yet-summarized papers listing as "papers to review" on this years or last year’s syllabus (I guess last year they were "papers to present") are pre-approved - otherwise, it's fine to pick something new, and we will give you feedback if a paper is a problem. Also, don't propose papers I’ve presented in class, or papers that already have entries in the wiki.

Assignment 2: Due 10:30 AM Thus, Sep 27

Send in your first summary - by sending a link of the new wikipage to sma-instructors@cs.cmu.edu following instructions: Submission Instructions for submitting paper reviews

Here are some example summaries:

Some examples without the new 'study guide' section are here:

Note that you are required to link the summary back into concepts on the wiki via the links AddressesProblem, Category, RelatedPaper, UsesMethod, and UsesDataset. It's ok to link to a problem/paper/method/dataset that's not yet on the wiki, BUT please search first to check if its there.

Assignment 3: Due 10:30 AM Tues, Oct 2

Submit the next two summaries by sending links of the new wikipages to sma-instructors@cs.cmu.edu following instructions: Submission Instructions for submitting paper reviews

Assignment 4: Due 10:30 AM Tues, Oct 9

Submit your preliminary project proposal by sending links of the new wikipages to sma-instructors@cs.cmu.edu following the submission instructions for project proposal.

You should add your page to the wiki by extending this list of project proposals for 10-802 in Fall 2012.

If you're looking for partners for your project - or looking for projects to join - then please add entries on the following wiki page : Hunt for Project partners

There are instructions for project proposals in the slides for the 10-2 lecture.

Assignment 5: Due 10:30 AM Tues, Oct 16

Submit your final project proposal by sending links of the new wikipages to sma-instructors@cs.cmu.edu following the submission instructions for project proposal.

Assignment 6: Due 10:30 AM Tues, Nov 6

In this assignment we want you to summarize a related (and non-wikified) paper of an already wikified paper and give a comparative critique for this pair of papers. There is a list of pairs of papers that you can choose from. You need to assign yourself a pair of papers by writing your Andrew-ID In the 3rd column. After you create a new page for your assignment, link it from the 4th column. Link to the list of papers : coming shortly You can email sma-instructors@cs.cmu.edu with subject containing [review-4] once you are done with the assignment.

Grading

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.