Course: CS 6474 / CS 4803 Social Computing
Term: Fall 2018
Location: Klaus 2456
Time: Monday & Wednesday 4:30 – 5:45pm
Office Hours: By appointment (TSRB 341)
Teaching Assistant: Koustuv Saha

Overview

This course is geared toward developing a broad understanding of the characteristics of today’s online social systems, including the opportunities and challenges that engender this emergent area. We will focus on the study of different social processes, behavior, and context on today's online social platforms, and learn how to make sense of the vast repositories of data that are generated on these platforms everyday. We will also learn about the design principles behind these systems and the key issues that arise from the widespread adoption of social computing systems in the wild. Learning objectives include:

- Collection and analysis of large-scale social data.
- Exploration of a variety of quantitative methodologies that could be applied to the study of social computing systems.
- Building social tools that augment current social computing systems.
- Apply social data to answer questions in a variety of practical scenarios and domains, such as politics and health.

The course will be taught seminar style, which means there will be weekly readings on a variety of topics (see topics and schedule below), and students will be required to participate in a group term project. There will be no exams, however there are going to be three assignments which will involve mini individual projects. Students will also be required to participate in discussions on the pre-assigned class readings in a blog (Piazza), in order to demonstrate their understanding of the material, and to raise interesting questions and points for class discussion.

The term project will be 3-4 person group projects, and each group will be required to make a midterm presentation and a final presentation of their work. They will also need to submit a midterm report outlining their work as well as a final report. Each student will need to clearly articulate their concrete contribution in the group project. Topic of the project can be picked by the student groups after discussion with the instructor; the instructor will also provide a set of sample project ideas in class materials. If the project requires data analysis, a contribution of the project could be collecting that data, or the students could also use any of the publicly available social datasets available online. Each project will require both original work as well as a small number of compulsory analyses that cover key concepts from the course.

Students may audit the course, but all students who attend must perform the weekly blog posts about the reading, to facilitate discussion.

Required Skills: In terms of prerequisite skills, students need to have basic knowledge of statistics and preliminary machine learning. An overview of the concepts and tools needed will be reviewed across two lectures, however in-depth coverage of the fundamentals is not in the scope of this course. Students also need to be proficient in programming, in an object-oriented/scripting language (e.g., Python, Perl, Java, C#). Experience in use of a scientific computing software like R is a bonus.

Academic Integrity: All assigned work is expected to be individual, except where explicitly indicated otherwise. You are encouraged to discuss the assignments with your classmates; however, what you hand in should be your own work. For more information, please review the Georgia Tech Honor Code.

Assignments and Grading

Responses to Class Readings (on Piazza; best 15 out of 18 in all) - 20%
Class Attendance/Participation - 10%
Assignment I - 10%
Assignment II - 10%
Assignment III - 10%
Term Project - 40%
      : Project Proposal - 5%
      : Midterm Project Presentation (schedule) - 5%
      : Milestone Report - 10%
      : Final Project Presentation (schedule) - 5%
      : Final Report - 15%

Weekly Schedule *

Week 1 (20-Aug) Introduction
Week 1 (22-Aug) Sociological Background
Week 2 (27-Aug) Sociological Foundations I
Week 2 (29-Aug) Sociological Foundations II
Week 3 (3-Sep) Labor Day - No Class
Week 3 (5-Sep) Sociological Foundations III
Discussion of Example Term Projects
Week 4 (10-Sep) Social Computing Theories: Public Displays and Performance
Week 4 (12-Sep) Social Computing Theories: Identity
Assignment I Due
Week 5 (17-Sep) Social Computing Theories: Disclosure and Regulation
Week 5 (19-Sep) Social Computing Theories: Social Capital and Social Influence
Week 6 (24-Sep) Quantitative Methods Review I
Week 6 (26-Sep) Attend GVU Brown Bag Seminar on 27-Sep - No in-class meeting
Term Project Proposals Due
Week 7 (1-Oct) Quantitative Methods Review II
Week 7 (3-Oct)Class Exercises on Quantitative Methods (Guest Lecture) - Bring Laptops
Week 8 (8-Oct) Fall Recess - No Class
Week 8 (10-Oct) Analyzing Language I
Week 9 (15-Oct) Analyzing Language II
Week 9 (17-Oct) Social Computing Constructs: Credibility
Assignment II Due
Week 10 (22-Oct) Social Computing Constructs: Polarization and Selective Exposure
Week 10 (24-Oct) Benefits/Applications of Social Computing: Politics
Week 11 (29-Oct) Midterm Project Presentations (Day 1)
Week 11 (31-Oct) Midterm Project Presentations (Day 2)
Midterm Milestone Reports Due
Week 12 (5-Nov) Social Computing and Societal Bias (Guest Lecture by Sandeep Soni)
Week 12 (7-Nov) Offline Connections of Social Computing (Guest Lecture by Sandeep Soni)
Week 13 (12-Nov) Benefits/Applications of Social Computing Systems: Activism, Social Movements, Crisis
Week 13 (14-Nov) Benefits/Applications of Social Computing: Predictions and Forecasting
Week 14 (19-Nov) Challenges of Social Computing Systems: Ethics of Algorithms
Assignment III Due
Week 14 (21-Nov) Student Recess (Thanksgiving) - No Class
Week 15 (26-Nov) Challenges of Social Computing Systems: Privacy
Week 15 (28-Nov) Final Project Presentations I
Slides for all teams due by 11:59pm on Nov 27 (Canvas)
Week 16 (3-Dec) Final Project Presentations II
Final Project Reports Due (on Dec 12)

Weekly Readings *

Week 2 (27-Aug): Sociological Foundations I
An Experimental Study of the Small World Problem [pdf]

Week 2 (29-Aug): Sociological Foundations II
Structural Holes and Good Ideas [pdf]

Week 3 (5-Sep): Sociological Foundations III
The Strength of Weak Ties [pdf]
Predicting Tie Strength With Social Media [pdf]

Week 4 (10-Sep): Social Computing Theories: Public Displays and Performance
The Presentation of Self in Everyday Life: Introduction (PDF file pgs. 6-10) [pdf]
The Presentation of Self in the Age of Social Media: Distinguishing Performances and Exhibitions Online [pdf]

Week 4 (12-Sep): Social Computing Theories: Identity
Identity and Deception in the Virtual Community [pdf]
4chan and/b: An Analysis of Anonymity and Ephemerality in a Large Online Community [pdf]

Week 5 (17-Sep): Social Computing Theories: Disclosure and Regulation
Anonymity and Self-Disclosure on Weblogs [pdf]
Understanding Social Media Disclosures of Sexual Abuse Through the Lenses of Support Seeking and Anonymity [pdf]

Week 5 (19-Sep): Social Computing Theories: Social Capital and Social Influence
The Benefits of Facebook “Friends:” Social Capital and College Students' Use of Online SNS [pdf]
Everyone's an influencer: Quantifying Influence on Twitter [pdf]

Week 8 (10-Oct): Analyzing Language I
Diurnal and Seasonal Mood Vary with Work, Sleep, and Daylength Across Diverse Cultures [pdf]
Personality, Gender, and Age in the Language of Social Media: The Open-Vocabulary Approach [pdf]

Week 9 (15-Oct): Analyzing Language II
Gender and Power: How Gender and Gender Environment Affect Manifestations of Power [pdf]
No Country for Old Members: User lifecycle and linguistic change in online communities [pdf]

Week 9 (17-Oct): Social Computing Constructs: Credibility
Tweeting is Believing? Understanding Microblog Credibility Perceptions [pdf]
Examining the Alternative Media Ecosystem Through the Production of Alternative Narratives of Mass Shooting Events on Twitter [pdf]
(Optional) Social bots distort the 2016 US Presidential election online discussion [link]

Week 10 (22-Oct): Social Computing Constructs: Polarization and Selective Exposure
Echo Chambers Online?: Politically Motivated Selective Exposure among Internet News Users [pdf]
Exposure to ideologically diverse news and opinion on Facebook [pdf]

Week 10 (24-Oct): Benefits/Applications of Social Computing Systems: Politics
The Political Blogosphere and the 2004 U.S. Election: Divided They Blog [pdf]
Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment [pdf]
(Optional) "I Wanted to Predict Elections with Twitter and all I got was this Lousy Paper" - A Balanced Survey on Election Prediction using Twitter Data [pdf]
(Optional) What is Twitter, a Social Network or a News Media? [pdf]

Week 12 (5-Nov): Social Computing and Societal Bias (Guest Lecture by Sandeep Soni)
Quantitative Analysis of Culture Using Millions of Digitized Books [pdf]
Word embeddings quantify 100 years of gender and ethnic stereotypes [pdf]

Week 12 (7-Nov): Offline Connections of Social Computing (Guest Lecture by Sandeep Soni)
Language from police body camera footage shows racial disparities in officer respect [pdf]
Gender identity and lexical variation in social media [pdf]

Week 13 (12-Nov): Benefits/Applications of Social Computing Systems: Activism, Social Movements
The revolutions were tweeted: Information flows during the 2011 Tunisian and Egyptian revolutions [pdf]
Social media and the decision to participate in political protest: Observations from Tahrir Square [pdf]

Week 13 (14-Nov): Benefits/Applications of Social Computing Systems: Predictions and Forecasting
Predicting Depression via Social Media [pdf]
Private traits and attributes are predictable from digital records of human behavior [link]
Prediction and explanation in social systems [link]

Week 14 (19-Nov): Challenges of Social Computing Systems: Ethics of Algorithms
Experimental evidence of massive-scale emotional contagion through social networks [pdf]
“I always assumed that I wasn’t really that close to [her]”: Reasoning about invisible algorithms in the news feed [pdf]

Week 15 (26-Nov): Challenges of Social Computing Systems: Privacy
Data ex Machina: Introduction to Big Data [link]
Data, privacy, and the greater good [pdf]

Recommended, Relevant Readings

Not required, but the following books are good references for the class:

Networks, Crowds, and Markets, by David Easley and Jon Kleinberg
Six Degrees, by Duncan Watts
On Individuality and Social Forms, by Georg Simmel
Networked, by Barry Wellman
Writing for Social Scientists, by Howard Becker
Machine Learning for Hackers, by Drew Conway and John Myles White
Natural Language Processing with Python, by Steven Bird, Ewan Klein, and Edward Loper



* Topics to be covered and the corresponding readings are subject to change. Please always check the online schedule.