691, Fall 2016
Advanced Topics on Social Media Analysis
Social media emerges as a mainstream communication means. It is used by people in all walks of life, employed in different disciplines and industries from trend prediction to business intelligence, from cybersecurity to behavior modeling. People share content, opinions, comment, like, tag, as well as connect old friends, meet new ones, and organize special interest groups. These user-generated activities help create various types of social media networks, generating various, heterogeneous sources of information otherwise not available through conventional media and communication channels. In this graduate course, we will introduce basic concepts and fundamental principles, learn the state-the-art research findings, study challenges indigenous to big social media data, and explore interdisciplinary solutions to social media analysis. We will study issues like public opinion, influence and intervention, sentiment analysis, privacy, trust, security, and reputation, examine social media applications in social mobility, cybersecurity, healthcare, education, and discuss intriguing open questions such as big data paradox, evaluation dilemma, and noise-removal fallacy. The ultimate goal of this graduate course is to sharpen problem solving skills of our graduate students, improve critical thinking capability, and explore novel research issues, paving way for generating startup ideas and conducting advanced research.
- Two of the following: probability and statistics/linear algebra, data mining, machine learning, social media mining, or artificial intelligence.
- Other students should receive permission from the instructor.
Classroom and Hours:
- BYAC 260, TTh 3:00 – 4:15pm
TTh 4:15 - 5:15pm, BYE 566
Other times: by appointment only
TAs and Office Hours:
Ghazaleh Beigi: By appointment
Suhang Wang: Project
|Semester Duration: 8/18/2016 - 12/2/2016
Please send emails to TA
email@example.com for meetings and questions
Reference Textbooks and Reading Material:
- Social Media Mining: An Introduction,
Reza Zafarani, Mohammad Ali Abbasi, and Huan Liu, Cambridge University Press, 2014, free pdf download
- Networks, Mark Newman, Oxford University Press, 2010,
- Networks, Crowds, and Markets, David Easley and Jon Kleinberg, Cambridge University Press, 2010,
- Network Science, Albert-László Barabási,
Cambridge University Press, 2016,
- State-of-art papers/articles, and
- Casual readings from news and magazines.
- Dr. Yi Chang, Huawei Research America, "Whole Page Presentation
Optimization for Search Engines". November 29, 2016.
- Professor Wei Wang, UCLA, "Big Data Analytics in Science". November 18,
- Professor Xintao Wu, University of Arkansas, "Causal Network-based
Discrimination Discovery and Prevention". November 4, 2016.
- Professor Vipin Kumar, University of Minnesota, "Big Data in Climate:
Opportunities and Challeges for Machine Learning and Data Mining". October
- Dr. Karl Kempf, Intel, "Business Decision Making - Intuition is
Unreliable, Analytics is Incomplete". October 20, 2016.
- Mr. Fred Morstatter, ASU, "Detecting and Mitigating Data Collection
Bias in Online Social Networks". October 18, 2016.
Reading Assignments, Homework, Projects,
and Mid-Term Exams (Tentative, Details at myASU):
- Paper presentation
- Projects and report presentation (30%)
- 1 exam or
- Class participation, Quizzes,
Extra Credit (10% + 10%)
Slides and Schedule::p>
- Announcements are made
regularly in Blackboard. Emails will be sent out on a need basis.
- Weekly Schedule - Please
visit Blackboard for Course Documents and Blog (or Discussion Board).
- Experienced practitioners and renowned researchers
may be invited as guest instructors for specific topics.
We will include below interesting links recommended by our students and
To encourage the online participation, we moved this part to Course Information on
Last updated: 11/29/16
Maintained by Huan Liu
If you have comments or suggestions, email
huan.liu at asu.edu
with Subject "CSE691 Suggestions"