Skip to main content

Social media provides a massive amount of valuable information and shows us how language is actually used by lots of people. This course will give an overview of prominent research findings on language use in social media. The course will also cover several machine learning algorithms and the core natural language processing techniques for obtaining and processing Twitter data.

Instructor
Wei Xu is an assistant professor in the Department of Computer Science and Engineering at the Ohio State University. Her research interests lie at the intersection of machine learning, natural language processing, and social media. She holds a PhD in Computer Science from New York University. Prior to joining OSU, she was a postdoc at the University of Pennsylvania. She is organizing the ACL/COLING Workshop on Noisy User-generated Text, serving as a workshop co-chair for ACL 2017, an area chair for EMNLP 2016 and the publicity chair for NAACL 2016.

Time/Place new
     Fall 2017, CSE 5539-0010 The Ohio State University
     Bolz Hall Room 318 | Tuesday 2:20PM – 4:10PM
     dual-listed undergraduate and graduate course
     [Office Hour] Dreese 495 | Tuesday 4:15PM – 5:15PM

Prerequisites
In order to succeed in this course, you should know basic probability and statistics, such as the chain rule of probability and Bayes’ rule. On the programming side, all projects will be in Python. You should understand basic computer science concepts (like recursion), basic data structures (trees, graphs), and basic algorithms (search, sorting, etc).

Course Readings
     Various academic papers

Discussion Board
     Piazza (TBA)

Grading (subject to changes)
This is a research-oriented project-based course (total 100 points). Instead of exams, each student will do two hands-on programming assignments or an optional research project. The class will assign one paper for reading each week. Each student should read the assigned paper and submit a short critique (between 100-200 words) online in Carmen before 10am on the day of class. These reviews should not be simple summaries, but discuss positive aspects of the paper and limitations, or suggestions for how the work could be improved or extended. Students are allowed to skip two reviews throughout the semester. Please email your reviews or homeworks to the instructor if there are any technical issues with online submission.
  • programming homework #1 (10 points/individual)
  • programming homework #2 (40 points/individual) or a research project (40 points/group)
  • paper summaries (20 points/individual)
  • in-class presentation (20 points/group)
  • participation in class discussions (10 points/individual)

Previous Offerings
     Fall 2016, Ohio State University
     Summer 2016, The North American Summer School on Logic, Language, and Information (NASSLLI)
     Teaching evaluation was 5.72 out of 6 at NASSLLI; average across all instructors was 5.23.
     Summer 2015, University of Pennsylvania