` COMSE6998 Spring 2018 (NLP In Context): Computational Models of Social Meaning
COMSE6998 (NLP in Context)
Computational Models of Social Meaning
Spring 2018
[Announcements] [General Information]
[Syllabus]

Announcements
  • Deadline for Literature Review: March 30 at 11:59pm. Again one sumission per team.
  • Notice slight change in schedule as discussed in class! The change in schedule of discussion presentation has led to some conflict for 2 presenters so those have been moved to solve the conflict.
  • [9/29/2018] Unassigned papers can be presented for extra credit as mentioned in class. If you are interested please email the instructor (will be assigned based on request first come first served).
  • [9/29/2018] Assignment of students to papers is done (based on responses we had at 9:00am today) . We manage to match the top choices of everyone. WHile majority of students filled to survey there are few who did not. If you did not fill up the survey you can email the instructor and select papers that are no currently assigned. If you do not email by end of class today, we will assign you to a paper.
  • [9/25/2018] List of papers for discussion is up. You will have to select your top 10 choices by filling up this Survey You will have until Sunday January 28 at 8pm to fill in the survey. Note: there are some short papers (5 pages), we expect that for those papers we will only assign one student to present.
  • [9/24/2018] List of papers for discussion will be up soon and an announcement will be posted here and on Coursework. Once the announcement is sent you will have 2 days to pick papers (we will mention day and time). And a link to survey to select 5 top choices will be posted.
  • As discussed in class, to facilitate the discussions on sentiment starting on Wed 1/31 papers for that section have been posted. If you want ot present one those papers you can email the instructor before even the survey is up.
  • your name will be added to the papers in first come first serve.
  • Please fill in the survey about your background by Friday January 23 at 12pm: Survey about Background
  • Welcome to Computational Models of Social Meaning!
[Top]

General Information

Description

Computational Models of Social Meaning is a seminar in Natural Language Processing, focusing on computational methods for extracting social and interactional meaning, mainly from text (both traditional media and social media) and speech. Topics include detection of speaker's sentiments, emotions, opinions and beliefs, sarcasm, deception, persuation, perspective, power and influence, politeness, and personality. Analysis of meaning-bearing characteristics of the speaker and topic, including text, discourse, prosodic and other cues.

Prerequisites

  • COMS 3133/4/7/9 (Data Structures) or equivalent programming ability in at least one systems or scripting language (C++, Java, Python)

Instructor: Smaranda Muresan

  • smara [who is at] columbia [dot] edu
  • Office Hours: Wed 5:30pm-6:30pm
    Office: Interchurch Center (61 Claremont Avenue --- SW corner of 120th Street and Claremont Avenue), Room 850

TA: Kevin Raji Cherian

  • Email: kr2741@columbia.edu
  • Office Hours: Wednesday 10:00-12:00pm
  • Office: TA room Mudd Building

TA: Ryan Serrao

  • Email: rs3774@columbia.edu
  • Office Hours: Fridays 6:00-8:00pm
  • Office: TA room Mudd Building

Lectures

  • Monday, Wednesday 4:10-5:25, Hamilton 303. Link to Columbia University Campus Map
The classes consists of lectures and discussions of research papers led by students. To facilitate the discussion of research articles on a particular topic each week, the topic is introduced the previous week. Usually Wednesdays will be lectures and Mondays discussion of research articles led by students Lecture notes will be posted on CourseWorks.

Grade Breakdown

  • 15% Data Analysis Assignments

  • There will be 3 data analysis assignments that will require relatively small amount of work to learn about a data source. You will be asked to answer one or two questions and to notice some interesting points about the data source. The grading for this will be Excellent/Good/Insufficient. The data analysis assignments will be due before class, on Courseworks site. Late assignments will not be accepted, except emergency situations.

  • 20% Discussion of Papers

  • Each student will do a critical discussion of ONE of the research articles proposed for reading. Students will prepare a brief presentation of the paper (What is the goal of the paper? The research hypothesis? What data they use? What methods? How is evaluated?) followed by leading a critical discussion on key positive and negative aspects, availability of code and datasets. You can consider as inspiration guidelines given to reviewers of conference papers Review Form ). But all ratings should be accompanied by a critical discussion that justifies your scores. Due to class size you will present in pairs (two students per paper). Teaming will be based on your paper choices (you will be asked to send a ranked list of top 5 papers you'd like to discuss)

  • 5% Class Participation

  • 60% Final Project

  • Design and implement a software product of appropriate scope and complexity given the time constraints. Project should be related to one topic discussed in class or related issues. Prepare a literature review (by mid semester), give a class presentation and a paper write-up describing the methodology and results. The projects will be done in groups of 3-4 students. Split up of grades will be 10% for literature review, 5% class presentations, 45% for project and final paper. Contribution of each participant will need to be clearly stated at each stage of the project deliverables.
[Top]

Syllabus

Schedule is tentative and subject to change.

Date Topics Readings Due dates
1/17 Class Introduction
1/22 Lecture: Sentiment Analysis (Word Level)
1/24 Lecture: Sentiment Analysis (Sentence Level; Target-based Sentiment; multilinguality)
1/29 Lecture: Deep Learning for Sentiment Analysis (word, sentence, and multilinguality)
1/31 Discussion: Sentiment Analysis
2/5 Discussion: Sentiment Analysis
2/7 Lecture: Emotion/Mood
2/12 Discussion: Emotion/Mood
2/14 Lecture: Irony/Sarcasm
2/19 Discussion: Irony and Sarcasm Detection
2/21 Lecture: Argument Mining
2/26 Discussion: Sentiment (cont) + Argument Mining
2/28 Lecture: Perspective/Framing/Ideology
3/5 Lecture: Persuasion
Guest Lecturer: Chris Hidey
3/7 Canceled due to snow
  • [PF1] moved to 3/21
  • [PF2] moved to 3/19
  • [PF3] moved to 3/28
3/12 No Class (Spring Break)
3/14 No Class (Spring Break)
3/19 Discussion : Perspective/Framing/Ideology(cont)+ Persuasion
3/21 Canceled due to Snow
3/26 Discussion: Framing and Perception/Ideology
3/28 Lecture: Deception Detection
Guest Lecture: Sarah Ita Levitan
4/2 Discussion: Deception Detection
4/4 Lecture: Personality and Interpersonal Stanceand
Tentiative: Social Impact and Ethics
4/9 Discussion: Personality and Interpersonal Stance
Tentative aslos Social Impact and Ethics
4/11 Lecture: Extracting Social Networks
4/16 Discussion: Extracting Social Networks
4/18 Lecture: Social Power/Influence
4/23 Discussion: Social Power/Influence; Social Impact of NLP
4/25 Final Project Presentations
4/30 Final Project Presentations Final Project Due May 7th






smara [who is at] columbia [dot] edu