Computer Science W6998:
Computational Models of Social Meaning
Spring 2014
[Announcements] [General Information]
[Syllabus]

Announcements
  • April 10: Data Analysis Assisgnment 2 out today. It is due in a week, April 17 before class
  • Feb 14: Project Descriptions up on Corseworks under Assignments. Examples of Project ideas also included
  • Feb 13: Class Canceled due to weather (All Columbia Classes are canceled after 3pm)
  • Feb 1: Selection of presenters for paper discussion up (names appear near the assigned paper).
  • Jan 29: Class set up also on Columbia's Courseworks.
  • Jan 28: List of discussion papers is up. Each student will lead discussion on one paper. Please bring to class on Thursday Jan 30th, a list of your top five choices. Please write down your name
  • Jan 27: Full list of readings for the semester will be up by Tuesday, Jan 28 11:59pm (an email will be send out, and this space updated)
  • 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 conversational text (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] ccls [dot] columbia [dot] edu
  • Office Hours: Thursdays 6:00pm-7:00pm

TA: Arpit Gupta

  • ta [dot] cmsm [AT] gmail [dot] com
  • Office Hours: Mondays 4:15pm-5:15pm in the TA room in Mudd

Lectures

  • Thursday 4:10-6:00, MUD 644
The class consists of lectures and discussion of research papers led by students. To facilitate the discussion of research articles on a particular topic each week, an introduction to the topic is given in the previous week. Thus, the class structure will be as follows: 50 min discussion of two research articles led by students on the topic of the week (intro to the topic given in the previous week); 30 minutes in depth lecture and discussion of open questions related to the topic of the week; 25 minutes Intro lecture to the topic of the following week (to facilitate paper discussion).

Grade Breakdown

  • 10% Data Analysis Assignments

    • There will be 2 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.

  • 30% 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 followed by leading a critical discussion on key positive and negative aspects, availability of code and datasets. Full reading list will be up Tuesday Jan 28 at 11:59pm . Each student will prepare a list of her/his top five choices and bring it to class on January 30th. Please write down you name! Final selection will be done by TA/instrutor by Feb 1 . We will try to take into account your preferences, so it is important you bring those to class on Jan 30.

  • 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. Groups of 2-3 are welcome as is individual work (complexity expectations being tuned accordingly). Split up of grades will be 10% for literature review, 5% class presentations, 45% for project and final paper.
[Top]

Syllabus

Schedule is tentative and highly subject to change.

"
Date Topics Readings Due dates
1/23 Class Introduction
1/30 Sentiment Lexicon
&
Intro to Sentiment Analysis 		Discussion papers:
Data Analysis Assignment 1 out
2/6 Sentiment Analysis
&
Intro do Emotion/Mood 		General reading for lecture Discussion papers: Data Analysis Assignment 1 Due
2/13 Canceled due to Snow
2/20 Emotion/Mood
&
Intro to Hedge & Belief Analysis 		Discussion papers:
2/27 Hedge Detection and Belief Analysis
&
Intro to Irony and Sarcasm; Detecting Conflicting Statements 		General Readings:

Discussion papers:

Project Ideas due
3/6 Irony/Sarcasm & Detecting Contradictory Statements
&
Intro to Agreement/Disagreement 		General readings (optional)
  • Ido Dagan, Dan Roth, Mark Sammons, Fabio Zanzotto. Recognizing Textual Entailment. Synthesis Lecture on Human Language Technologies. Graeme Hirst (ed). (Chapater 1, 4).[book uploded on CourseWorks Files\&Resources/Readings]
  • Roberto Gonzalez-Ibanez, Smaranda Muresan, Nina Wacholder (2011). Identifying Sarcasm in Twitter: A Closer Look . Proceedings of ACL-HTL 2011 (short paper).
Discussion papers: 		Project Proposal due March 10 at 11:59pm
3/13 Agreement/Disagreement
&
Intro to Perspective 		Discussion Papers:
3/20 No Lecture: Spring Break
3/27 Perspective
&
Intro to Decepton 		Discussion Papers:
4/3 Deception
&
Intro to Social Power 		General readings (optional):
  • DePaulo, Bella M.; James J. Lindsay; Brian E. Malone; Laura Muhlenbruck; Kelly Charlston; and Harris Cooper. 2003. Cues to deception Psychological Bulletin 129(1):74–118.
  • Enos, Frank, Elizabeth Shriberg, Martin Graciarena, Julia Hirschberg, and Andreas Stolcke. 2007. Detecting deception using critical segments. In Proceedings Interspeech, 1621-1624. Antwerp.
Discussion Papers: 		Literature Review due
4/10 Social Power

Guest Lecture		 General readings (guest lecture based on these) Discussion Papers: Data Analysis Assignment 2 out
4/17 Extracting Social Networks from Text

Guest Lecture		 General Readings (guest lecture based on these) Discussion Papers: Data Analysis Assignment 2 DUE
4/24 Personality and Interpersonal Stance Discussion Papers:
5/1 Final Project Presentations (Final projects writeup due May 7, 12pm)





smara [who is at] ccls [dot] columbia [dot] edu

Design adapted from David Elson's site design