CS6742: Natural Language Processing and Social Interaction
1/25/2011: Course description and policies

Time and place Tuesdays and Thursdays, 10:10-11:00, Upson 315
Instructor Professor Lillian Lee. For contact info and updates, see http://www.cs.cornell.edu/home/llee
Co-pilot Cristian Danescu-Niculescu-Mizil, http://www.cs.cornell.edu/∼cristian
Course homepage http://www.cs.cornell.edu/courses/cs6742/2011sp. Site for course info; updated frequently.
Course CMS page http://cms.csuglab.cornell.edu. Site for submitting assignments.

Prerequisites CS 2110 or equivalent programming experience, course in artificial intelligence or any relevant subfield (e.g., NLP, information retrieval, machine learning), and graduate standing; or, permission of instructor.

Course description

More and more of life is now manifested online, and many of the digital traces that are left by human activity are increasingly recorded in natural-language format. This course examines the opportunities for natural language processing to contribute to the analysis and facilitation of socially embedded processes.

CS6742 is geared towards the research-oriented, although not specifically tailored towards students with much research experience or with research interests directly in natural language processing or social interaction (network science, social media, traditional modes of communication, etc).

The planned structure of the course (see course homepage for updates) reflects this focus:

Lecture Date Agenda item Pedagogical purpose Assignment released
#1 Jan 25 Course overview   A1: diagnostic reading asst (due a bit before lecture #2; see asst. for exact date).
#2 27 "How opinions are" paper (WWW 2009) Case study: opinions, influence; reviews A2: reading on controversy detection (due a bit before lecture #4).
#3 Feb 1 "Meme-tracking" paper (KDD 2009) Case study: influence, information diffusion; blogs and on-line news sources  
#4 3 "Leave a reply" paper (Wksp on the weblogging ecosystem, 2006) Instructor-led class discussion, to exemplify how students should structure project-proposal sessions: conversational interactions; comment threads A3: diagnostic hands-on data-acquisition (due a bit before lecture #6).
#5 8 "Mark my words!" paper (WWW 2011) Case study: conversational interactions; Twitter  
#6 10 Introduction to discourse analysis Foundational material A4: extending A3 with exploratory classification and language analysis (due a bit before lecture #8).
#7 15 Theories of discourse structure Foundational material


#8 17 Group discussion of A4 solutions Instructor-led class discussion, as guidance/feedback on A4

A5: reading for student-led project-proposal session (due the morning of the Wednesday before lecture #10 so discussion leaders can integrate others' suggestions with their own.)

Subsequent assignments that are released on Thursdays are due the next Wednesday morning for the whole class, with the discussion leader running the project-discussion the following day and turning in a finalized project proposal the day after that (Friday). So, the process takes about a week.

#9 22 "Get out the vote" paper (EMNLP 2006) Case study: conversational interaction, sentiment analysis; face-to-face conversations, political settings

A6: reading for student-led project-proposal session (due the morning of the Monday before lecture #11).

Subsequent assignments that are released on Tuesdays are due the next Monday morning for the whole class, with the discussion leader running the project-discussion the following day and turning in a finalized project proposal the day after that (Wednesday). So, the process takes about a week.







Mar 24

Project-proposal sessions begin with A5 results


(about 3.5 weeks)

Group development of possible research projects, discussing interesting questions, required resources, etc.

Final projects are to be chosen from among those proposed by the group.

Assignments released every Tuesday and Thursday.
Mar 22 Spring Break
Mar 24 Spring Break




Mar 29-



Project-proposal sessions continue (number depends on final enrollment tally) (ditto) (ditto)






May 3

Some time after Spring Break (depending on final enrollment tally), class sessions will turn into progress-report/feedback sessions, with the earlier sessions perhaps devoted to a more thorough coverage of related work Group feedback on projects, and learning about related work Assignments consist of each group's presentations; probably 1-2.
May 12 final project due

Grading The approximate proportion of the course grade is indicated in brackets.

Courses of related interest This semester, these include:

Academic Integrity Academic and scientific integrity compels one to properly attribute to others any work, ideas, or phrasing that one did not create oneself. To do otherwise is fraud.

Much of the coursework involves written work, so we emphasize certain points here. The easiest rule of thumb is, acknowledge the work and contributions and ideas and words and wordings of others. Do not copy or slightly reword portions of papers, Wikipedia articles, textbooks, other students' work, something you heard from a talk or a conversation, or anything else, really, without acknowledging your sources. See http://www.cs.cornell.edu/courses/cs6742/2011sp/handouts/ack-others.pdf and http://www.theuniversityfaculty.cornell.edu/AcadInteg/ for more information and useful examples.

I take violations of the Code of Academic Integrity (http://cuinfo.cornell.edu/Academic/AIC.html) and the principles behind it very seriously, and have assigned failing grades for such violations in the past.

Code for generating the calendar above and css was (barely) adapted from the original versions created by Andrew Myers.