|
Policies and Requirements
Assignments: Assignments are centered around the practical aspects of implementing, training, and evaluating social computing systems. Assignments will be graded based on code correctness and quality of results determined by model performance on unseen test data. Similar to Homework, assignments are to be completed individually.
Spotlight Papers: Prior to every class, we provide a list of select research papers related to a specific topic in social computing. For some classes, students are expected to choose and read one of the spotlight papers in-depth and write a summary (or review) of the paper before the class. The review should provide a concise summary of the work including the main contributions and (perceived) strengths and limitations of the paper.
Final Project: The final project is a team-based research project, and its purpose is for students to
identify and formulate a social computing problem (task/application),
tackle the problem using current or new methods,
experimentally evaluate the methods on (ideally real-world) datasets, and
analyze the obtained results for insights.
While identifying new problems or developing novel techniques are highly encouraged, they are not required for the purpose of the project; see the provided Latex templates for details.
Note that a team of two students is recommended and each student should clearly report his/her responsibilities in the project, actively contribute to the project, and try to help the other team members.
Each team should submit a 2-page proposal, a 4-page progress report, and an 8-page final report including all references, figures, tables, etc.;
submissions that do not conform to the provided templates, including number of pages, paper size, margin width, and font size restrictions, will receive zero mark with no exception.
In addition, all projects will be presented during the last week of the class; each team should prepare a 15 minute presentation (to introduce the problem and its solution as well as any interesting results, insights, or findings discovered):
Extra Credit: Students can earn extra credits by attending a related CS colloquium, and sending us a report within one week of the talk. The report should provide a concise summary of the research problems addressed in the presentation and draw connections to materials discussed in class. A maximum of two reports will be considered for a total credit of 5%.
Lateness: Late submission for homework or spotlight papers is not allowed, i.e. late after due date/time: zero mark. However, late submission for assignments or projects is allowed: late within three days: 30% reduction in grade; after that: zero mark.
Attendance: We expect students to come to class prepared, having completed the assigned readings – especially the spotlight papers. Your participation will make the class more fun and interactive, and help us to better estimate your progress.
Collaboration and the Facebook Rule: Students are encouraged to work together, and to teach and help each other. However, cheating is a very serious offense and will be revealed and reported to the dean office with no exception. Please always follow UML's Code of Academic Integrity. The Facebook Rule (CREDIT: Min-Yen Kan): This rule says that you are free to meet with fellow students and discuss assignments with them. Writing on a board or shared piece of paper is acceptable during the meeting; however, you may not take any written (electronic or otherwise) record away from the meeting. This applies when the assignment is supposed to be an individual effort. After the meeting, engage in a half hour of mind-numbing activity (like catching up with your friends and family's activities on Facebook), before starting to work on the assignment. This will assure that you are able to reconstruct what you learned from the meeting, by yourself, using your own brain. You must always report names of your collaborators on your assignments.
Religious Observance: Some dates are recognized by the campus as religious holidays – listed here. There will be no due date or exam on these dates. In addition, I accommodate students of all faiths on an individual basis. If you observe a specific religious holiday that is not listed at the above link and overlaps with any due dates of the course, please let us know by the end of the first week of classes.
Anti-Harassment (adapted from ACL Anti-Harassment policy): The open exchange of ideas, the freedom of thought and expression, and respectful scientific debate are central to the aims and goals of this course. Harassment and hostile behavior in any form (including but not limited to harassment based on race, gender, religion, age, appearance, national origin, ancestry, disability, sexual orientation, gender identity, etc.,) are unwelcome in this course.
|