|
Social Science and Policy Studies |
|||
|
|
TOWARDS A VIRTUAL TEACHING
ASSISTANT TO ANSWER QUESTIONS ASKED BY STUDENTS IN INTRODUCTORY COMPUTER
SCIENCE
Abstract
: Students in introductory
programming classes often articulate their questions and information needs incompletely. Consequently, the automatic classification
of student questions to provide automated tutorial responses is a challenging
problem. I analyze a set of 411
questions from an introductory Java programming course by reducing the
natural language of the questions to a vector space, and then utilizing
cosine similarity to identify similar previous questions. I report classification accuracies between
23% and 56%, obtaining substantial improvements by exploiting domain
knowledge (compiler error messages) and educational context (assignment
name). My results are especially timely and
relevant for online courses where students are completing the same set of
assignments asynchronously and access to staff is limited. ____ Cecily Heiner is a PhD candidate at the University of
Utah. Her research interests include
artificial intelligence, natural language processing, human computer
interaction, intelligent tutoring, and machine learning. For her dissertation, she built and
evaluated a tool to provide automated answers to common questions in
introductory computer science(advisor Joe Zachary). Prior to beginning her PhD, she was a
Masters student at mentor, and judge. She
has been recognized for her outreach and involvement with women in computing as an Anita Borg
finalist. Her hobbies include
traveling, running, cooking, gardening, and learning to play the organ. Host: Ryan S.J.d. Baker, Department of Social Science & Policy
Studies Refreshments will be served. Last modified:August 6, 2009 |
|
||