Increasing the Scalability and Reliability of a Web-based Intelligent Tutoring System
Assistment project representation for WPI's Poster Symposium 2006
Increasing the Scalability and Reliability of a Web-based Intelligent Tutoring System
Authors: Kai Rasmussen and Jozsef Patvarczki
Advisor: Neil Heffernan
Abstract
The Assistments project is a Web-based tutoring system. The system focus is to teach 8th and 10th grade mathematics and MCAS preparation. It is currently being used in schools throughout Worcester. Our goal is to serve our web-based tutoring system across the entire sate of Massachussetts. The Intelligent Tutoring System (ITS) must provide scalability and high availability in order to serve thousands of users. We wish to show that through even simple load sharing and redirection we can achieve a high level of reliability and support greater numbers of students. The ideal fault-tolerant system should detect when an application is no longer available and then it can redirect requests to another server. Moreover, it needs to do continuous monitoring and error-detection as well as attempt to solve the occured problems. Finally, student content is persisted in a relational database as XML and then parsed into a java object during runtime. We will show that caching these parsed XML objects can provide a significant performance boost, and increase our scalability.
Addressing the Testing Challenge with a Web-Based E-Assessment System thet Tutors as it Assesses
Author: Mingyu Feng
Advisor: Neil Heffernan
Abstract
Secondary teachers across the country are being asked to use formative assessment data to inform their classroom instruction. At the same time, critics of No Child Left Behind are calling the bill "No Child Left Untested" emphasizing the negative side of assessment, in that every hour spent assessing students is an hour lost from instruction. Or does it have to be? What if we better integrated assessment into the classroom, and we allowed students to learn during the test? Maybe we could even provide tutoring on the steps of solving problems. Our hypothesis is that we can achieve more accurate assessment by not only using data on whether students get test items right or wrong, but by also using data on the effort required for students to learn how to solve a test item. We provide evidence for this hypothesis using data collected with our E-ASSISTment system by more than 600 students over the course of the 2004-2005 school year. We also show that we can track student knowledge over time using modern longitudinal data analysis techniques.
The ASSISTment Builder: Towards an Analysis of the Cost Effectiveness of ITS
Authors: Darren Torpey, Abraao Lourenco, Terrence Turner, and Neil Heffernan
Advisor: Neil Heffernan
Abstract
Intelligent Tutoring Systems, while effective at producing student learning, are notoriously costly to construct, and require PHD level experience in cognitive science and rule based programming. The literature suggests that it takes at least 200 hours of work to build 1 hour of ITS content. With funding from the Office of Naval Research, we have been engaged in building tools to reduce the development time by allowing authors with no programming experience to build "pseudo-tutors". Pseudo-tutors are ITS constructs that mimic cognitive tutors but are limited in that they only apply to a single problem. The ASSISTment Builder is a tool designed to rapidly create, test, and deploy a very simple type of pseudo-tutors called ASSISTments. These tutors provide a simplified cognitive model based upon a state graph designed for a specific problem. The system simplifies the process of tutor creation to allow users with little or no ITS experience to develop content.
Are Students Learning in the Assistment System?
Author: Leena Razzaq
Advisor: Neil Heffernan
Abstract
Razzaq et al, 2005 reported that the Assistment system was causing students to learn at the computer but we were not sure if that was simply due to students getting practice or more due to the "intelligent tutoring" that we created and force students to do if they got an item wrong. Our survey indicated that some students found being forced to do scaffolding sometimes frustrating. We were not sure if all of the time we invested into these "fancy" scaffolding questions was worth it. We conducted a simple experiment to see if students learned on a set of 4 items, if they were given the scaffolds compared with just being given hints that tried to TELL them the same information that the scaffolding questions tried to ASK from them. Our results show that students that were given the scaffolds performed better with an effect size of 0.3.