Student Model Adjustment Through Random-Restart Hill Climbing
A. Doost, and E. Melis.. Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet, Kassel, Germany, (2010)
Abstract
ACTIVEMATH is a web-based intelligent tutoring system (ITS) for studying mathematics. Its course generator, which assembles content to personalized books, strongly depends on the underlying student model. Therefore, a student model is important to make an ITS adaptive. The more accurate it is, the better could be the adaptation. Here we present which parameters can be optimized and how they can be optimized in an efficient and affordable manner. This methodology can be generalized beyond ACTIVEMATH’s student model. We also present our results for the optimization based on two sets of log data. Our optimization method is based on random-restart hill climbing and it considerably improved the student model’s accuracy.
%0 Conference Paper
%1 abis6
%A Doost, Ahmad Salim
%A Melis., Erica
%B Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet
%C Kassel, Germany
%D 2010
%E Atzmüller, Martin
%E Benz, Dominik
%E Hotho, Andreas
%E Stumme, Gerd
%K clustering community detection graph theory
%T Student Model Adjustment Through Random-Restart Hill Climbing
%X ACTIVEMATH is a web-based intelligent tutoring system (ITS) for studying mathematics. Its course generator, which assembles content to personalized books, strongly depends on the underlying student model. Therefore, a student model is important to make an ITS adaptive. The more accurate it is, the better could be the adaptation. Here we present which parameters can be optimized and how they can be optimized in an efficient and affordable manner. This methodology can be generalized beyond ACTIVEMATH’s student model. We also present our results for the optimization based on two sets of log data. Our optimization method is based on random-restart hill climbing and it considerably improved the student model’s accuracy.
@inproceedings{abis6,
abstract = {ACTIVEMATH is a web-based intelligent tutoring system (ITS) for studying mathematics. Its course generator, which assembles content to personalized books, strongly depends on the underlying student model. Therefore, a student model is important to make an ITS adaptive. The more accurate it is, the better could be the adaptation. Here we present which parameters can be optimized and how they can be optimized in an efficient and affordable manner. This methodology can be generalized beyond ACTIVEMATH’s student model. We also present our results for the optimization based on two sets of log data. Our optimization method is based on random-restart hill climbing and it considerably improved the student model’s accuracy.},
added-at = {2010-09-30T13:24:41.000+0200},
address = {Kassel, Germany},
author = {Doost, Ahmad Salim and Melis., Erica},
biburl = {https://www.bibsonomy.org/bibtex/2346ed20efe83e405169d9f251a50c070/folke},
booktitle = {Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen {\&} Adaptivitaet},
crossref = {lwa2010},
editor = {Atzmüller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
interhash = {bb243736903c7e422ab650a7e2fe4ae4},
intrahash = {346ed20efe83e405169d9f251a50c070},
keywords = {clustering community detection graph theory},
pdf = {http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/abis6.pdf},
presentation_end = {2010-10-05 14:30:00},
presentation_start = {2010-10-05 14:00:00},
room = {-1418},
session = {joint6},
timestamp = {2010-09-30T13:24:41.000+0200},
title = {Student Model Adjustment Through Random-Restart Hill Climbing},
track = {abis},
year = 2010
}