Award Abstract # 1021975
Adding an Intelligent Tutoring System to Alice

NSF Org: DUE
Division Of Undergraduate Education
Recipient: PURDUE UNIVERSITY
Initial Amendment Date: September 2, 2010
Latest Amendment Date: September 14, 2012
Award Number: 1021975
Award Instrument: Standard Grant
Program Manager: Michael Erlinger
DUE
 Division Of Undergraduate Education
EDU
 Directorate for STEM Education
Start Date: September 1, 2010
End Date: August 31, 2015 (Estimated)
Total Intended Award Amount: $348,089.00
Total Awarded Amount to Date: $348,089.00
Funds Obligated to Date: FY 2010 = $348,089.00
History of Investigator:
  • Hubert Dunsmore (Principal Investigator)
  • Stephen Cooper (Co-Principal Investigator)
  • Luo Si (Co-Principal Investigator)
  • Stephen Cooper (Former Principal Investigator)
Recipient Sponsored Research Office: Purdue University
2550 NORTHWESTERN AVE # 1100
WEST LAFAYETTE
IN  US  47906-1332
(765)494-1055
Sponsor Congressional District: 04
Primary Place of Performance: Purdue University
2550 NORTHWESTERN AVE # 1100
WEST LAFAYETTE
IN  US  47906-1332
Primary Place of Performance
Congressional District:
04
Unique Entity Identifier (UEI): YRXVL4JYCEF5
Parent UEI: YRXVL4JYCEF5
NSF Program(s): S-STEM-Schlr Sci Tech Eng&Math,
CCLI-Type 2 (Expansion)
Primary Program Source: 04001011DB NSF Education & Human Resource
1300XXXXDB H-1B FUND, EDU, NSF
Program Reference Code(s): 9178, SMET
Program Element Code(s): 153600, 749200
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.076

ABSTRACT

Alice is a high-impact, high-interest program visualization environment, that is increasingly being used to teach novices object-oriented programming in a range of courses. Results provide evidence that using Alice can significantly improve achievement, retention and recruitment of high-risk CS majors during their first year. This project is expanding the capabilities of Alice by integrating an intelligent tutoring system (ITS). The ITS has three major functions: 1) intelligent delivery of individualized instructional materials, 2) automatic detection of off-task student behavior and 3) the ability to alert instructors that a student may be having difficulties. Expected project outcomes include the enhanced version of Alice with the ITS and additional curricular materials. Assessment is designed to determine if student achievement and attitudes improve as a result of using the ITS. The PIs expect to grow the community of ITS developers for computing education. The Alice community includes hundreds of college faculty and high school teachers across a diverse collection of settings and has been used by thousands of students.

PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Stephen Cooper, Yoon Jae Nam, and Luo Si "Initial results of using an intelligent tutoring system with Alice" Proceedings of the 17th ACM annual conference on Innovation and technology in computer science education (ITiCSE '12) , 2012 , p.138 10.1145/2325296.2325332 http://doi.acm.org/10.1145/2325296.2325332
Suleyman Cetintas, Luo Si, Hans Aagard, Kyle Bowen, Mariheida Cordova-Sanchez "Microblogging in a Classroom: Classifying Students' Relevant and Irrelevant Questions in a Microblogging-Supported Classroom" IEEE Transactions on Learning Technologies , v.4 (4) , 2011 , p.292

PROJECT OUTCOMES REPORT

Disclaimer

This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.

Effective Intelligent Tutoring Systems

Based on our experience with building the tutoring systems and conducting our research, we think that the following should be the important components for an intelligent tutoring system:

• The design of the tutoring system should be based on the type of supervision.  In a school-like environment, where students’ performance can be judged by supervisors, it would be better to have a Tutoring system like the Type 1 as it can speedup learning.  On the other hand, tutoring systems focusing on self-learning or online learning without external supervisors where the system plays an important role in judging the progress of a student, Type 2 tutoring systems would be preferred.

• A clearly designed workflow that allows students to track their progress is crucial.

• The tutorial should be short and at the same time should teach generic concepts as opposed to focusing on the student solving a particular task.

• Having pop-ups should be based on the audience targeted.  For much younger learners (middle or primary school), having them can be beneficial.

• The time limit allowed to complete a task should be based on a student’s exposure to Alice.  We recommend anywhere between 15-30 minutes for a typical Alice Program.

• Having multiple contexts for tasks of similar levels prevents the student from losing interest and at the same time helps in grasping the concept.

• Feedback at the end of each task is very important.  If students are made to switch contexts, they should be aware of the reasons, for example, they took more time than average to solve a program.

• Tutorials are not useful after a point.  Deciding the number of times a tutorial should be repeated after failing activities at the same level of difficulty should depend on the target audience.  For high school students, making them repeat the tutorial more than twice might make them lose interest in the tutoring system and hinder learning.

• Having a simple rule-based judger to decide student progress can be effective to ensure that the student actually learns the concepts and avoids external supervision.

• In a tutoring system with rule-based judgers, careful attention must be paid to the selection of tutorials and activities as some programs can be solved in multiple ways and hence, the judging system might fail for a different but correct solution.

Conclusion

In this research, we created three tutorials that we constructed on Alice to closely resemble the design of Intelligent Tutoring systems.  We presented the results of the case studies on these tutoring system.  We have discussed what we think are the essential components for an intelligent tutorial system.  As we conducted the case studies on a fairly small number of students, we suggest that these studies be repeated with larger groups to further reinforce the results of the studies.


Last Modified: 11/30/2015
Modified by: Hubert E Dunsmore

Please report errors in award information by writing to: awardsearch@nsf.gov.

Print this page

Back to Top of page