Towards Collaborative Intelligent Tutors: Automated Recognition of Users’ Strategies

Yakov Gal; Elif Yamangil; Stuart M. Shieber; Andee Rubin; Barbara J. Grosz

doi:10.1007/978-3-540-69132-7_21

Towards Collaborative Intelligent Tutors: Automated Recognition of Users’ Strategies

Yakov Gal
, Elif Yamangil
, Stuart M. Shieber
, Andee Rubin
, Barbara J. Grosz

School of Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper addresses the problem of inferring students’ strategies when they interact with data-modeling software used for pedagogical purposes. The software enables students to learn about statistical data by building and analyzing their own models. Automatic recognition of students’ activities when interacting with pedagogical software is challenging. Students can pursue several plans in parallel and interleave the execution of these plans. The algorithm presented in this paper decomposes students’ complete interaction histories with the software into hierarchies of interdependent tasks that may be subsequently compared with ideal solutions. This algorithm is evaluated empirically using commercial software that is used in many schools. Results indicate that the algorithm is able to (1) identify the plans students use when solving problems using the software; (2) distinguish between those actions in students’ plans that play a salient part in their
problem-solving and those representing exploratory actions and mistakes; and (3) capture students’ interleaving and free-order action sequences.

Original language	English
Title of host publication	9th International Conference of Intelligent Tutoring Systems
Place of Publication	Montreal, Canada
Publisher	Springer
Pages	162-172
Number of pages	11
ISBN (Electronic)	978-3-540-69132-7
ISBN (Print)	978-3-540-69130-3
DOIs	https://doi.org/10.1007/978-3-540-69132-7_21
Publication status	Published - 2008
Event	9th International Conference of Intelligent Tutoring Systems - Montreal, Canada Duration: 23 Jun 2008 → 27 Jun 2008

Conference

Conference	9th International Conference of Intelligent Tutoring Systems
Abbreviated title	ITS 2008
Country/Territory	Canada
City	Montreal
Period	23/06/08 → 27/06/08

Access to Document

10.1007/978-3-540-69132-7_21

https://link.springer.com/chapter/10.1007/978-3-540-69132-7_21

Cite this

@inproceedings{6b3e04f173c245fa8f307730c78b0a70,

title = "Towards Collaborative Intelligent Tutors: Automated Recognition of Users{\textquoteright} Strategies",

abstract = "This paper addresses the problem of inferring students{\textquoteright} strategies when they interact with data-modeling software used for pedagogical purposes. The software enables students to learn about statistical data by building and analyzing their own models. Automatic recognition of students{\textquoteright} activities when interacting with pedagogical software is challenging. Students can pursue several plans in parallel and interleave the execution of these plans. The algorithm presented in this paper decomposes students{\textquoteright} complete interaction histories with the software into hierarchies of interdependent tasks that may be subsequently compared with ideal solutions. This algorithm is evaluated empirically using commercial software that is used in many schools. Results indicate that the algorithm is able to (1) identify the plans students use when solving problems using the software; (2) distinguish between those actions in students{\textquoteright} plans that play a salient part in their problem-solving and those representing exploratory actions and mistakes; and (3) capture students{\textquoteright} interleaving and free-order action sequences.",

author = "Yakov Gal and Elif Yamangil and \{M. Shieber\}, Stuart and Andee Rubin and Grosz, \{Barbara J.\}",

year = "2008",

doi = "10.1007/978-3-540-69132-7\_21",

language = "English",

isbn = "978-3-540-69130-3",

pages = "162--172",

booktitle = "9th International Conference of Intelligent Tutoring Systems",

publisher = "Springer",

address = "United Kingdom",

note = "9th International Conference of Intelligent Tutoring Systems, ITS 2008 ; Conference date: 23-06-2008 Through 27-06-2008",

}

Gal, Y, Yamangil, E, M. Shieber, S, Rubin, A & Grosz, BJ 2008, Towards Collaborative Intelligent Tutors: Automated Recognition of Users’ Strategies. in 9th International Conference of Intelligent Tutoring Systems. Springer, Montreal, Canada, pp. 162-172, 9th International Conference of Intelligent Tutoring Systems, Montreal, Canada, 23/06/08. https://doi.org/10.1007/978-3-540-69132-7_21

TY - GEN

T1 - Towards Collaborative Intelligent Tutors: Automated Recognition of Users’ Strategies

AU - Gal, Yakov

AU - Yamangil, Elif

AU - M. Shieber, Stuart

AU - Rubin, Andee

AU - Grosz, Barbara J.

PY - 2008

Y1 - 2008

N2 - This paper addresses the problem of inferring students’ strategies when they interact with data-modeling software used for pedagogical purposes. The software enables students to learn about statistical data by building and analyzing their own models. Automatic recognition of students’ activities when interacting with pedagogical software is challenging. Students can pursue several plans in parallel and interleave the execution of these plans. The algorithm presented in this paper decomposes students’ complete interaction histories with the software into hierarchies of interdependent tasks that may be subsequently compared with ideal solutions. This algorithm is evaluated empirically using commercial software that is used in many schools. Results indicate that the algorithm is able to (1) identify the plans students use when solving problems using the software; (2) distinguish between those actions in students’ plans that play a salient part in their problem-solving and those representing exploratory actions and mistakes; and (3) capture students’ interleaving and free-order action sequences.

AB - This paper addresses the problem of inferring students’ strategies when they interact with data-modeling software used for pedagogical purposes. The software enables students to learn about statistical data by building and analyzing their own models. Automatic recognition of students’ activities when interacting with pedagogical software is challenging. Students can pursue several plans in parallel and interleave the execution of these plans. The algorithm presented in this paper decomposes students’ complete interaction histories with the software into hierarchies of interdependent tasks that may be subsequently compared with ideal solutions. This algorithm is evaluated empirically using commercial software that is used in many schools. Results indicate that the algorithm is able to (1) identify the plans students use when solving problems using the software; (2) distinguish between those actions in students’ plans that play a salient part in their problem-solving and those representing exploratory actions and mistakes; and (3) capture students’ interleaving and free-order action sequences.

U2 - 10.1007/978-3-540-69132-7_21

DO - 10.1007/978-3-540-69132-7_21

M3 - Conference contribution

SN - 978-3-540-69130-3

SP - 162

EP - 172

BT - 9th International Conference of Intelligent Tutoring Systems

PB - Springer

CY - Montreal, Canada

T2 - 9th International Conference of Intelligent Tutoring Systems

Y2 - 23 June 2008 through 27 June 2008

ER -

Towards Collaborative Intelligent Tutors: Automated Recognition of Users’ Strategies

Abstract

Conference

Access to Document

Fingerprint

Cite this