Improving Artificial Teachers by Considering How People Learn and Forget

Aurélien Nioche; Pierre-Alexandre Murena; Carlos de la Torre Ortiz; Antti Oulasvirta

doi:10.1145/3397481.3450696

Improving Artificial Teachers by Considering How People Learn and Forget

Aurélien Nioche^*, Pierre-Alexandre Murena, Carlos de la Torre Ortiz, Antti Oulasvirta

^*Corresponding author for this work

University of Helsinki

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

6 Citations (Scopus)

143 Downloads (Pure)

Abstract

The paper presents a novel model-based method for intelligent tutoring, with particular emphasis on the problem of selecting teaching interventions in interaction with humans. Whereas previous work has focused on either personalization of teaching or optimization of teaching intervention sequences, the proposed individualized model-based planning approach represents convergence of these two lines of research. Model-based planning picks the best interventions via interactive learning of a user memory model’s parameters. The approach is novel in its use of a cognitive model that can account for several key individual- and material-specific characteristics related to recall/forgetting, along with a planning technique that considers users’ practice schedules. Taking a rule-based approach as a baseline, the authors evaluated the method’s benefits in a controlled study of artificial teaching in second-language vocabulary learning (N = 53).

Original language	English
Title of host publication	26th International Conference on Intelligent User Interfaces, IUI 2021
Publisher	ACM
Pages	445-453
Number of pages	9
ISBN (Electronic)	9781450380171
DOIs	https://doi.org/10.1145/3397481.3450696
Publication status	Published - 14 Apr 2021
MoE publication type	A4 Conference publication
Event	International Conference on Intelligent User Interfaces - Virtual, Online, College Station, United States Duration: 13 Apr 2021 → 17 Apr 2021 Conference number: 26

Conference

Conference	International Conference on Intelligent User Interfaces
Abbreviated title	IUI
Country/Territory	United States
City	College Station
Period	13/04/2021 → 17/04/2021

Access to Document

10.1145/3397481.3450696

ELEC_Nioche_Improving_Artificial__Teachers_IUI_2021_finalpublishedversionFinal published version, 626 KB

Cite this

@inproceedings{73665e06175441d9bf8f20f47b87184e,

title = "Improving Artificial Teachers by Considering How People Learn and Forget",

abstract = "The paper presents a novel model-based method for intelligent tutoring, with particular emphasis on the problem of selecting teaching interventions in interaction with humans. Whereas previous work has focused on either personalization of teaching or optimization of teaching intervention sequences, the proposed individualized model-based planning approach represents convergence of these two lines of research. Model-based planning picks the best interventions via interactive learning of a user memory model{\textquoteright}s parameters. The approach is novel in its use of a cognitive model that can account for several key individual- and material-specific characteristics related to recall/forgetting, along with a planning technique that considers users{\textquoteright} practice schedules. Taking a rule-based approach as a baseline, the authors evaluated the method{\textquoteright}s benefits in a controlled study of artificial teaching in second-language vocabulary learning (N = 53).",

author = "Aur{\'e}lien Nioche and Pierre-Alexandre Murena and {de la Torre Ortiz}, Carlos and Antti Oulasvirta",

year = "2021",

month = apr,

day = "14",

doi = "10.1145/3397481.3450696",

language = "English",

pages = "445--453",

booktitle = "26th International Conference on Intelligent User Interfaces, IUI 2021",

publisher = "ACM",

address = "United States",

note = "International Conference on Intelligent User Interfaces, IUI ; Conference date: 13-04-2021 Through 17-04-2021",

}

Nioche, A, Murena, P-A, de la Torre Ortiz, C & Oulasvirta, A 2021, Improving Artificial Teachers by Considering How People Learn and Forget. in 26th International Conference on Intelligent User Interfaces, IUI 2021. ACM, pp. 445-453, International Conference on Intelligent User Interfaces, College Station, Texas, United States, 13/04/2021. https://doi.org/10.1145/3397481.3450696

Improving Artificial Teachers by Considering How People Learn and Forget. / Nioche, Aurélien; Murena, Pierre-Alexandre; de la Torre Ortiz, Carlos et al.
26th International Conference on Intelligent User Interfaces, IUI 2021. ACM, 2021. p. 445-453.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Improving Artificial Teachers by Considering How People Learn and Forget

AU - Nioche, Aurélien

AU - Murena, Pierre-Alexandre

AU - de la Torre Ortiz, Carlos

AU - Oulasvirta, Antti

N1 - Conference code: 26

PY - 2021/4/14

Y1 - 2021/4/14

N2 - The paper presents a novel model-based method for intelligent tutoring, with particular emphasis on the problem of selecting teaching interventions in interaction with humans. Whereas previous work has focused on either personalization of teaching or optimization of teaching intervention sequences, the proposed individualized model-based planning approach represents convergence of these two lines of research. Model-based planning picks the best interventions via interactive learning of a user memory model’s parameters. The approach is novel in its use of a cognitive model that can account for several key individual- and material-specific characteristics related to recall/forgetting, along with a planning technique that considers users’ practice schedules. Taking a rule-based approach as a baseline, the authors evaluated the method’s benefits in a controlled study of artificial teaching in second-language vocabulary learning (N = 53).

AB - The paper presents a novel model-based method for intelligent tutoring, with particular emphasis on the problem of selecting teaching interventions in interaction with humans. Whereas previous work has focused on either personalization of teaching or optimization of teaching intervention sequences, the proposed individualized model-based planning approach represents convergence of these two lines of research. Model-based planning picks the best interventions via interactive learning of a user memory model’s parameters. The approach is novel in its use of a cognitive model that can account for several key individual- and material-specific characteristics related to recall/forgetting, along with a planning technique that considers users’ practice schedules. Taking a rule-based approach as a baseline, the authors evaluated the method’s benefits in a controlled study of artificial teaching in second-language vocabulary learning (N = 53).

UR - http://www.scopus.com/inward/record.url?scp=85104541749&partnerID=8YFLogxK

U2 - 10.1145/3397481.3450696

DO - 10.1145/3397481.3450696

M3 - Conference article in proceedings

SP - 445

EP - 453

BT - 26th International Conference on Intelligent User Interfaces, IUI 2021

PB - ACM

T2 - International Conference on Intelligent User Interfaces

Y2 - 13 April 2021 through 17 April 2021

ER -

Improving Artificial Teachers by Considering How People Learn and Forget

Abstract

Conference

Access to Document

Other files and links

Fingerprint