LittleToDo: Large Language Model Driven Intervention Tool for Adolescent Academic Procrastination with Affective Computing

Xiaofan HU; Xiaojia YANG; Xiaolong LOU; Tao HE

doi:10.1145/3706599.3719890

LittleToDo: Large Language Model Driven Intervention Tool for Adolescent Academic Procrastination with Affective Computing

Xiaofan HU^*
, Xiaojia YANG
, Xiaolong LOU
, Tao HE

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

Abstract

This paper explores the causes and intervention methods of adolescent academic procrastination and proposes LittleToDo, a compact on-desk device designed to support after-school learning tasks completion by reduce procrastination behaviors. LittleToDo integrates an AI agent as its core component and utilizes a miniature printer as its interaction medium. It monitors and analyzes users’ emotional states and attention levels to provide personalized task planning, reminders and companionship. Additionally, it integrates therapeutic doodling activities and a reward system to alleviate stress and boost motivation. Our research demonstrates that LittleToDo effectively mitigates procrastination while showing positive effects on stress reduction and self-efficacy enhancement. This study contributes an innovative intervention pathway to address academic procrastination among adolescents.

Original language	English
Title of host publication	CHI EA '25: Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems
Publisher	Association for Computing Machinery, Inc
Number of pages	9
ISBN (Electronic)	9798400713958
DOIs	https://doi.org/10.1145/3706599.3719890
Publication status	Published - 26 Apr 2025
Externally published	Yes
Event	2025 CHI Conference on Human Factors in Computing Systems - PACIFICO Yokohama, Yokohama, Japan Duration: 26 Apr 2025 → 1 May 2025

Publication series

Name	Conference on Human Factors in Computing Systems - Proceedings
Publisher	Association for Computing Machinery

Conference

Conference	2025 CHI Conference on Human Factors in Computing Systems
Abbreviated title	CHI 2025
Country/Territory	Japan
City	Yokohama
Period	26/04/25 → 1/05/25

Bibliographical note

Publisher Copyright:
© 2025 Copyright held by the owner/author(s).

Funding

This research was funded by Natural Science Foundation of Zhejiang Province (Project LMS25F020008), Open Research Fund of State Key Laboratory of Digital Medical Engineering of Southeast University (Project 2024-M08) and National Natural Science Foundation of China (Grant No.61902097).

Keywords

Academic Procrastination
Affective Computing
AI Agent
Expressive Art Therapy

Access to Document

10.1145/3706599.3719890

Cite this

HU, X., YANG, X., LOU, X., & HE, T. (2025). LittleToDo: Large Language Model Driven Intervention Tool for Adolescent Academic Procrastination with Affective Computing. In CHI EA '25: Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems Article 382 (Conference on Human Factors in Computing Systems - Proceedings). Association for Computing Machinery, Inc. https://doi.org/10.1145/3706599.3719890

HU, Xiaofan ; YANG, Xiaojia ; LOU, Xiaolong et al. / LittleToDo: Large Language Model Driven Intervention Tool for Adolescent Academic Procrastination with Affective Computing. CHI EA '25: Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, Inc, 2025. (Conference on Human Factors in Computing Systems - Proceedings).

@inproceedings{abdf5a593cb34f87a6adbe817398341b,

title = "LittleToDo: Large Language Model Driven Intervention Tool for Adolescent Academic Procrastination with Affective Computing",

abstract = "This paper explores the causes and intervention methods of adolescent academic procrastination and proposes LittleToDo, a compact on-desk device designed to support after-school learning tasks completion by reduce procrastination behaviors. LittleToDo integrates an AI agent as its core component and utilizes a miniature printer as its interaction medium. It monitors and analyzes users{\textquoteright} emotional states and attention levels to provide personalized task planning, reminders and companionship. Additionally, it integrates therapeutic doodling activities and a reward system to alleviate stress and boost motivation. Our research demonstrates that LittleToDo effectively mitigates procrastination while showing positive effects on stress reduction and self-efficacy enhancement. This study contributes an innovative intervention pathway to address academic procrastination among adolescents.",

keywords = "Academic Procrastination, Affective Computing, AI Agent, Expressive Art Therapy",

author = "Xiaofan HU and Xiaojia YANG and Xiaolong LOU and Tao HE",

note = "Publisher Copyright: {\textcopyright} 2025 Copyright held by the owner/author(s).; 2025 CHI Conference on Human Factors in Computing Systems, CHI 2025 ; Conference date: 26-04-2025 Through 01-05-2025",

year = "2025",

month = apr,

day = "26",

doi = "10.1145/3706599.3719890",

language = "English",

series = "Conference on Human Factors in Computing Systems - Proceedings",

publisher = "Association for Computing Machinery, Inc",

booktitle = "CHI EA '25: Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems",

address = "United States",

}

HU, X, YANG, X, LOU, X & HE, T 2025, LittleToDo: Large Language Model Driven Intervention Tool for Adolescent Academic Procrastination with Affective Computing. in CHI EA '25: Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems., 382, Conference on Human Factors in Computing Systems - Proceedings, Association for Computing Machinery, Inc, 2025 CHI Conference on Human Factors in Computing Systems, Yokohama, Japan, 26/04/25. https://doi.org/10.1145/3706599.3719890

LittleToDo: Large Language Model Driven Intervention Tool for Adolescent Academic Procrastination with Affective Computing. / HU, Xiaofan; YANG, Xiaojia; LOU, Xiaolong et al.
CHI EA '25: Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, Inc, 2025. 382 (Conference on Human Factors in Computing Systems - Proceedings).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - LittleToDo: Large Language Model Driven Intervention Tool for Adolescent Academic Procrastination with Affective Computing

AU - HU, Xiaofan

AU - YANG, Xiaojia

AU - LOU, Xiaolong

AU - HE, Tao

PY - 2025/4/26

Y1 - 2025/4/26

N2 - This paper explores the causes and intervention methods of adolescent academic procrastination and proposes LittleToDo, a compact on-desk device designed to support after-school learning tasks completion by reduce procrastination behaviors. LittleToDo integrates an AI agent as its core component and utilizes a miniature printer as its interaction medium. It monitors and analyzes users’ emotional states and attention levels to provide personalized task planning, reminders and companionship. Additionally, it integrates therapeutic doodling activities and a reward system to alleviate stress and boost motivation. Our research demonstrates that LittleToDo effectively mitigates procrastination while showing positive effects on stress reduction and self-efficacy enhancement. This study contributes an innovative intervention pathway to address academic procrastination among adolescents.

AB - This paper explores the causes and intervention methods of adolescent academic procrastination and proposes LittleToDo, a compact on-desk device designed to support after-school learning tasks completion by reduce procrastination behaviors. LittleToDo integrates an AI agent as its core component and utilizes a miniature printer as its interaction medium. It monitors and analyzes users’ emotional states and attention levels to provide personalized task planning, reminders and companionship. Additionally, it integrates therapeutic doodling activities and a reward system to alleviate stress and boost motivation. Our research demonstrates that LittleToDo effectively mitigates procrastination while showing positive effects on stress reduction and self-efficacy enhancement. This study contributes an innovative intervention pathway to address academic procrastination among adolescents.

KW - Academic Procrastination

KW - Affective Computing

KW - AI Agent

KW - Expressive Art Therapy

UR - https://www.scopus.com/pages/publications/105005745033

U2 - 10.1145/3706599.3719890

DO - 10.1145/3706599.3719890

M3 - Conference paper (refereed)

AN - SCOPUS:105005745033

T3 - Conference on Human Factors in Computing Systems - Proceedings

BT - CHI EA '25: Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems

PB - Association for Computing Machinery, Inc

T2 - 2025 CHI Conference on Human Factors in Computing Systems

Y2 - 26 April 2025 through 1 May 2025

ER -

HU X, YANG X, LOU X, HE T. LittleToDo: Large Language Model Driven Intervention Tool for Adolescent Academic Procrastination with Affective Computing. In CHI EA '25: Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, Inc. 2025. 382. (Conference on Human Factors in Computing Systems - Proceedings). doi: 10.1145/3706599.3719890

LittleToDo: Large Language Model Driven Intervention Tool for Adolescent Academic Procrastination with Affective Computing

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this