MathBuddy: A Multimodal System for Affective Math Tutoring

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kar, Debanjana, Böss, Leopold, Braca, Dacia, Dennerlein, Sebastian Maximilian, Hubig, Nina Christine, Wintersberger, Philipp, Hou, Yufang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916967824228352
author Kar, Debanjana
Böss, Leopold
Braca, Dacia
Dennerlein, Sebastian Maximilian
Hubig, Nina Christine
Wintersberger, Philipp
Hou, Yufang
author_facet Kar, Debanjana
Böss, Leopold
Braca, Dacia
Dennerlein, Sebastian Maximilian
Hubig, Nina Christine
Wintersberger, Philipp
Hou, Yufang
contents The rapid adoption of LLM-based conversational systems is already transforming the landscape of educational technology. However, the current state-of-the-art learning models do not take into account the student's affective states. Multiple studies in educational psychology support the claim that positive or negative emotional states can impact a student's learning capabilities. To bridge this gap, we present MathBuddy, an emotionally aware LLM-powered Math Tutor, which dynamically models the student's emotions and maps them to relevant pedagogical strategies, making the tutor-student conversation a more empathetic one. The student's emotions are captured from the conversational text as well as from their facial expressions. The student's emotions are aggregated from both modalities to confidently prompt our LLM Tutor for an emotionally-aware response. We have evaluated our model using automatic evaluation metrics across eight pedagogical dimensions and user studies. We report a massive 23 point performance gain using the win rate and a 3 point gain at an overall level using DAMR scores which strongly supports our hypothesis of improving LLM-based tutor's pedagogical abilities by modeling students' emotions. Our dataset and code are available at: https://github.com/ITU-NLP/MathBuddy .
format Preprint
id arxiv_https___arxiv_org_abs_2508_19993
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MathBuddy: A Multimodal System for Affective Math Tutoring
Kar, Debanjana
Böss, Leopold
Braca, Dacia
Dennerlein, Sebastian Maximilian
Hubig, Nina Christine
Wintersberger, Philipp
Hou, Yufang
Computation and Language
Artificial Intelligence
Human-Computer Interaction
The rapid adoption of LLM-based conversational systems is already transforming the landscape of educational technology. However, the current state-of-the-art learning models do not take into account the student's affective states. Multiple studies in educational psychology support the claim that positive or negative emotional states can impact a student's learning capabilities. To bridge this gap, we present MathBuddy, an emotionally aware LLM-powered Math Tutor, which dynamically models the student's emotions and maps them to relevant pedagogical strategies, making the tutor-student conversation a more empathetic one. The student's emotions are captured from the conversational text as well as from their facial expressions. The student's emotions are aggregated from both modalities to confidently prompt our LLM Tutor for an emotionally-aware response. We have evaluated our model using automatic evaluation metrics across eight pedagogical dimensions and user studies. We report a massive 23 point performance gain using the win rate and a 3 point gain at an overall level using DAMR scores which strongly supports our hypothesis of improving LLM-based tutor's pedagogical abilities by modeling students' emotions. Our dataset and code are available at: https://github.com/ITU-NLP/MathBuddy .
title MathBuddy: A Multimodal System for Affective Math Tutoring
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2508.19993