Characterizing LLM-Based Family Education through the Lens of Activity Theory: A Scoping Review of the HCI Literature

2026-09-23

AI Summary

This study addresses the lack of systematic explanations regarding how large language models (LLMs) mediate home education within human-computer interaction research. Pioneering an integration of Activity Theory with the AODM framework, it employs a scoping review methodology to conduct quantitative and qualitative analyses of 53 studies. The findings reveal how LLMs restructure the division of labor and rule systems in home education, elucidating how their capabilities are organized through family engagement and how parent-child interaction patterns evolve accordingly. Furthermore, this work identifies limitations in current evidence concerning sustained personalization and authority negotiation. Ultimately, it provides a systematic theoretical perspective for understanding LLM-supported home education practices.

Abstract

Large language models (LLMs) are increasingly involved in family education, yet HCI has not systematically explained the educational interactions that emerge around them. This scoping review analyzes 53 HCI studies from 6,540 records across 19 venues. Using activity theory and AODM, it relates participants and educational objects to mediation, labour, and rules. We find that the literature centers on child--parent interaction and on language, AI literacy, and relational learning. The introduction of LLMs enabled conversational, embodied, and spatial systems to generate support from the context of an unfolding interaction. LLMs redistributed educational labour, while family and institutional rules left parents and professionals responsible for interpreting outputs and deciding how they entered practice. Evidence across families and educational purposes remains limited, especially on sustained personalization, repair labour, and how families negotiate authority and rules. The review offers a framework explaining how LLM capabilities become organized through family participation.

Problem

• Large Language Models
• Family Education
• Human-Computer Interaction
• Educational Interactions

Innovation

• Large Language Models
• Activity Theory
• Family Education
• Human-Computer Interaction
• Educational Labour