ChatPPG.
Paper

Scoping the Landscape of Large Language Model-based Affective Personal Informatics: Review, Reflection, Future Direction

Minjie Liu, Lihuan Li, Xuran Li, Flora Salim, Benjamin Tag (arXiv)
arXiv 2610.200842026multimodalText
Read paper arXiv Cite
PreprintFirst posted: Oct 14, 2026Added to atlas: Oct 15, 2026Source
Citations—Not available
GitHub stars—Not available
HF downloads—Not available

Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.

Affective personal informatics (PI) involves capturing, tracking, analyzing, and reflecting on personal data to support emotional self-awareness and mental well-being. Recent advances in large language models (LLMs) are reshaping affective PI, yet a comprehensive survey of LLM-based affective PI systems is lacking. Their synthesis reveals an overreliance on multi-stage, text-centric pipelines, a predominance of active, screen-bound interactions, and a severe demographic skew toward young, university-campus-based cohorts in empirical evaluations.

  • Venue: arXiv 2610.20084 (submitted 2026-10-14)
  • Signals: multimodal, text
  • Form factor: any
At a glance
Venue
arXiv 2610.20084 (submitted 2026-10-14)
Published
2026
DOI
Not reported
arXiv
2610.20084 (opens in a new tab)
PMID
Not reported
Licence
Not reported
Signals
multimodalText
Form factor
Any
Subjects
Not reported
Code
Not reported
Added
Oct 15, 2026

Abstract

Affective personal informatics (PI) involves capturing, tracking, analyzing, and reflecting on personal data to support emotional self-awareness and mental well-being. Recent advances in large language models (LLMs) are reshaping affective PI, yet a comprehensive survey of LLM-based affective PI systems is lacking. To bridge this gap, we systematically analyzed 45 papers published between January 2020 and June 2026 across four major computing and health databases, examining their macro trends, system taxonomies, and research methodologies. Our synthesis reveals an overreliance on multi-stage, text-centric pipelines, a predominance of active, screen-bound interactions, and a severe demographic skew toward young, university-campus-based cohorts in empirical evaluations. Based on these findings, we critically reflect on prevailing architectural and methodological shortcomings and outline actionable future directions for building end-to-end multimodal, low-burden, and inclusive affective PI systems.

Verbatim fromarXiv· arXiv metadata (abstracts are released under CC0)

Scoping the Landscape of Large Language Model-based Affective Personal Informatics: Review, Reflection, Future Direction: ChatPPG research summary card

How it works

How Method works: Setup → Method → TargetSetup: Signals (multimodal, text); Form factor (any). Method: Method (Language-aligned).SetupSignals: multimodal, textSignalsmultimodal, textForm factor: anyForm factoranyMethodMethodLanguage-aligned

Cite

@article{llmaffectivepersonalinfo2026,
  title = {{Scoping the Landscape of Large Language Model-based Affective Personal Informatics: Review, Reflection, Future Direction}},
  author = {Minjie Liu and Lihuan Li and Xuran Li and Flora Salim and Benjamin Tag (arXiv)},
  year = {2026},
  journal = {arXiv 2610.20084 (submitted 2026-10-14)},
  eprint = {2610.20084},
  url = {https://arxiv.org/abs/2610.20084}
}

History

  1. Added to the ChatPPG research hub

More on ChatPPG