← CHI 2026 map

CHI '26 · Honorable mention · full-paper review · confidence medium-high

EmoFlow: From Tracking to Sense-Making of Emotions Through Creative Drawing

Shannon Sie Santosa , Qian Wan , Junnan Yu , Yuhan Luo

EmoFlow’s main value is not a new classifier but a careful empirical correction: drawings do not behave like universal emotion signals. The paper’s strongest contribution is showing how people use drawing as personal sense-making, which is a useful design pivot for CHI.


Axes Lens

Rare contribution shape, typical evidence profile. The point here is not a score. It is to show what kind of claim the paper makes, and whether the evidence pattern is unusual or baseline in this 268 -review set.

Contribution shape

Knowledge form
descriptive knowledge typical · 92/268
Novelty type
empirical finding typical · 68/268
Abstraction level
practice typical · 85/268
Generalization target
methodological argument typical · 16/268
Validation mode
mixed methods typical · 136/268

Evidence profile

Evidence strength
strong typical · 158/268
Claim alignment
strong typical · 231/268
Overclaim risk
low typical · 53/268

Review Summary

EmoFlow is a solid CHI paper because it makes a clear, evidence-backed argument that is easy to miss if one assumes drawings should function like standardized emotion indicators. Rather than claiming a predictive breakthrough, it uses a two-week diary study and follow-up interviews to show that visual expression is highly individualized: the same colors, symbols, or motifs can mean different things across people and even within the same person over time. That is a meaningful departure from common-sense expectations in emotion-tracking systems, where one might expect measurable drawing features to align with reported affect. The paper’s novelty is primarily empirical and methodological: it reframes drawing from a signal to be decoded into a medium for expression and sense-making, and it identifies recurring expression patterns such as emotion-source depictions, metaphors, direct expression, and random mark-making. The validation is appropriate for that claim because the authors combine diary data, statistical analysis, and interviews, and they explicitly report no significant associations between reported emotions and drawing behaviors. The limitations are also candid and important: the sample is small, culturally skewed toward Asian participants, and some quantitative signals are incomplete, so the work should not be overgeneralized. Overall, the paper’s contribution is strongest as a design and interpretation argument for expression-centered emotion tracking technologies, not as a universal model of emotion inference from drawings.

What Changed

Canon before

Prior work often treated drawings as if stable visual features could be mapped to emotion labels in a broadly generalizable way, implying that a small set of observable marks, colors, or shapes could be decoded into affect with little dependence on the drawer’s own context, habits, or explanation.

Departure from common sense

The paper argues against universal, objective mappings from visual drawing features to emotions, claiming meanings are personal and context-dependent rather than decodable via consistent visual cues.

Actual novelty

It introduces an expression-centered emotion-tracking approach using free-form creative drawing (EmoFlow) and identifies four expression-pattern categories (emotion source, metaphorical representation, direct expression, random drawing) from diary study data.

Evidence

A two-week diary study with 21 participants produced 252 drawings plus interviews. The paper reports no significant associations between reported emotions and drawing behaviors or expression patterns, and instead surfaces diverse personal expression patterns, consistent styles, and interpretive challenges. The evidence supports a descriptive and methodological contribution rather than a predictive model.

“ Furthermore, for drawing to be effectively integrated as an input modality in future emotion-tracking tools, we need to examine the user experience of drawing-based emotion expression more closely, including the perceived value, usability, and the challenges it may pose for individuals with varying levels of artistic experience”

actual novelty · Abstract and Findings, section 4.1.1 · confidence 0.98

“3642255 Digital Library Google Scholar [36] Xiaojuan Ma, Emily Yang, and Pascale Fung. 2019. Exploring perceived emotional intelligence of personality-driven virtual agents in handling user challenges”

departure from common sense · Discussion, section 5 · confidence 0.99

“S. Danko. 2004. Influence of the Emotional Perception of a Signal on the Electroencephalographic Correlates of Creative Activity. Human Physiology 30 (03 2004), 145–151. Crossref Google Scholar [56] Erika H Siegel, Molly K Sands, Wim Van den Noortgate, Paul Condon, Yale Chang, Jennifer Dy, Karen S Quigley, and Lisa”

limitation · Limitations & Future Work, section 6 · confidence 0.98

“ 7 Conclusion By investigating how people track everyday emotions through drawings, we conducted a 14-day diary study and collected 252 drawings from 21 participants who showed interest in emotion track”

validation scope · Abstract and Method, section 3.2.2 · confidence 0.99

Limits

Method limits

The study is limited by a small sample, a predominance of Asian participants, and some missing quantitative signals such as pressure data for two participants; categorization also depends on human interpretation of drawings.

Deployment limits

The approach is best suited to exploratory, expression-centered emotion tracking contexts rather than systems that require universal decoding of drawings into emotion labels.

Boundary conditions

Findings are grounded in a two-week diary setting with 21 participants and 252 drawings; the reported patterns may not transfer to more diverse populations, longer deployments, or tasks where drawing skill and cultural conventions differ substantially.

Position in field

The paper positions itself against feature-to-emotion decoding assumptions and toward individualized, creative, expression-centered emotion tracking, contributing a qualitative-quantitative account of how people actually use drawings to make sense of emotions.

Abstract