Adaptive stress-aware recommendation of supportive engagement activities for digital mental health: a contextual bandit approach with domain-specific language models

Most digital mental-health tools give every user the same content, regardless of how that user feels now or what has helped them before. We built a pipeline that reads free text, detects stress and emotion with domain-adapted language models, and then picks a supportive activity with a contextual bandit. We also asked when per-user personalisation pays off. With five seeds per model, MentalRoBERTa outperformed retrained BERT-base and RoBERTa-base on stress detection (weighted F1 0.818). On our five-class, intervention-oriented emotion taxonomy it did not (macro F1 0.571). In a simulated engagement environment, simple non-contextual bandits did better than LinUCB at the population level. Per-user LinUCB gained nothing when it started from a shared population prior. Started from scratch, it beat the shared model by 0.179 in mean reward over 20 seeds, but only when simulated users had different activity preferences. We tested the classifiers on 70 free-text responses from real users, rated blind by a psychologist. Stress was detected well (area under the ROC curve 0.940). Emotion agreement was only fair (Cohen's κ 0.278), and most disagreements involved responses the psychologist labelled as overwhelm. The pipeline works technically, but its recommendation benefits come from simulation and need prospective testing.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-19
DOI
https://doi.org/10.21203/rs.3.rs-11454113/v1
Primary Topic
Emotion and Mood Recognition
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Adaptive stress-aware recommendation of supportive engagement activities for digital mental health: a contextual bandit approach with domain-specific language models

Md Ariful Islam Mozumder, Sabeeha Jabeen, Muahmmad Ahmed, Hee-Cheol Kim et al.
Research Square
Emotion and Mood Recognition
preprint

Adaptive stress-aware recommendation of supportive engagement activities for digital mental health: a contextual bandit approach with domain-specific language models

Md Ariful Islam Mozumder, Sabeeha Jabeen, Muahmmad Ahmed, Hee-Cheol Kim, Ziinat Makaeva
preprint en

Abstract

Most digital mental-health tools give every user the same content, regardless of how that user feels now or what has helped them before. We built a pipeline that reads free text, detects stress and emotion with domain-adapted language models, and then picks a supportive activity with a contextual bandit. We also asked when per-user personalisation pays off. With five seeds per model, MentalRoBERTa outperformed retrained BERT-base and RoBERTa-base on stress detection (weighted F1 0.818). On our five-class, intervention-oriented emotion taxonomy it did not (macro F1 0.571). In a simulated engagement environment, simple non-contextual bandits did better than LinUCB at the population level. Per-user LinUCB gained nothing when it started from a shared population prior. Started from scratch, it beat the shared model by 0.179 in mean reward over 20 seeds, but only when simulated users had different activity preferences. We tested the classifiers on 70 free-text responses from real users, rated blind by a psychologist. Stress was detected well (area under the ROC curve 0.940). Emotion agreement was only fair (Cohen's κ 0.278), and most disagreements involved responses the psychologist labelled as overwhelm. The pipeline works technically, but its recommendation benefits come from simulation and need prospective testing.

Research Square
Inje University (KR)
Emotion and Mood Recognition
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon