DreamerNLplus applies a mix of classification, regression, few-shot prompting, rules, and retrieval-augmented generation to model psychological states and changes from social media, placing in the top ranks on several CLPsych 2026 subtasks.
Prompt Engineering for Capturing Dynamic Mental Health Self States from Social Media Posts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG Methods
DreamerNLplus applies a mix of classification, regression, few-shot prompting, rules, and retrieval-augmented generation to model psychological states and changes from social media, placing in the top ranks on several CLPsych 2026 subtasks.