Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health
For computational psychiatry and narrative analysis, this work provides a theoretically grounded framework that identifies macro-structural organization as the primary locus of clinical signal, offering testable hypotheses for intervention design.
The paper introduces a three-level narrative evaluation framework (micro-lexical, meso-embedding, macro-LLM) and shows that macro-level evaluation substantially outperforms lexical and embedding features for mental health prediction across 830 Chinese therapeutic texts, challenging the field's emphasis on word-counting.
How people narrate their experiences offers a window into how the mind organizes them. Computational approaches to therapeutic writing have evolved from lexical counting to neural methods, yet remain fragmented: dictionary tools miss discourse structure, while embeddings conflate local coherence with global organization. No existing framework maps these techniques onto the hierarchical processes through which narratives are constructed. Here we introduce a three-level framework - micro-level lexical features, meso-level semantic embeddings, and macro-level LLM narrative evaluation - and show, across 830 Chinese therapeutic texts spanning depression, anxiety, and trauma, that macro-level evaluation substantially outperforms lexical and embedding features for mental health prediction. This challenges the field's emphasis on word-counting: formal structural features (Labov's story grammar, RST coherence, propositional composition) demonstrate that narrative organization per se carries predictive signal, while clinically-grounded narrative dimensions capture how psychological states are expressed through discourse. Semantic embeddings add minimal independent value but yield incremental gains in multi-level classification. By grounding computational levels in discourse processing theory, this framework identifies macro-structural organization as the primary locus of clinical signal and generates testable hypotheses for intervention design and longitudinal research.