From Relevant Posts to Attributable Spans: Explicit Symptom Evidence for Depression Questionnaire Inference
Paper · https://arxiv.org/abs/2611.12900
arXiv:2611.12900v1 Announce Type: new Abstract: Longitudinal social-media histories offer an opportunity to assess depression, potentially supporting the inference of standardized depression questionnaire responses. However, this task requires evidence that is semantically relevant to a symptom and attributable to the user, while being sufficiently specific to support an individual questionnaire item. Existing approaches rely on semantic similarity to retrieve posts, which can introduce misleading or non-attributable evidence, particularly in multi-symptom posts and discussions of others' experiences. We propose SREE (Symptom Retrieval and Evidence-Grounded InfErence), an evidence-grounded pipeline that extracts first-person and symptom-specific text spans, selects a representative subset using a Facility Location-inspired objective, and performs Evidence-Gated Inference over the selected evidence. We evaluate evidence retrieval on BDI-Sen and evidence-conditioned questionnaire inference on eRisk 2019-2021. Compared with state-of-the-art retrieval approaches, SREE achieves relative improvements of 70% in post-level precision and 59% in F1, while retaining at least 30% fewer posts. On multi-symptom sentences, it also outperforms dense retrieval in precision and F1 even with twice the retrieval budget. Across all three eRisk collections, SREE achieves the highest exact item-level agreement while remaining competitive on ordinal and aggregate metrics. These results highlight the importance of localizing attributable evidence and controlling its composition before inferring depression questionnaire responses.
First seen by Oriel on .
AI summary
The paper presents SREE, a pipeline that improves depression questionnaire inference by retrieving first-person, symptom-specific, and attributable evidence spans from longitudinal social-media histories.
- SREE extracts symptom-specific first-person spans, selects a representative subset with a Facility Location-inspired objective, and applies Evidence-Gated Inference.
- On BDI-Sen, SREE improves post-level precision by 70% and F1 by 59% relative to state-of-the-art retrieval approaches.
- SREE retains at least 30% fewer posts and outperforms dense retrieval on multi-symptom sentences even with twice the retrieval budget.
- Across eRisk 2019-2021, SREE achieves the highest exact item-level agreement while remaining competitive on ordinal and aggregate metrics.
#depression inference #evidence retrieval #social media #nlp
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| arXiv AI Papers | oai:arXiv.org:2611.12900v1 | https://arxiv.org/abs/2611.12900 Read discussion |