Text Classification
sentence-transformers
Safetensors
English
questionnaire-harmonization
prototype-learning
impulse-control
Instructions to use julia-pfarr/HarmoniCA_impulse-control with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use julia-pfarr/HarmoniCA_impulse-control with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("julia-pfarr/HarmoniCA_impulse-control") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,61 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language: en
|
| 3 |
+
license: cc-by-4.0
|
| 4 |
+
base_model: hkunlp/instructor-large
|
| 5 |
+
tags:
|
| 6 |
+
- questionnaire-harmonization
|
| 7 |
+
- sentence-transformers
|
| 8 |
+
- prototype-learning
|
| 9 |
+
- impulse-control
|
| 10 |
+
pipeline_tag: text-classification
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
# HarmoniCA — Impulse Control Model
|
| 14 |
+
|
| 15 |
+
Part of the **HarmoniCA** collection for harmonising psychiatric questionnaire items across studies.
|
| 16 |
+
This model assigns items from impulse control questionnaires to one of six theoretically motivated symptom dimensions.
|
| 17 |
+
|
| 18 |
+
## Dimensions
|
| 19 |
+
|
| 20 |
+
| ID | Label | Description |
|
| 21 |
+
|----|-------|-------------|
|
| 22 |
+
| 1 | Pathological Gambling | preoccupation with gambling, difficulty controlling gambling urges, time and money spent on gambling |
|
| 23 |
+
| 2 | Hypersexuality | preoccupation with sex, difficulty controlling sexual urges, time and money spent on sexual activities |
|
| 24 |
+
| 3 | Compulsive Buying | preoccupation with buying, difficulty controlling buying urges, excessive spending |
|
| 25 |
+
| 4 | Compulsive Eating | preoccupation with eating, difficulty controlling eating urges, overeating |
|
| 26 |
+
| 5 | Punding & Hobbyism | stereotyped or repetitive behaviors, excessive engagement with hobbies, purposeless repetitive activities |
|
| 27 |
+
| 6 | Dopamine Dysregulation Syndrome | compulsive use of dopaminergic medication beyond therapeutic need |
|
| 28 |
+
|
| 29 |
+
Items rated as not belonging to the impulse control construct are assigned dimension **-1** (Does not fit).
|
| 30 |
+
|
| 31 |
+
## Model Architecture
|
| 32 |
+
|
| 33 |
+
- **Type:** PrototypeModel (prototype-based learning with a fine-tuned sentence transformer)
|
| 34 |
+
- **Base encoder:** [hkunlp/instructor-large](https://huggingface.co/hkunlp/instructor-large)
|
| 35 |
+
- **Inference:** Fine-tuned encoder with learned class prototypes
|
| 36 |
+
|
| 37 |
+
The PrototypeModel learns a single prototype embedding per dimension. At inference, items are assigned to the nearest prototype in the fine-tuned embedding space.
|
| 38 |
+
|
| 39 |
+
## Training Data
|
| 40 |
+
|
| 41 |
+
- **Training items:** 58 expert-labeled questionnaire items
|
| 42 |
+
- **Questionnaires:** QUIP-C, QUIP-RS
|
| 43 |
+
- **Labels:** Expert consensus from two rounds of surveys (psychiatrists/neurologists)
|
| 44 |
+
|
| 45 |
+
## Evaluation
|
| 46 |
+
|
| 47 |
+
Evaluated on 124 held-out items from unseen questionnaires against expert labels.
|
| 48 |
+
|
| 49 |
+
| Cohen's κ | Accuracy |
|
| 50 |
+
|-----------|----------|
|
| 51 |
+
| **0.884** | **90.3%** |
|
| 52 |
+
|
| 53 |
+
## Limitations
|
| 54 |
+
|
| 55 |
+
- Trained on QUIP-RS and QUIP-C; generalization to questionnaires that frame items very differently may be limited.
|
| 56 |
+
- Dopamine Dysregulation Syndrome (dimension 6) is Parkinson's-specific and may not be applicable in non-PD contexts.
|
| 57 |
+
- Dimension structure reflects theoretical consensus among a specific expert panel and may not match all theoretical frameworks.
|
| 58 |
+
|
| 59 |
+
## Citation
|
| 60 |
+
|
| 61 |
+
in preparation
|