Ishaank18/screenplay-lexicons

# Screenplay Lexicons

This dataset contains lexicon files used for screenplay feature extraction:

## Files

### 1. Concreteness Ratings (`Concreteness_ratings_Brysbaert_et_al_BRM.txt`)
- **Source**: Brysbaert et al. (2014) - Behavior Research Methods
- **Content**: Concreteness ratings for 40,000 English words
- **Format**: TSV with columns: Word, Bigram, Conc.M, Conc.SD, Unknown, Total, Percent_known, SUBTLEX, Dom_Pos
- **Size**: ~1.6 MB

### 2. Distributional Polarity Lexicon (`DPLp-EN_lrec2016.txt`)
- **Source**: Distributional Polarity Lexicon (DPLp-EN) from LREC 2016
- **Content**: Sentiment polarity scores for English words
- **Format**: TSV with word::pos and positive,negative,neutral scores
- **Size**: ~4.6 MB

## Usage

```python
from huggingface_hub import hf_hub_download

# Download concreteness lexicon
conc_path = hf_hub_download(
repo_id="Ishaank18/screenplay-lexicons",
filename="Concreteness_ratings_Brysbaert_et_al_BRM.txt",
repo_type="dataset"
)

# Download polarity lexicon
pol_path = hf_hub_download(
repo_id="Ishaank18/screenplay-lexicons",
filename="DPLp-EN_lrec2016.txt",
repo_type="dataset"
)
```

## Citation

If you use these lexicons, please cite the original papers:

**Concreteness Ratings:**
```
Brysbaert, M., Warriner, A.B., & Kuperman, V. (2014).
Concreteness ratings for 40 thousand generally known English word lemmas.
Behavior Research Methods, 46, 904-911.
```

**Distributional Polarity Lexicon:**
```
Abdaoui, A., Azé, J., Bringay, S., & Poncelet, P. (2016).
Feel: French Expanded Emotion Lexicon.
Language Resources and Evaluation, 50(4), 1-23.
```

## License

These lexicons are provided for research purposes. Please refer to the original publications for licensing information.