Update README.md

README.md

@@ -4,7 +4,12 @@ tags:
 - setfit
 - sentence-transformers
 - text-classification
+- hate speech
 pipeline_tag: text-classification
+language:
+- it
+metrics:
+- accuracy
 ---
 
 # setfit-italian-hate-speech
@@ -14,6 +19,14 @@ This is a [SetFit model](https://github.com/huggingface/setfit) that can be used
 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
 2. Training a classification head with features from the fine-tuned Sentence Transformer.
 
+This model detects the hate speech for italian language:
+* 1 --> is hate speech
+* 0 --> isn't hate speech
+
+## Dataset
+
+`setfit-italian-hate-speech` is trained on [HaSpeeDe-FB](http://twita.di.unito.it/dataset/haspeede) dataset.
+
 ## Usage
 
 To use this model for inference, first install the SetFit library:
@@ -30,7 +43,7 @@ from setfit import SetFitModel
 # Download from Hub and run inference
 model = SetFitModel.from_pretrained("setfit-italian-hate-speech")
 # Run inference
-preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
+preds = model(["Lei è una brutta bugiarda!", "Mi piace la pizza"])
 ```
 
 ## BibTeX entry and citation info
@@ -47,3 +60,13 @@ year = {2022},
 copyright = {Creative Commons Attribution 4.0 International}
 }
 ```
+
+```bibtex
+@inproceedings{del2017hate,
+  title={Hate me, hate me not: Hate speech detection on facebook},
+  author={Del Vigna12, Fabio and Cimino23, Andrea and Dell’Orletta, Felice and Petrocchi, Marinella and Tesconi, Maurizio},
+  booktitle={Proceedings of the first Italian conference on cybersecurity (ITASEC17)},
+  pages={86--95},
+  year={2017}
+}
+```