Update README.md

README.md

@@ -1,7 +1,28 @@
+---
+license: mit
+datasets:
+- cardiffnlp/super_tweeteval
+language:
+- en
+pipeline_tag: text-classification
+---
 # cardiffnlp/twitter-roberta-base-latest-tweet-sentiment
 
-This is a [RoBERTa-base](https://huggingface.co/cardiffnlp/twitter-roberta-base-2022-154m) model fine-tuned on [tweet_sentiment](https://huggingface.co/datasets/cardiffnlp/super_tweeteval).
+This is a RoBERTa-base model trained on 154M tweets until the end of December 2022 and finetuned for sentiment analysis (target based) on the _TweetSentiment_ dataset of [SuperTweetEval](https://huggingface.co/datasets/cardiffnlp/super_tweeteval).
+The original Twitter-based RoBERTa model can be found [here](https://huggingface.co/cardiffnlp/twitter-roberta-base-2022-154m).
 
+# Labels
+<code>
+  "id2label": {
+    "0": "strongly negative",
+    "1": "negative",
+    "2": "negative or neutral",
+    "3": "positive",
+    "4": "strongly positive"
+  }
+</code>
+
+## Example
 ```python
 from transformers import pipeline
 text= 'If I make a game as a #windows10 Universal App. Will #xboxone owners be able to download and play it in November? @user @microsoft'
@@ -11,4 +32,17 @@ text_input = f"{text} </s> {target}"
 pipe = pipeline('text-classification', model="cardiffnlp/twitter-roberta-base-latest-tweet-sentiment")
 pipe(text)
 >> [{'label': 'negative or neutral', 'score': 0.9601162672042847}]
+```
+
+## Citation Information
+
+Please cite the [reference paper](https://arxiv.org/abs/2310.14757) if you use this model.
+
+```bibtex
+@inproceedings{antypas2023supertweeteval,
+  title={SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research},
+  author={Dimosthenis Antypas and Asahi Ushio and Francesco Barbieri and Leonardo Neves and Kiamehr Rezaee and Luis Espinosa-Anke and Jiaxin Pei and Jose Camacho-Collados},
+  booktitle={Findings of the Association for Computational Linguistics: EMNLP 2023},
+  year={2023}
+}
 ```