README.md

---
language:
- en
license: mit
datasets:
- cardiffnlp/super_tweeteval
pipeline_tag: text-classification
---
# cardiffnlp/twitter-roberta-large-topic-sentiment-latest

This is a RoBERTa-large 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-large-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'
target = "@microsoft"
text_input = f"{text} </s> {target}"

pipe = pipeline('text-classification', model="cardiffnlp/twitter-roberta-large-topic-sentiment-latest")
pipe(text)
>> [{'label': 'negative or neutral', 'score': 0.8927537798881531}]
```

## 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}
}
```