Twitter RoBERTa-base Sentiment Analysis (safetensors)
This repository contains a safetensors-only version of the model:
cardiffnlp/twitter-roberta-base-sentiment-latest
The model performs sentiment classification on English tweets and predicts the following labels:
- Negative
- Neutral
- Positive
No architectural changes or retraining have been performed. The only modification is the conversion of model weights to the safetensors format.
Original Model
- Training Data: ~124M tweets (2018–2021)
- Task: Sentiment analysis (TweetEval benchmark)
- Reference Paper: TimeLMs
- Original Repository: TimeLMs GitHub
- Demo / Integration: TweetNLP
Label Mapping:
| ID | Label |
|---|---|
| 0 | Negative |
| 1 | Neutral |
| 2 | Positive |
Modifications
- Converted PyTorch weights to
safetensors - Tokenizer and configuration preserved
- No changes to model behavior, labels, or performance
References
@inproceedings{camacho-collados-etal-2022-tweetnlp,
title = "{T}weet{NLP}: Cutting-Edge Natural Language Processing for Social Media",
author = "Camacho-collados, Jose and Rezaee, Kiamehr and Riahi, Talayeh and Ushio, Asahi and Loureiro, Daniel and Antypas, Dimosthenis and Boisson, Joanne and Espinosa Anke, Luis and Liu, Fangyu and Martínez Cámara, Eugenio and others",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-demos.5",
pages = "38--49"
}
@inproceedings{loureiro-etal-2022-timelms,
title = "{T}ime{LM}s: Diachronic Language Models from {T}witter",
author = "Loureiro, Daniel and Barbieri, Francesco and Neves, Leonardo and Espinosa Anke, Luis and Camacho-collados, Jose",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-demo.25",
doi = "10.18653/v1/2022.acl-demo.25",
pages = "251--260"
}