← Resource library

Tool

Twitter-RoBERTa sentiment model (Cardiff NLP)

An English RoBERTa sentiment classifier with negative, neutral and positive labels, pretrained on tweets and fine-tuned on TweetEval.

What is reported

A downloadable baseline for comparison with LLM labels; pin a model revision and validate it on your corpus.

Before you use it

Designed for English Twitter-style text. Performance may change with time, genre or population; do not assume transfer to Chinese.

Sources and review

Original source ↗

Source checked · Not tested by this site

Checked the public primary-source description; this site has not independently tested the resource.

Evidence / source record ↗

License and reuse

Model card: CC BY 4.0. Hosting or inference services may charge separately.

License source ↗

A license note is not a license audit. Open source does not guarantee free hosting, model access or commercial reuse.

Related resources