cardiffnlp/twitter-roberta-large-emotion-latest

This is a RoBERTa-large model trained on 154M tweets until the end of December 2022 and finetuned for emotion classification (multilabel classification) on the TweetEmotion dataset of SuperTweetEval. The original Twitter-based RoBERTa model can be found here.

Labels

"id2label": { "0": "anger", "1": "anticipation", "2": "disgust", "3": "fear", "4": "joy", "5": "love", "6": "optimism", "7": "pessimism", "8": "sadness", "9": "surprise", "10": "trust" }

Example

from transformers import pipeline
text= "@user it also helps that the majority of NFL coaching is inept. Some of Bill O'Brien's play calling was wow, ! #GOPATS"

pipe = pipeline('text-classification', model="cardiffnlp/twitter-roberta-large-emotion-latest", return_all_scores=True)
predictions = pipe(text)[0]
predictions = [x for x in predictions if x['score'] > 0.5]
predictions
>> [{'label': 'anger', 'score': 0.927680253982544},
 {'label': 'disgust', 'score': 0.895420491695404},
 {'label': 'joy', 'score': 0.9239692687988281},
 {'label': 'optimism', 'score': 0.6795405745506287}]

Citation Information

Please cite the reference paper if you use this model.

@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}
}