CoolFace
Modelpublic

michelleli99/emotion_text_classifier

sourceHugging Faceupdated 3y agoView on Hugging Face
151likes54kdownloads
Model Card

Fine-tuned DistilRoBERTa-base for Emotion Classification 🤬🤢😀😐😭😲

Model Description

DistilRoBERTa-base is a transformer model that performs sentiment analysis. I fine-tuned the model on transcripts from the Friends show with the goal of classifying emotions from text data, specifically dialogue from Netflix shows or movies. The model predicts 6 Ekman emotions and a neutral class. These emotions include anger, disgust, fear, joy, neutrality, sadness, and surprise.

The model is a fine-tuned version of Emotion English DistilRoBERTa-base and DistilRoBERTa-base. This model was initially trained on the following table from Emotion English DistilRoBERTa-base:

Nameangerdisgustfearjoyneutralsadnesssurprise
Crowdflower (2016)Yes--YesYesYesYes
Emotion Dataset, Elvis et al. (2018)Yes-YesYes-YesYes
GoEmotions, Demszky et al. (2020)YesYesYesYesYesYesYes
ISEAR, Vikash (2018)YesYesYesYes-Yes-
MELD, Poria et al. (2019)YesYesYesYesYesYesYes
SemEval-2018, EI-reg, Mohammad et al. (2018)Yes-YesYes-Yes-

It was fine-tuned on: |Name|anger|disgust|fear|joy|neutral|sadness|surprise| |---|---|---|---|---|---|---|---| |Emotion Lines (Friends)|Yes|Yes|Yes|Yes|Yes|Yes|Yes|

How to Use

python
from transformers import pipeline
classifier = pipeline("sentiment-analysis", model="michellejieli/emotion_text_classifier")
classifier("I love this!")
python
Output:
[{'label': 'joy', 'score': 0.9887555241584778}]

Contact

Please reach out to michelleli1999@gmail.com if you have any questions or feedback.

Reference

Jochen Hartmann, "Emotion English DistilRoBERTa-base". https://huggingface.co/j-hartmann/emotion-english-distilroberta-base/, 2022.
Ashritha R Murthy and K M Anil Kumar 2021 IOP Conf. Ser.: Mater. Sci. Eng. 1110 012009