emotion_text_classifier LLM Model

Introduction

The Emotion Text Classifier is a fine-tuned version of the DistilRoBERTa-base model designed to classify emotions in text data. It is specifically optimized for analyzing dialogue from media such as Netflix shows or movies, predicting six Ekman emotions—anger, disgust, fear, joy, sadness, surprise—and a neutral class.

Architecture

The model is based on the DistilRoBERTa-base, a transformer architecture known for its efficiency and performance in natural language processing tasks. This particular version has been fine-tuned with datasets that include dialogues from the Friends TV show, among others, enabling it to effectively determine emotional context in text.

Training

The Emotion Text Classifier was initially trained on several datasets, including Crowdflower (2016), Emotion Dataset (Elvis et al., 2018), GoEmotions (Demszky et al., 2020), ISEAR (Vikash, 2018), MELD (Poria et al., 2019), and SemEval-2018 EI-reg (Mohammad et al., 2018). Fine-tuning was performed on the Emotion Lines dataset from Friends, enhancing its ability to discern emotions in conversational text.

Guide: Running Locally

Install Transformers: Ensure you have the transformers library installed.
```
pip install transformers
```

Load the Model: Use the transformers library to load the model and create a sentiment analysis pipeline.

from transformers import pipeline
classifier = pipeline("sentiment-analysis", model="michellejieli/emotion_text_classifier")

Classify Text: Input text to classify emotions.
```
classifier("I love this!")
```
Example output: {'label': 'joy', 'score': 0.9887555241584778}
Cloud GPUs: For efficient processing, consider using cloud-based GPU services like AWS EC2, Google Cloud Platform, or Azure.

License

Please refer to the model's documentation or its hosting platform for specific licensing information. For inquiries, contact michelleli1999@gmail.com.

More Related APIs in Text Classification