This is a fine-tuned version of the Distilbert model. It's best suited for sentiment-analysis.
Social Media Sentiment Analysis Model was trained on the
dataset consisting of tweets obtained from Kaggle."
This model is meant for sentiment-analysis. Because it was trained on a corpus of tweets, it is familiar with social media jargons.
1>>>from transformers import pipeline
2
3>>> model_name = "Kwaku/social_media_sa"
4>>> generator = pipeline("sentiment-analysis", model=model_name)
5>>> result = generator("I like this model")
6>>> print(result)
7
8Generated output: [{'label': 'positive', 'score': 0.9494990110397339}]
This model inherits the bias of its parent,
Distilbert.
Besides that, it was trained on only 1000 randomly selected sequences, and thus does not achieve a high probability rate.
It does fairly well nonetheless.
