Kwaku/social_media_sa

Social Media Sentiment Analysis Model

This is a fine-tuned version of the Distilbert model. It's best suited for sentiment-analysis.

Model Description

Social Media Sentiment Analysis Model was trained on the dataset consisting of tweets obtained from Kaggle."

Intended Uses and Limitations

This model is meant for sentiment-analysis. Because it was trained on a corpus of tweets, it is familiar with social media jargons.

How to use

You can use this model directly with a pipeline for text generation:

>>>from transformers import pipeline

>>> model_name = "Kwaku/social_media_sa"
>>> generator = pipeline("sentiment-analysis", model=model_name)
>>> result = generator("I like this model")
>>> print(result)

Generated output: [{'label': 'positive', 'score': 0.9494990110397339}]

Limitations and bias

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.