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.

Downloads last month
12
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Kwaku/social_media_sa