Project 9 : Kaggle Natural Language Processing Competition — Part 2
Natural Language Processing with Disaster Tweets Classification part 2.
Sentiment analysis is the automated process of tagging data according to their sentiment, such as positive, negative and neutral. Sentiment analysis allows companies to analyze data at scale, detect insights and automate processes.
Introduction: Business Problem
Description: Now we have created a basic model. The goal now is to iterate on this model by making a good validation dataset. This is an issue of try and error since there is no general way of doing this. Thus we have no insure that we can perform a lot of tests without a long training time.
Evaluation: The evaluation metric for this competition is F1.
Methodology
The project will be executed by completing the following tasks:
- Notebook Setup
- Imports and EDA(Exploritory Data Analysis)
- Training
- Create a validation set
- Initial model
- Use validation set of Part 1
- Improving model
- Huggingface login
- Final model for part 2 notebook
- Saving and Sharing model
- Use the model via pipeline
