Urgency Classifier

Table of Contents:

1. Background and Motivation
2. Dataset
3. Structure
4. Technologies Used and Requirements for Use
5. Difficulties
6. Author Info

1. Background and Motivation

Let's say there are two messages for help – one where a house is in a raging fire, and the other is where someone got a slight burn on their finger. Which call should be responded to and helped with first?

For us humans, this may be an easy decisions to make – for machine learning models however, it is not so simple. To make choices based on "priority" or "urgency" based on text using ML is something that requires a complex natural language processing (NLP) model. Using a ML model with optimal accuracies and efficiency, not only can it sort which messages to be answered first and last, but also save countless lives in extreme scenarios

In this project, we decided to build such ML model: the Urgency Classifier.

2. Dataset

3. Structure

• meeting_notes meetting notes from entire project span (Jan-Apr)
• data data (csv) we used to train model
• models includes trained models

4. Technologies Used and Requirements for Use

5. Difficulties

6. Author Info

• Keerthi Nalabotu (mentor): GitHub
• Sia Patodia (mentor): GitHub goog
• Kiran Garre: GitHub goog
• Hikaru Isayama: GitHub
• Rishab Bora: GitHub goog