Natural Language Processing with Disaster Tweets

Local Chapter Giza, Egypt Chapter

Coordinated byEgypt ,

Status: Completed

Project Duration: 24 Apr 2023 - 24 Jun 2023

Open Source resources available from this project

Project background.

Natural Language Processing (NLP) is a rapidly evolving field of computer science that deals with the interactions between human language and computers. In recent years, NLP has been applied to a variety of real-world problems, including the analysis of social media data during natural disasters. Social media platforms like Twitter are rich sources of real-time information about disaster events, and NLP techniques can be used to extract useful information from the text data generated by users during these events.

The problem.

The analysis of social media data during natural disasters can be challenging due to the sheer volume of data generated and the need to quickly identify relevant information. Additionally, tweets are often short, informal, and contain non-standard language, making them difficult to analyse using traditional NLP techniques. As a result, there is a need for more advanced NLP techniques that can accurately classify disaster-related tweets and extract relevant information in real-time.

The dataset provided for this challenge consists of a collection of tweets that have been labelled as either “disaster” or “not disaster”. The goal is to build a model that can learn to distinguish between the two classes based on the text content of the tweets. The challenge is designed to test participants’ skills in natural language processing (NLP) and machine learning. It requires them to preprocess the text data, perform feature engineering, and build a model that can accurately classify tweets.

Project goals.

The goals of Natural Language Processing with Disaster Tweets research are: - To explore the current state-of-the-art in NLP techniques for disaster tweet analysis, including tweet classification and sentiment analysis. - Text Preprocessing. - Model Development: We will try to apply machine learning, and deep learning models including RNN and Transformers. - Evaluate Model. - Compare the performance of machine learning and deep learning (RNNS and Transformers). - App Deployment.

Project plan.

  • Week 1

    Research previous work and Data Collection

  • Week 2

    Exploratory Data Analysis

  • Week 3

    Data Cleaning

  • Week 4

    Model Development

  • Week 5

    Model Development

  • Week 6

    Model Development

  • Week 7

    Model Analysis and Interpretation

  • Week 8

    App Development

Learning outcomes.

Teamwork, Machine Learning , Deep Learning , NLP , Data Preprocessing

Share project on: