IDRISI is the largest-scale publicly-available Twitter Location Mention Prediction (LMP) datasets, in both English and Arabic languages. It contains 41 disaster events of different types (e.g., floods, fires). Annotations include tagged LMs in posts, location types (e.g., cities, streets), links to OSM toponyms, & usefulness of features for LMD.

A Multitask Framework for Present and Absent Keyphrase Generation using Knowledge Graphs

An approach to solve the Kaggle Competition, Natural Language Processing with Disaster Tweets

Natural Language Processing with Disaster Tweets

Classification of Disaster Tweets as REAL or FAKE using Machine Learning

Utilizing Natural Language Processing (NLP) to analyze and classify tweets for detecting disaster-related content.

Kaggle real or not disaster tweets classification using FastText.

My Kaggle submission notebook - 83.8% Accuracy 🤟 (Top 8%)

A machine learning project that classifies disaster-related tweets using Natural Language Processing techniques. The study compares Naive Bayes and Logistic Regression models to identify whether a tweet describes a real disaster event.

Creating a model for the Kaggle competition: https://www.kaggle.com/competitions/nlp-getting-started/overview

🚀 Welcome to my Kaggle submission for "Natural Language Processing with Disaster Tweets." In this challenge, we explore tweets, using NLP to distinguish between those about real disasters and those that aren't. The goal is to build a robust model for accurate disaster-related tweet prediction. 🏆 Impressive F1 score of 0.79926 on the public leader

This project was developed for the Natural Language Processing with Disaster Tweets Kaggle competition

[FIUBA] 75.06/95.58 Organización de Datos 2020 - Trabajo Práctico 2 - Machine Learning

Integrates data from various sources to provide comprehensive insights into floods, leveraging spatial analysis, advanced summarization, and real-time data visualization.

Classifier for predicting if a tweet is about real disasters or not.

(Re) Introduction to Tensorflow Natural Language Processing

A comparative study on different word vectorization techniques and machine learning algorithms on disaster tweets.

Ein Machine-Learning-Projekt, in dem ich Tweets mit NLP-Techniken bereinigt, vektorisiert und mit verschiedenen Modellen klassifiziert habe. Verglichen wurden LogReg, Random Forest und MLP, inklusive Validierung und Hyperparameter-Tuning.