erYash15/Real-or-Not-NLP-with-Disaster-Tweets
Sentiment analysis of the dataset of twitter disaster tweets and predicting is it the actual disaster or metaphorically expressed as disaster.
Implements comprehensive text preprocessing including URL/emoji/HTML tag removal, stopword filtering, and stemming, then benchmarks multiple classical ML models (Logistic Regression, Naive Bayes variants, SVM, Random Forest) against deep learning architectures (perceptrons with dropout/batch normalization) using TensorFlow/Keras. Evaluates all approaches on micro/macro F1-scores and accuracy, finding SVM and ReLU+Adam+Dropout configurations most effective for this binary classification task.
No commits in the last 6 months.
Stars
8
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
Jan 31, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/erYash15/Real-or-Not-NLP-with-Disaster-Tweets"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
wri-dssg-omdena/policy-data-analyzer
Building a model to recognize incentives for landscape restoration in environmental policies...
IliaZenkov/NLP-keras-nltk-lime
Classification of tweets pertinent to disaster events. NLP basics with a focus on text...
wang0324/TwitterRelevanceClassification
Classifies if a tweet is relevant to a disaster or not
kushv16/Disaster_Tweets_Analysis
Project based on Natural Language Processing to identify if the given tweet indicates a disaster.
prdai/disaster-tweet-classifier
NLPrescue is an advanced Natural Language Processing system designed to detect and classify...