Skip to content

This is a getting started competition of predicting whether a tweet is actually referring to real disasters.

Notifications You must be signed in to change notification settings

buddhadeb33/Real-or-Not-NLP-with-Disaster-Tweets

Repository files navigation

Real-or-Not-NLP-with-Disaster-Tweets

Competition Description

Twitter has become an important communication channel in times of emergency. The ubiquitousness of smartphones enables people to announce an emergency they’re observing in real-time. Because of this, more agencies are interested in programatically monitoring Twitter

Here We have perfromed some basics operation in this project which is really easy to understand.

  • Basic exploration
  • Keywords
  • Locations
  • Clean up textHere we clean up the text column by:
  1. Making a 'clean' text column, removing links and unnecessary white spaces
  2. Creating separate columns containing lists of hashtags, mentions, and links
  • Text statistics
  • Unigrams and bigrams
  • Encoding and Vectorizers
  • Simple model
  • Evaluate and improve our model

About

This is a getting started competition of predicting whether a tweet is actually referring to real disasters.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published