Inspiration
We want to create a faster way to send users alerts as fast as possible by using social media, mainly using twitter since the news of crimes or natural disasters will be mentioned faster than local news.
What it does
AlertMe uses Twitter as a data source to retrieve events in near-real time.
AlertMe can detect emergencies such as natural disasters, active shooters, and a multitude of other anomalies. This is accomplished by using Twitter's PowerTrack API to pull tweets in real-time and filter them based on keywords we have predefined.
The next step is to identify whether the tweets are indeed emergencies or false positives. Our team used IBM Watson's Natural Language Understanding API to analyze the sentiment of the tweets. If a tweet was not deemed as a false positive, then it got forwarded to our delivery system.
Our delivery system was powered by Twilio's SMS API and sent out SMS notifications to users who signed up for the AlertMe service.
How we built it
We use python and SQL for the back-end, database and bots to check for follower of the twitter account and the to interact with the database. HTML and CSS for front-end. APIs we used is from twitter, twilio, IBM Watson. Database using MySql.
Challenges we ran into
Trying to connect python to HTML and have it work as a complete program
Accomplishments that we're proud of
Finally get to understand the structure of a website with front-end and back-end. Not feeling to competitive while working on the project and to be able to teach each other while having a good time
What we learned
Takes a lot of trial and error to get things to work and learn something new. Finally get to understand how useful APIs can be while working on a project.
What's next for cruzhacks2019
Hopefully to expand to different communities and locations to provide quick notifications of danger and minimize the false positives of events.
Log in or sign up for Devpost to join the conversation.