Inspiration At USF’s first Hackathon we decided to visit all the booths, most of the booths had different challenges, and we liked JPMorgan’s “Social for good” challenge, and the first thing that came up to our mind was assembling a program that uses social media and data mining to save lives. What it does Our program filters tweets containing words related to natural disaster and graphs them based on frequency, this can help emergency teams to decide which areas need more attention. How we built it The tweets were gathered from the Twitter API using Tweepy and we wrote a python code extracting live data.Then we used Pandas and Matplotlib to process the data. Challenges we ran into Processing raw data Unstructured data is hard to process. People use social media for everything from memes to emergencies, and it can be difficult to find catch-all keywords to look for. Instead, we focused on detecting potential rescue requests to send to users, combining low-latency computational filtering with human validation.