During the summer of 2015 my KDD class at UNC Charlotte mined the International Shark Attack Database for knowledge. The database was integrated with data on weather, water, population, crabs, moon phases and population to learn when sharks attack. Some interesting association rules were discovered. During the summer of 2016 the study was extended with a small class devoted to the research. Additionally, student Christian Watts at Catawba College also participated in the study during the Fall 2015 semester.
Please find information on the research at: https://github.com/AKDDResearch/Shark-Attack
Statement of Purpose:
The objective of this research is to improve our understanding of the presence of sharks during tourist seasons in middle Atlantic and south eastern coastal waters, specifically North Carolina and South Carolina. Our study will focus on the analysis of existing data from the International Shark Attack database, weather and water data from NOAA, calculated moon phase dates, fish, crab and turtle populations. The quantitative analysis on this data will lead to new and interesting knowledge that will provide the basis for an app providing advanced information on the likelihood of sharks in coastal waters where tourists swim, surf and wade.
An additional focus of this research is to analyze social media activity relative to shark presence. Tweets will be mined with specific data ranges and locations in order to assess social media activity with respect to shark sightings, attacks, and even activities that are related to shark presence such as schools of fish. Once the nature of this activity is understood, a standardized way to tweet will be promoted with interested and strategic partners in order to ultimately provide an additional feed to the app described above.