What is Litics360?
Litics360 is a voter-to-election campaign communication web and mobile app that allows political campaigns to deliver and engage their message to various sets of audiences, such as those who maybe uninformed about the issues that they are proposing to combat.
Why build this?
In the US a citizen is required to register to vote and is federally mandated to declare their affiliated party in all states with the exception of North Dakota. This does not necessarily mean they will vote for that particular party every year. In states such as Ohio, a voter's registered party is public data.
A lot of research goes into voter-lead generation and AI-powered methods to classify whether or not a registered voter will actually vote for their party in any given election.
However, most of this research is done for proprietary applications for a lot of past political election campaign (or PECs), and therefore not academically available to the public in most cases.
How was it developed?
Developing this requires a four-stages of prototyping and development before the actual deployment. Currently, it is in the first stage of prototyping and development.
What's the benefit?
It will allow campaigns to minimize confrontational cold calling and door knocking. Rather they'll be able to use their resources and funding appropriately to engage the right audience through data-driven models.
Voters will be able to access data about all political candidates uniformly. They'll also be able to engage campaign staff if they choose to – using the app by participating in polls, messaging directly with campaigns, among many other interactive methods.
Overall, it will allow election campaigns to reach their particular audience, and voters will have the chance to be well-informed before casting their vote in an election.
ICDATA conference presentation
CSCE'20 | July 27, 2020 | Las Vegas, NV, USA
Presentation live recording:
GLDS'20 | May 2020 | Erie, PA, USA
The academic paper was completed as a part of my master of science in data science program, department of Computing and Information Science at Mercyhurst University. The paper was first published in Proceedings of the Third Annual Great Lakes Data Science Symposium by Mercyhurst University.
Springer Nature – Book series | October 2020 | USA
The academic paper was accepted to be published in the Springer Nature - Book Series: Transactions on Computational Science & Computational Intelligence, as a part of the 2020 World Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE'20), hosted by American Council on Science and Education.