I’m currently working on a project Success of Books and Authors in collaboration with Burcu Yucesoy, Onur Varol, Prof Tina Eliassi-Rad and Prof Albert-László Barabási. We are interested in why some books and authors become successful.
We recently published our first paper in this project in EPJ Data Science. We analzed the New York Times Bestseller data and found a lot of interesting pattern in it. We also have an interactive visualization website and it’s fun to play with!
We are currently working on the prediction of book sales prior to the publication of a book. I have shown part of our results at various conferences:
Fairness in Machine Learning has become an arising topic recently. With increasing application of Machine Learning algorithms in daily lives, people have found out those algorithms can be “unfair” since the data is biased. We recently started a project “Just ML” with Prof. Tina Eliassi-Rad and Dr. Onur Varol, trying to quantify two potential sources of “unfairness”: in-group favortism” and “out-group prejudice” using the COMPAS data. The project is still in its early stage.
As a continution project of Success of Books and Authors, we set out to explore the career of artists and try to reveal patterns behind their success. Our current idea is to build higher-order networks based on artists career (exhibition) to see whether there are interesting characteristics of this network. We also have the idea to use machine learning to analyze art pieces themselves to see how art envolve over time.
Started as a course project, I initially collaborated with Syed Haque trying to understand music from the sheet music purely. We built the one-step note transition matrix for music pieces and use these matrices to cluster music; we found the matrices themselves are very distinct for Bach’s Fugue and the clusters we found aligns with music era. Check our paper!
During the Santa Fe Summer School, I pitched this music related project and collaborated with Josefine Brask, Ricky Laishram and Carlos Marcelo, trying to understand music by building higher-order networks. We came up with several metrics to quantify different charateristics of music from those higher-order networks such as “branchingness”, “repetitiveness”, etc., and try to connect them with different music genres. Here are the related slides!