CS doctoral candidate Di Chen and CS Professor Carla Gomes have written a paper that aims to point-up and correct biases that appear in the data gathering of citizen scientists. In their paper, of which Chen is the lead author, “Bias Reduction via End-to-End Shift Learning: Application to Citizen Science,” they propose the Shift Compensation Network (SCN)—an “end-to-end learning scheme which learns the shift from the scientific objectives to the biased data while compensating for the shift by re-weighting the training data.” At the AAAI conference on Artificial Intelligence, convened in Honolulu from January 27-February 1, 2019, Chen and Gomes present their findings.
See also Melanie Lefkowitz’s article—“AI adjusts for gaps in citizen science data”—in the Cornell Chronicle (January 25, 2019)—where she discusses the specific application of this new SCN scheme, in particular, on data gathering of bird sightings. As Lefkowitz notes: “Chen and Gomes tested several models and found their deep learning algorithm to be more effective than other statistical or machine learning models at predicting where bird species might be found.”