Election Polls on Social Media: Prevalence, Biases, and Voter Fraud Beliefs
(DOI and citation coming soon)
CV
Education
- M.S. in Computer Science with Concentration in Data Science, University of Massachusetts Amehrst, 2023
- B.S. in Computer Science with Commonwealth Honors, University of Massachusetts Amehrst, 2021
Work experience
- 2021-2023: Research Data Scientist
- Employer: Socially-Intelligent Media & Systems Lab (SIMs)
- Responsibilities: Principal investigator into research focussed on social media polling and leveraging machine learning and tradsitional statistics to improve election prediction.
- Supervisor: Professor Przemyslaw Grabowicz
- Summer 2023: Machine Learning Engineer
- Employer: Center for Data Science
- Responsibilities: Data Science for the Common Good (DS4CG) is a summer program–managed by the University of Massachusetts, Amherst’s Center for Data Science–that trains aspiring data scientists to work on real-world problems that benefit the common good. I implemented and produced traditional machine learning and Gaussian processes to forecast property emissions data for the Massachusetts Department of Capital Asset Management and Maintenance (DCAMM).
- Supervisors: Purva Pruthi, Erin Bartuska
- 2021: Research Assistant
- Employer: University of Massachusetts, Amherst Computer Vision Lab
- Responsibilities: I created a novel, highly-reliable dataset for rotation and translation estimation using optical flow. Our method outperforms state-of-the-art rotation estimation methods using only video data.
- Supervisor: Professor Erik Learned-Miller
Skills
- Machine Learning: skill in PyTorch, Tensorflow, Sklearn, vectorization, transformers, AWS
- Data Science: linear regression, Gaussian processes, prediction, neural networks, deep learning, and optimization
- Computer Vision: optical flow, SLAM, CNNs, classification, object detection/segmentation, and 3D-deep learning techniques
- Programming: proficiency in Python, R, C, C#, C++, Java, Javascript, Julia, and Jupyter Notebooks
Publications
Analyzing Support for U.S. Presidential Candidates in Twitter Polls
Scarano, S. et al. 2024. Analyzing Support for U.S. Presidential Candidates in Twitter Polls. Journal of Quantitative Description: Digital Media . 4, (May 2024). DOI:https://doi.org/10.51685/jqd.2024.icwsm.4.
Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes
Fabien Delattre, David Dirnfeld, Phat Nguyen, Stephen Scarano, Michael J. Jones, Pedro Miraldo, and Erik Learned-Miller. 2023. Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes