INTERESTS
PROJECTS
- Performed Data-Wrangling on the raw data of the Minecraft testbed game and created a Data Visualization tool to understand the behavior of the player in the game
- Designed and implemented prototype architecture of 2d grid game application to test the hypothesis for different experiment setups that got adapted into the 2d games of other teams of the project
- Developed APIs for different versions of the recommendation model that recommends music for each user using online learning from the data extracted using Spotify API
- Developed music player web application for running experiments on Amazon Mechanical Turk
- Performed experiments on Amazon Mechanical Turk and conducted an analysis to successfully demonstrate the performance of the model for prediction and recommendation tasks
- Worked on the research and implementation of a computational model that mimics the behavior of a non-native speaker of a specific language(L1) to provide a deeper understanding of the problem of learning a second language(L2)
- Implemented model that predicts erroneous choices with no explicit training data of non-native mistakes which can provide a new medium to analyze and develop tools for L2 teaching
- Implemented multiple versions of the Probabilistic Topic Model in Python for the search and exploration of text corpora
- Developed web application for conducting experiments to collect user data and identified distribution parameters of data responsible for high/low co-operative inference
RESEARCH ARTICLES
- Scott Cheng-Hsin Yang, Chirag Rank, Jake Alden Whritner, Olfa Nasraoui, and Patrick Shafto (2020)
Unifying recommendation and active learning for information filtering and recommender systems (Under Review)
- Libby Barak, Scott Cheng-Hsin Yang, Chirag Rank, and Patrick Shafto (2020)
Replicating L2 learning in a Computational Model. Proceedings of the 42th annual conference of the Cognitive Science Society
- Yang, S.,C-H., Anderson, S., Rank, C., Wang, P., Folke, T., & Shafto, P.
Inferring knowledge from behavior in search-and-rescue tasks. (Under Progress)