Data Science for the Common Good (DS4CG) is a summer program that trains aspiring data scientists to work on real-world problems that benefit the common good. Join the 2023 cohort of DS4CG fellows for lunch and a poster session where you will get to learn about each project directly from students.
Lunch will be provided.
RSVP requested but not required. Please RSVP so that we make sure to order enough food. RSVP here: https://docs.google.com/forms/d/e/1FAIpQLSc5jWtS6FDcO_W1NgvbBMAXPtR2nfPSDL8x-a5pd96s5t9-ag/viewform
DS4CG 2023 Projects:
Media Cloud Youtube Extreme Speech
The team analyzed ways that extreme and hateful speech could be detected on YouTube, creating an evaluation dataset of YouTube videos from specific types of content creators and comparing how features from the audio and transcribed text in a video can be used to flag extreme speech using machine learning.
Media Cloud Byline Extraction
Media Cloud's Search tool provides researchers with a way to analyze digital news content, seeing what topics are being covered around the globe, but due to the varied style and content of online news articles, they have not yet been able to include author information on their platform. The DS4CG project takes the first step to adding that feature, creating a dataset, evaluation framework and benchmarking the performance of existing tools for author and byline extraction.
Co-Insights
This project completed a longitudinal analysis of the #StopAsianHate Twitter hashtag, investigating who used it, what topics of discussion and offline events it was associated with, supporting Co-Insights' broader goal of studying the spread of misinformation in Asian-American digital communities and developing culturally appropriate interventions.
Red Cross
The focus of the second summer of our partnership with the Red Cross was to integrate DISCount, UMass Computer Vision Lab's new approach to estimating counts in object detection, into the Red Cross' workflow for counting damaged buildings after a disaster, saving time and effort in determining the disaster's impact and severity, and ultimately helping the Red Cross deliver aid more quickly.
Roost Canada
The Roost Canada project spun off of an ongoing effort in the US to scale a specialized detection algorithm that identifies roosts of birds from RADAR data. This research plays a crucial role in studying declining bird populations. Supported by Environment and Climate Change Canada, who supplied the RADAR datasets, the project's primary challenge was to effectively adapt and process the Canadian data formats to the detection algorithm and qualitatively analyze the performance of the algorithm.
Massachusetts Department of Asset Management and Maintenance
DCAMM is responsible for managing resources in various state buildings like state hospitals, prisons, universities, community colleges, office buildings. This project analyzed 5 year energy usage of 279 utility meters in 23 academic buildings. Using this data, time-series prediction models were developed for 12-month energy consumption of various utilities (electricity, steam, natural gas, water) by building. Prediction is the first step towards data-driven efficient management of energy resources and energy conservation.
Unity
Unity is a collaborative, multi-institutional high-performance computing cluster, primarily used for research computing. The Unity project focused on generating useful metrics and analysis for Unity by building a pipeline to a database that could power a live dashboard for Unity’s admin staff. Metrics included unnecessarily idle GPUs, daily and weekly node usage, total resource usage, and wait time. Additionally, a prediction model for wait time at job submission time was built.