The team, led by computer science professor Jure Leskovec, created a system called "Data Wrangler" that can automatically clean and transform raw data into a format that is more accessible and usable.
"Raw government data is often messy and difficult to understand," Leskovec said. "Our goal was to create a tool that could make this data more accessible to people who want to use it for research, journalism, or other purposes."
Data Wrangler works by using a variety of machine learning and natural language processing techniques to identify and correct errors in the data, as well as to extract meaningful information from the text.
The system can be used to analyze a wide variety of government data, including financial records, crime statistics, and environmental data.
Leskovec and his team have already used Data Wrangler to analyze several large datasets, including the U.S. Census Bureau's American Community Survey and the New York City Police Department's stop-and-frisk data.
The results of these analyses have been published in several academic journals and have been used by journalists and policymakers to inform their work.
"We believe that Data Wrangler has the potential to revolutionize the way that people use government data," Leskovec said. "By making this data more accessible and usable, we can empower people to make better decisions about their lives and their communities."
The team's research was published in the journal "Nature Machine Intelligence".
