The U.S. labor market has experienced dramatic changes over the last several decades, including increased wage inequality and shifts in the distribution of jobs over time and across geographic regions. These changes raise questions about the associated changes in the tasks that workers perform and how skills applied to different tasks are rewarded. However, it is difficult to analyze the evolving structure of occupations because of limited availability of data measuring the skill requirements and task content of jobs. Drawing on machine learning techniques, Enghin Atalay and colleagues will extract a variety of job-related elements, including tasks, skills, and technology requirements from a dataset of job vacancies from published newspaper help wanted ads between 1940 and 2000 and online job vacancies posted between 2011-2017. They will study how the task content of occupations has changed from 1960 to 2000 and how these changes have affected earnings; how new technology has transformed the tasks that workers perform, the occupations that workers sort into, and the returns to different skill profiles; how changing patterns of specialization in tasks across local labor markets have influenced productivity and wages; and whether explicit gender discrimination in job ads changed following the passage of the Civil Rights Act of 1964.