Take a glance through recent news or social media and you would be hard-pressed not to see mentions of chatbots and artificial intelligence (AI) methods aimed at generating text, images and other content. Recent work by Eloundou and colleagues (2023) explored the potential impact of these types of generative AI on labor markets, and survey research, specifically was among the top two most impacted industries. Professor Andrew Ng has been cited as saying “AI won't replace human workers, but 'people that use it will replace people that don't.'” Much of the way researchers in the social sciences and survey research are incorporating AI into their workflow involves some type of prompting. Prompt Engineering approaches along with more nuanced fine tuning approaches are being used and refined to better incorporate more robust approaches for AI incorporation into the research process. In this shortcourse we will provide an overview of the emerging field of prompt engineering and illustrate how a prompt engineering approach and problem specification mindset can be useful for maximizing the utility of large language models, specifically, within social science. Concepts and experimental approaches will be illustrated using several real-world, grounded and published work. The shortcourse also incorporates an experiential component that encourages participants to apply basic concepts that we cover in the course in real-time as we work on exercises together in the later part of the course.

This course will count as 4.0 CSS short course hours.