Research team explores history with cutting-edge technology
Zach Haala ’23 and history professor Charlie Goldberg noticed an anomaly in their data. Using artificial intelligence (AI), the two had tracked the presence of smiles over nearly 80 years and thousands of photographs of Bethel. As expected, smiles have become more common in photos over time, matching the cultural changes after WWII. But then, in the 1960s, the number of smiles declined. At first they were puzzled. Then Haala noticed that this is when the directories started to contain more sports photos. “It’s a good example of how data spits things out, but data needs to be interpreted,” Goldberg says. In the 1960s, male athletes rarely smiled in photos, and big teams like men’s football and basketball affected the research results. For Goldberg, it shows the promise of using AI to explore history and also raises questions. “What do we do with this stuff then?” How do we interpret it and use it to tell a human story, which historians do? Goldberg asks.
These are the kinds of questions Goldberg and Haala explored in the “Is a picture worth a thousand data points?” Research project. AI-Driven Machine Learning in Digital Humanities Analyzes ”. They were part of the 2021-2022 student-faculty teams to receive an Edgren scholarship to support their research.
To some, the story may seem like a long way from artificial intelligence and programming. But Goldberg also leads Bethel’s Digital Humanities program, which explores cutting-edge, forward-looking methods to apply to history, literature, and philosophy. While teaching advanced digital humanities last year, Goldberg came up with the idea of using AI to study history. The class explores advancements in AI technology and how it is often a double-edged sword – it offers a lot of opportunities with data and research, but it also leads to things like deepfakes – or fake photos or videos created using AI, often depicting world leaders or celebrities. Goldberg wanted to go further. As a historian, he uses data – usually text or photos – to search for patterns. He was interested in using AI to isolate the same patterns that historians are exploring, but on a larger scale, and wanted to see how well AI could recognize the same patterns in the photos that historians are looking for. He knew he needed a student who was highly skilled in coding and programming, and who was also willing to dive into the deep end and take risks. Enter Haala, who has a triple specialization in computer science: software project management, software engineering and digital humanities, and he had followed advanced digital humanities.