Shifting the Archival Gaze: A Case for Leveraging Computational Methods to Uncover Media History Narratives

Abstract

Abstract Through an interdisciplinary examination of a bourgeoning technology, this essay grapples with the opportunities and challenges of using a type of artificial intelligence called machine learning to catalog and make sense of the unpreceded number of digital materials now available to media historians. The authors—a journalism professor and an AI researcher—describe their recent interdisciplinary efforts to use machine learning to explore a collection of roughly 5.7 million photographic negatives donated to their institution by the Boston Globe. Their work illuminates the tremendous power of emerging computational methods to uncover more complete histories, but it also serves as a reminder that such tools should be used with caution.