Generating Stories From Archived Collections

Abstract

With the extensive growth of the Web, multiple Web archiving initiatives have been started to archive different aspects of the Web. Services such as Archive-It exist to allow institutions to develop, curate, and preserve collections of Web resources. Understanding the contents and boundaries of these archived collections is a challenge, resulting in the paradox of the larger the collection, the harder it is to understand. Meanwhile, as the sheer volume of data grows on the Web, "storytelling" is becoming a popular technique in social media for selecting Web resources to support a particular narrative or "story". We address the problem of understanding archived collections by proposing the Dark and Stormy Archive (DSA) framework, in which we integrate "storytelling" social media and Web archives. In the DSA framework, we identify, evaluate, and select candidate Web pages from archived collections that summarize the holdings of these collections, arrange them in chronological order, and then visualize these pages using tools that users already are familiar with, such as Storify. Inspired by the Turing Test, we evaluate the stories automatically generated by the DSA framework against a ground truth dataset of hand-crafted stories, generated by expert archivists from Archive-It collections. Using Amazon's Mechanical Turk, we found that the stories automatically generated by DSA are indistinguishable from those created by human subject domain experts, while at the same time both kinds of stories (automatic and human) are easily distinguished from randomly generated stories.