From Bedtime Stories to College Stories
Tim Tangherlini, a professor at UCLA in the Scandinavian Section, always liked stories and storytelling. His grandmother’s sister, a raconteur, often entertained Tangherlini with fascinating Danish fairytales she knew from her childhood growing up in late 19th century Denmark.
In his high school and early college careers, he believed he was going to major in geography and become a cartographer. Much to his dismay, however, Harvard University did not have a geography department, and so he chose computer science/applied math.
Yet, this choice of major did not last very long. “I realized very quickly that applied math was really hard, and I found some solace in classes in folklore. I saw it as the history and literature of the common man,” he said.
Diverse Interests
Since graduating from Harvard, Tangherlini has published on folklore, literature, film and critical geography. His geographic areas of interest include the Nordic region and Korea. Since his mom is a Dane, Tangherlini grew up speaking Danish and pursued this interest in graduate school with medieval studies. After his second year, Tangherlini’s inquisitive mind prompted him to apply to a program that sent him to Korea – a program whose main qualifying criteria was that the applicant knew nothing about Asia. His time in Korea was spent working at the National Folklore Museum studying shamanism and political aspects of folk culture.
Currently, Tangherlini’s work is focused on applying computational methods to the humanities. He first became intrigued by this subject while earning his Ph.D. from Berkeley.
Ahead of the Times
At Berkeley, Tangherlini picked up a project focused on the automated analysis of the Old Norse language that he had started as an undergraduate. What he thought would be an easy project turned out to be a project he just finished last year – about 30 years later. This interest in computational approaches to the humanities has been a recurring theme in his work ever since.
Tangherlini’s project utilized big data to analyze folklore collections. His dissertation, which included 125 storytellers and 1,500 stories, relied on statistical methods that would allow for the recognition of patterns in stories. His approach was revolutionary in that it looked at folklore as a collection of stories rather than as isolated, disconnected ones.
Tangherlini finalized his thesis in 1992, just before the era of big data, so he found himself ahead of the times. During this period, computational approaches to humanistic material were not a common way of thinking. Therefore, it wasn’t that his approach was poorly received, but that it wasn’t received at all. This did not impede his progress, however, as he recognized the value of his findings and was convinced he could use them for something important.
And he was right. Tangherlini’s continued research in this arena would later enable a large collection of folklore to be seamlessly organized into a database and categorized by story topic, storyteller, and location.
Computational Folkloristics
In the early 2000s, Tangherlini picked up where he had left off and started to work on the idea he had first conceptualized while at Berkeley – leveraging statistical and algorithmic methods to study a large quantity of cultural texts.
With this approach, termed computational folkloristics, tens of thousands of stories could be organized and classified, tremendously easing the job of the researcher. Tangherlini also realized he could use computational methods, such as machine learning, to identify important patterns in the texts.
Interdisciplinary Research
As a humanist working among computer scientists and mathematicians, Tangherlini has learned about and exchanged interesting approaches, data, and problems. Tangherlini is very fond of the support received from the university as a whole, as well as the Office of the Vice Chancellor for Research, and IDRE. “The whole research infrastructure has been pushing this type of ‘Let’s take advantage of the power that is in the intellectual possibilities here on campus.’”
Once he started thinking in an interdisciplinary manner, he was able to solve problems across various disciplines and uncover answers he wouldn’t have been able to otherwise.
A Publication-generating Machine
His proudest accomplishment, Danish Folktales, Legends, and Other Stories, is a collection of Danish folklore that is accompanied by a data portal, called Danish Folklore Nexus, which allows users to access the richest collection of Danish folklore in the English language. In recent years, this software has been his main area of focus, and it allows an individual to see all the places associated with a particular story, an aerial model view, historical maps, the text in English, the original Danish text, annotations, bibliographic references, and even the actual manuscript.
Tangherlini says one of his happiest moments was when a student walked in bleary-eyed saying, “I hate you. I opened your website and all I’ve been doing is reading stories.” This is exactly what he wants – for users to get lost in the collection and make new discoveries just as he did.
Surprising Discoveries
The robust software has allowed Tangherlini to make many important connections. As he began to look at places associated with certain types of stories, statistically significant evidence pointed to a hotspot in Denmark for witch and ghost stories that had echoed for centuries. He found that most of the stories failed to mention that a Catholic monastery associated with witchcraft was stationed where the last witch-burning took place, which explained why these kinds of stories emerged from the area.
This software program also allowed Tangherlini to trace the paths of storytellers and discover significant patterns. For example, his findings showed that males tended to follow the paths towards the marketplace, while women tended to stay close to the farm and neighborhood – reflecting the gender roles in place at the time.
Computational methods of analyzing folklore always bring up new questions. “It’s a publication-generating machine,” he said.
Modern Storytelling
Today, Tangherlini is studying storytelling in the context of the age of the Internet. He is looking at how stories circulate on the internet and in the media and how those stories affect people. Working alongside an electrical engineering professor and a professor from the School of Public Health, Tangherlini is analyzing several forums where mothers are engaged in a debate about vaccinations. By aggregating signals of opinions on vaccinations using computational methods, Tangherlini hopes to discover how differences in signals circulate and influence conversations and behaviors.
“I want to see if we can get this to scale and address issues that are a great concern to different communities in the 21st century.”