CSUN Faculty Member Awarded Grant to Develop Literature Analysis Software

Scott Kleinman

Scott Kleinman

California State University, Northridge English professor Scott Kleinman is writing a tale of literature and computer science.

Awarded a $60,000 grant from the National Endowment for the Humanities, Kleinman is working to further develop Lexos, a software tool that aids in the analysis and interpretation of literature. Lexos makes computational text analysis more easily accessible to scholars and students in the humanities, who may not have the time or resources to learn sophisticated computerized coding techniques.

Kleinman co-directs the grant with colleagues Michael Drout and Mark LeBlanc from Wheaton College in Massachusetts, where the Lexos software resulted from a 2007 Lexomics research project. Kleinman joined the project in 2010, working on the development of research techniques and the design of software tools to support the research.

Kleinman said Lexos identifies patterns of word usage that might be missed by traditional reading. The program simplifies the many steps in text analysis — such as the tedious work of “scrubbing” the elements of content including punctuation marks, capital letters and articles — and running the texts through statistical algorithms. It is a comparative tool that allows scholars and students to create graphs and visualize similarities and differences within or between literary texts.

“Typically, scholars would have to employ separate tools for each of these steps, or possibly even write the code themselves,” Kleinman said. “Lexos provides an integrated workflow for users to perform all these functions in one place.”

Lexos can be used to analyze ancient languages, Old English and even foreign languages such as Chinese. It can help scholars attribute authorship, identify an author’s source material and find evidence of collaboration and translation — especially for texts that were written anonymously. Such texts might include the ancient tale of “Beowulf,” where Lexos helps test hypotheses about the diverse sources of the poem.

“More recently, scholars using this kind of technology were able to reveal that novels published under the name of Robert Galbraith were written by J.K. Rowling, author of the ‘Harry Potter’ novels,” Kleinman said.

Kleinman noted that people should not expect Lexos to replace solid literary scholarship and critical reading, however.

“Part of the grant will be used to explore how Lexos can address the tension between quantitative and computational approaches to text analysis and the traditions of theoretical and cultural criticism that typically dominate the humanities,” Kleinman said. “The growing ease with which we can manipulate texts computationally is likely to increase this tension and will require us to examine closely our premises about the relationships between source materials and the results of computational experiments.”

The practice of using technology in the humanities is part of an emerging field called “digital humanities,” Kleinman said. Though scholars have been using computers to study literature since the 1940s, this methodology is a fairly new introduction to the classroom.

Only recently has technology become accessible enough so that students can learn digital humanities approaches, he said. However, many students are initially intimidated by the new approach, he added.

“One of the challenges I must overcome early on with students is the myth that English majors not only don’t, but can’t, use computational and statistical techniques,” Kleinman said. “They quickly see that these methods are empowering.”

The digital humanities approach provides a fresh perspective on literary studies and lets students combine the traditional communication skills in which humanities majors excel with technical skills that are in demand in the job market, Kleinman said.

The CSUN professor himself does not have a background in computer science. He said he picked up the skills while completing his doctoral degree in Anglo-Saxon, Norse and Celtic at Cambridge University in England. He was inspired to continue learning coding techniques after taking over management of CSUN’s Department of English website. In 2010, he started an initiative in the College of Humanities to incorporate digital humanities in teaching and research at CSUN.

He also is continuing to direct a $200,000 National Endowment for the Humanities grant called the Archive of Early Middle English, which will make digital editions of medieval English manuscripts accessible to the public.

“One moment, I’m immersed in the poetry of ancient language,” Kleinman said. “And in the next moment, I’m immersed in the poetry of code.”

Lexos is currently available online and is free to the public. To use Lexos, go to http://lexos.wheatoncollege.edu.

, , ,