Can a computer carry out sophisticated literary analysis?
Professor and researcher Matthew L. Jockers used a computer to determine influence, patterns in literature.
Yes, we as a society now use computers to analyze large amounts of data. But can a computer parse literature as well as (or better) than a human reader?Skip to next paragraph
Pastor reportedly buys his way onto New York Times bestseller list
'Paddington' movie trailer glimpses at children's book series bear
Goldman Sachs elevator tweeter loses book deal
Characters struggle for sleep in new literary works
Anne Rice and others sign petition urging Amazon to get rid of anonymous comments
Subscribe Today to the Monitor
That’s the question being explored by researcher Matthew L. Jockers, who used a computer to go through more than 3,000 works that were published between 1780 and 1900. According to a piece in The New York Times, Jockers released his findings last year and is about to publish a book compiling it titled “Macroanalysis: Digital Methods and Literary History.”
Based on the computer’s analysis, Jockers, who is a researcher at the Center for Digital Research in the Humanities at the University of Nebraska as well as an assistant professor in the English department, found that Jane Austen (happy birthday, “Pride and Prejudice”!) and “Ivanhoe”’s Sir Walter Scott were the most influential writers of their time.
They were “the literary equivalent of Homo erectus, or, if you prefer, Adam and Eve,” Jockers told The New York Times.
The researcher said that using such analysis can allow society to analyze literature in a larger way than ever before.
“Traditionally, literary history was done by studying a relative handful of texts,” Jockers told the Times. “What this technology does is let you see the big picture – the context in which a writer worked – on a scale we’ve never seen before.”
The computer also uncovered patterns in the writings of George Eliot that are similar to the patterns in writing of male authors. Jockers says he uses algorithms that search for patterns in words and common themes.
But can a computer ever reason on the same level as a human when it comes to literary analysis, a field where there is often more than one right answer?
Jockers told The New York Times that his algorithms can’t work on their own – analysis is only complete when there’s someone who has knowledge of literature overseeing the process.
“You’ll always need both,” he said. “But we’re at a moment now when there is much greater acceptance of these methods than in the past. There will come a time when this kind of analysis is just part of the tool kit in the humanities, as in every other discipline.”
What do you think? Could a literary expert and computer working in tandem analyze books to an extent that has never before been possible? Or will human beings always have the edge when it comes to matters literary?