How Algorithms Can Be Used to Predict Great Literature

Just like in music industries, book publishing bases its popularity on hits. More importantly, most experts feel that the process of predicting best-selling work is an art by itself. Most of the time, the aforementioned faculties serve the institution well. However, in other situations, they do not perform so well. For instance, when it comes to first time author. Occasionally, some of the prominent writers we view today experience some resistance before they come up to the spotlight. Some of these authors include John Grisham, E.L James amongst many other.

What Can this Algorithm Do?

Currently, most people view a computer algorithm that can give a prediction of about eighty percent success of published work as a fairy tale. Nonetheless, a group of experts made up of Jodie Archer, Nebraska Lincoln, and Matthew Jockers have come up with an algorithm that has solved the problem above known as bestseller-ometer. Probably, over the last few decades, according to New York Times when the system is applied retrospectively it has produced successful results.

The working principle of the above algorithm involves identifying the traits of best-selling work, let us say over 2000 and plus novels. Then they compare the data to the characteristics of the less selling novels, thereby helping the user to identify the secrets behind successful literary work. Additionally, the algorithm helps to determine the trend in specific styles and genres applied in literature.

Understanding Digital Humanities

In 2008, Jockers a professor at Stanford University led an emerging technology in digital humanities. The system involved the use of computer-aided quantitative analysis of literary work. Most of the scholars felt that a machine could do very little to identify substantial literature.

Looking at Archer, he became interested in the above concept a few years before Jockers during the era of Da Vinci Code written by Dan Brown. Initially, many professionals criticized the book, but eventually it found a great audience. For instance, it sold over eighty million copies. It is in this regard that Archer concluded that the scenario was due to "textual charisma."

Though the “bestseller-ometer” was the first successful computer algorithm in clarifying big data to novels, it does not mean that there were no other inventors. Initially, a scholar known as Inkitt had invented an algorithm that selected the first book in history. Currently, the London's Jelly books analyze and measures a phenomenon known as readers engagement before the novel is produced to determine its popularity.

How the “Besteller-Ometer” Uses Big Data

Looking at some of the characteristics that the bestselling-ometer use, to many might seem like magic. Mostly, the system utilizes certain features such as word patterns, repetition and thematic emphasis. Even those with literature proficiency don't alway have the above features in mind. Moreover, according to the algorithm, sex does not thrill many readers. Other characteristics used includes literature cohesion and the choice of topic.

One the most selling novel predicted by the system was Odysseus. Notably, the book by Homer illustrates the main character as a courageous warrior who was very cunning. The author creates a contradiction between him and other stereoscopic heroes in Greek literature. For instance, in many occasions, an Odyssey character analysis demonstrates provides insightfully intellect by logically analyzing each decision he makes and how that can be applied to readers.

Final Thoughts

Summing it up, Archer feels that some of prominent authors such as John Grisham, Patterson, and Steel control most publishers because they produce many of the top of best-selling novels. Thus, this makes identifying new upcoming talents very hard. As publishers begin using "bestseller-ometer" algorithm, then they will be able to identify profitable work. Hence, writers will be judged in terms of their work and not popularity.

Read more on data analytics at Things Cyber Big Data Analytics What You Need To Know.

Follow Me

Carol M. Evenson

Data Security Consultant at Evenson Corporate Consulting
Carol Evenson is a data security consultant specializing in cloud management and process analysis. She currently assists organizations within the continental US and UK.
Follow Me
About Carol M. Evenson

Carol Evenson is a data security consultant specializing in cloud management and process analysis. She currently assists organizations within the continental US and UK.

Leave a Reply