Every industry around the globe has started to channel the ultimate power of big data. Such industries include the real estate sector, music, sports as well as the information technology sector. Nevertheless, the publishing industry is not left behind. Just like the music industry, publishing industry in each state relies on big-ticket hits around the globe.

However, predicting the best book seller has never been an easy venture. The aspect has proved to be the most enigmatic art which no one apart from the publishing house and sharpest critics can get right. At times, these faculties may get the facts right, but sometimes, especially with new competitive authors in the industry, they may fall short of the facts.

How Can This Problem Be Combated

The industry has for years lacked a computer algorithm that can identify best sellers. Fortunately, we now have the best seller-o-meter. This is an upcoming, ‘The Bestseller Code: Anatomy of the Blockbuster Novel”, which is written by Jodie Archer. Jodie Archer is an ex-researcher lead on literature based on Apples. An associate professor of English in Nebraska-Lincoln, Matthew I. Jockers claimed that the analogy and results of Jodie Archer are mostly based on the track record of the act of predicting the New York Times’ Bestseller which is mostly prospectively applicable to the Novels for the three decades.

The bestseller-o-meter is intended to identify the characteristics of the best selling fiction on a given scale. The identification is done by interrogating a large load of literature which could amount to over 20,000 Novels. The interrogating project also focuses on offering a data-driven check to the secrets behind best-selling fictions.

The Dawn of the Publishing Industry

The algorithm introduced by other Archer and Jockers is not the first attempt to apply big data to books. Inkitt, a Berlin startup, which was the first novel selected by an algorithm, has intensively tracked the responses from stories of the various books to be able to identify the potential best sellers, sorting through everything from Their Eyes Were Watching God quotes to Harry Potter lines.

Jellybooks, founded in the year 2011, is known to measure reader’s engagement on the literary production especially before the publishing of the books is done. The technology is done through software that is downloaded by users with the aim of getting access to the topic of any novel they would like to purchase.

Nevertheless, the best seller-o-meter has proved outstanding by acutely joining the literary scholarship to computational horsepower. The algorithm also features interpretive and analytical options which are keenly involved in each given book. Features such as word usage pattern, repetitions, thematic emphases as well as allusions are factored the entire search process.

Fundamental Tools of the Algorithm

Some of the various elements used by algorithm include the authoritative “voice,” plainspoken, spare, often collogue, declarative verbs as well as prose. The other types of elements are the narrative cohesins, which were discovered by Jocker and Archer. Narrative cohesion has been a universal icon that has been used by several best-selling authors in this industry. For instance, John Grisham devotes a third of such a novel; to his signature topic, law and lawyers.

With the incredible bestsellers such as John Grisham and J.K Rowling taking over the publishing market, most publishers are still inclined to divert their resources towards the unknown authors. The bestseller-o-meter should be very useful at this stage. However, the primary concern with such technology will be that some writer will be writing their pieces to impress the systems, and not making any literary pedigree. With the Big data taking over every industry around the globe, it would be great to note the various side effects that it may bring to the publishing industry too.


by: Mark Palmer