New software can predict success of a book

New software can predict how successful a book can be

If you are a writer, your top most desire is to get your work read by virtually everyone. It doesn’t matter whether you write books, journals, or articles in magazines, newspapers or online – your interest is to have your work read by all.

The problem is before you publish your work you cannot predict how popular your book or article can be, even though you really want it to go viral. A team of software engineers from Stony Brook UniversityĀ have developed a software that can now predict for you the likelihood of success or failure of your work based on your writing style.

The Telegraph reports, “Computer scientists have developed an algorithm which can predict with 84 per cent accuracy whether a book will be a commercial success”.

As PopSci reports,”the software learned this trick from analyzing 800 books from Project Gutenberg, an online archive of public domain works, and comparing the books’ word use and grammar with how often they’ve been downloaded. For some books, the computer scientists also considered Amazon sales data awards such as Pulitzer Prizes. The books were of all different genres and types, ranging from novels to poetry, and from love stories to sci-fi.”

The software uses aĀ technique called statistical stylometry, which mathematically examines the use of words and grammar in literary works.

According to the software’s findings,Ā successful books contained more conjunctions, such as “and” and “but” and large numbers of nouns and adjectivesĀ whereas unpopular books containedĀ more adverbs and “relied on words that explicitly describe actions and emotions such as ‘wanted,’ ‘took’ or ‘promised.”

Next time you are writing an article you might want to make your sentences longer and “just stick to plain writing”.

Odipo Riaga1804 Posts

Film Director, Tech and Business Blogger, Chess Player, and Photographer. God is Science.


Welcome! Login in to your account

Remember me Lost your password?

Lost Password