There’s a big difference between getting your novel published and writing popular novels. This research shows how to predict popular novels. If you can convince literary agents and publishing houses your writing will be popular, you’re more likely to get your novel published.
Need encouragement to Blossom into a new season of life? Sign up for my free weekly emails!
In Outlining Your Novel: Map Your Way to Success, K. M. Weiland helps authors choose the right type of outline, offers guidance in brainstorming plot ideas, reveals characters, and shows authors how to structure scenes. Popular novels didn’t just pop out of nowhere; they were crafted by authors serious about writing fiction.
In this article, I share research from a study that used writing style to predict the popularity of novels. Assistant Professor Yejin Choi of the Department of Computer Science at Stony Brook believes she has a tool to bring science to the art of determining popular novels. This is good news for book publishers – and even better news for authors who need that extra oomph to get their novels published.
Predicting Popular Novels
Imagine the challenge publishers, editors, and literary agents face, pouring over thousands of manuscripts from thousands of authors, trying to determine if a book will be popular. Sometimes they have obvious reasons to reject a book manuscript; other times they just have a feeling that a novel won’t be popular.
But what if there was a formula that helped us predict if a novel will be a hit?
Define what a “popular novel” is. The researchers defined successful novel by download counts from Project Gutenberg, which houses 42,000 books that are available for free in electronic format. Dr. Choi and her team examined eight genres of popular novels: adventure, mystery, historical fiction, fiction, science-fiction, love stories, short stories, and poetry. They also studied a number of books not included at Project Gutenberg, ranging from A Tale of Two Cities by Charles Dickens, through The Old Man and the Sea by Ernest Hemingway, to The Lost Symbol by Dan Brown.
“For a small number of novels, we also considered award recipients—such as Pulitzer and Nobel prizes—and Amazon sales records in order to define a novel’s success,” Choi says. “Additionally, we extended our empirical study to movie scripts, where we quantified a film’s success based on the average review scores at imdb.com.”
To learn which novels are most likely to be popular, these researchers examined the writing style in successful literature. “Predicting the success of literary works poses a massive dilemma for publishers and aspiring writers alike,” Choi said. “We examined the quantitative connection between writing style and successful literature. Based on novels across different genres, we investigated the predictive power of statistical stylometry in discriminating successful literary works, and identified the stylistic elements that are more prominent in successful writings.” In other words, they looked for similarities in the writing styles of different authors.
Statistical stylometry is the analysis of variations in literary style between authors and genres. This research shows that it’s possible to distinguish highly successful literature – popular novels – from unpopular ones. With accuracy rates as high as 84%, this seems like an excellent way to determine if a novel should be published.
Popular novels use lots of conjunctions. This research indicated that more popular novels make more frequent use of discourse connectives (conjunctions such as “and”, “but”, “or”) to join sentences and prepositions. Popular novels also use prepositions, nouns, pronouns, adjectives , and determiners (words that precede nouns to indicate whether the noun is specific or general, e.g. “your letter”). If you want your novel to be published and popular, use more conjunctions.
Less popular books use more verbs, adverbs, and foreign words. Additionally, less popular novels rely more heavily on topical words that could be almost cliché (eg, love, romance), typical locations (eg, Paris, New York City), and extreme (breathless, freezing) and negative (bruised) words. Less successful books also rely on verbs that explicitly describe actions and emotions (“wanted”, “took”, “promised”, “cried”, “cheered”), while more successful novels favor verbs that describe thought-processing (“recognized”, “remembered”) and verbs that simply serve the purpose of quotes (“say”).
How this research was conducted – the nitty gritty details of predicting popular novels. The researchers took 1000 sentences from the beginning of each book. They performed systematic analyses based on lexical and syntactic features that have been proven effective in Natural Language Processing (NLP) tasks such as authorship attribution, genre detection, gender identification, and native language detection. The best way to predict if your novel will be popular is to run this test…and do lots of book marketing and promotion. Because writing style alone won’t make your novel popular.
“To the best of our knowledge, our work is the first that provides quantitative insights into the connection between the writing style and the success of literary works,” says Professor Choi. “Previous work has attempted to gain insights into the ‘secret recipe’ of successful books. But most of these studies were qualitative, based on a dozen books, and focused primarily on high-level content—the personalities of protagonists and antagonists and the plots. Our work examines a considerably larger collection—800 books—over multiple genres, providing insights into lexical, syntactic, and discourse patterns that characterize the writing styles commonly shared among the successful literature.”
Predicting popular novels not only achieved up to 84% accuracy rates in novels, it had an 89% accuracy rate in the predicting popular movies.
“This [predicting a novel’s popularity] sets forth an understanding of the connection between successful writing style and readability,” says Dr. Choi. “We also shed light on the connection between sentiment/connotation and literary success, and put forward comparative insights between successful writing styles of fiction and nonfiction.”
A novel’s readability and popularity are negatively correlated. Professor Choi stated that they made an unexpected observation on the connection between readability and the literary success: they correlate into the opposite directions. This means the more popular the novel, the less readable it is. That explains why I hated reading “popular novels” in university. They’re hard to read!
Can you use this research to predict if your novel will be popular? I wonder if literary agents and publishing houses would adopt statistical stylometry when deciding what novels to take a chance on.
Source: This research paper was called Success with Style: Using Writing Style to Predict the Success of Novels , and presented at the conference on Empirical Methods in Natural Language Processing.