Success in books: predicting book sales before publication

Abstract

Reading remains a preferred leisure activity fueling an exceptionally competitive publishing market: among more than three million books published each year, only a tiny fraction are read widely. It is largely unpredictable, however, which book will that be, and how many copies it will sell. Here we aim to unveil the features that affect the success of books by predicting a book's sales prior to its publication. We do so by employing the Learning to Place machine learning approach, that can predicts sales for both fiction and nonfiction books as well as explaining the predictions by comparing and contrasting each book with similar ones. We analyze features contributing to the success of a book by feature importance analysis, finding that a strong driving factor of book sales across all genres is the publishing house. We also uncover differences between genres: for thrillers and mystery, the publishing history of an author (as measured by previous book sales) is highly important, while in literary fiction and religion, the author's visibility plays a more central role. These observations provide insights into the driving forces behind success within the current publishing industry, as well as how individuals choose what books to read.

Fiction Popularity Prediction Based on Emotion Analysis

“…In this research, we first model the emotional information of books using our proposed emotion trace. Emotion trace is a phrase used in this article to represent the emotion aware vector of a fiction book generated by the proposed method based on the full content of book and the NRC Emotion Intensity Lexicon 4 . After the generation of emotion traces these generated emotion aware vectors along with their labels measuring the potential popularity which is based on readers' real ratings of books will be fed into a GRU based deep learning network.…”

“…Except from methods of predicting book's success based on the content, there are also researches that studied the impact of features that have no relation with the content on the book's success. In 2019, Wang [4] studied the relationship be-tween the sales of books and features other than content of books. They studied the three feature groups: publisher features, author features (author's visibility, author's sales history, etc.)…”

PPORTAL: Public Domain Portuguese-language Literature Dataset

“…AI-powered technology has accelerated dramatically over the past few years in creative industries, such as music, movies, and books. With so much digital information available, machine learning solutions have been developed to predict the next hit song [Martín-Gutiérrez et al 2020], the next blockbuster [Ahmad et al 2017], or even the next bestseller [Wang et al 2019]. Moreover, book recommendation systems have also been a hot application in ML.…”

“…Book publishers are increasingly investing in AI-powered and data-driven strategies to offer a holistic view of the books' performance, extracting meaningful insights for better business prospects. Consequently, potential success drivers of books have been of great interest to many researchers [Maity et al 2019, Wang et al 2019]. However, understanding how such factors shape the success of books written in languages other than English (e.g., Brazilian literature) has received much less attention.…”

“…Along with the publishing industry, researchers rely on book-related data to develop tools, whose results feed better informed, faster decisions. Such solutions range from best-sellers prediction models [Maity et al 2019, Wang et al 2019 to natural language processing techniques to classify raw text [de Araujo et al 2018, Soares et al 2018, Wagner Filho et al 2018. Besides requiring Artificial Intelligence (AI) methods, all of them are essentially datadependent; i.e., mostly book-related data-dependent.…”