A Multi-task Approach to Predict Likability of Books

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 1217–1227, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics A Multi-task Approach to Predict Likability of Books Suraj Maharjan Dept. of Computer Science University of Houston Houston, TX, 77004 smaharjan2@uh.edu John Arevalo and Fabio A. Gonz´alez Computing Systems and Industrial Engineering Dept. Universidad Nacional de Colombia Bogot´a, Colombia {jearevaloo, fagonzalezo}@unal.edu.co Manuel Montes-y-G´omez Instituto Nacional de Astrofısica Optica y Electronica Puebla, Mexico mmontesg@ccc.inoep.mx Thamar Solorio Dept. of Computer Science University of Houston Houston, TX, 77004 solorio@cs.uh.edu Abstract We investigate the value of feature en- gineering and neural network models for predicting successful writing. Similar to previous work, we treat this as a binary classification task and explore new strate- gies to automatically learn representations from book contents. We evaluate our fea- ture set on two different corpora created from Project Gutenberg books. The first presents a novel approach for generating the gold standard labels for the task and the other is based on prior research. Us- ing a combination of hand-crafted and re- current neural network learned representa- tions in a dual learning setting, we obtain the best performance of 73.50% weighted F1-score. 1 Introduction Every year millions of new books are published, but only a few of them turn into commercial suc- cesses, and even fewer achieve critical praise in the form of prestigious awards or meaningful sales. Editors have the difficult task of making the go/no- go decision for all manuscripts they receive, and the revenue for their publishing house depends on the accuracy of that judgment. The website www.litrejections.com documents some of the biggest mistakes in the history of the pub- lishing industry, including Agatha Christie, J.K. Rowling, and Dr. Seuss, all of whom received many rejection letters before landing their first publishing deal. Many factors contribute to the eventual success of a given book. Internal factors such as plot, story line, and character development all have a role in the likability of a book. External factors such as author reputation and marketing strategy are ar- guably equally relevant. Some factors might even be out of the control of an author or publishing house, such as the current trends, the competition from books released simultaneously, and the his- torical and contextual factors inherent to society. Previous work by Ganjigunte Ashok et al. (2013) demonstrated relevant results using stylis- tic features to predict the success of books. Their definition of success was a function of the number of downloads from Project Gutenberg. However downloading a book is not by itself an indicator of a highly liked or a commercially successful book. We instead propose to use the rating from review- ers collected from Goodreads as a measure of suc- cess. We also propose features and deep learning techniques that have not been used before on this problem, and validate their usefulness in two dif- ferent tasks: success prediction and genre classifi- cation. Our key contributions are the …

Content truncated to 500 words