Fabula-NET: A Deep Neural Network for Automated Multidimensional Assessment of Literary Fiction and Narratives
Project description
Fabula-NET is an interdisciplinary collaboration between literary research, linguistics and informatics with the aim of expanding the scope of machine learning with domain knowledge from the humanities. Literature’s multidimensional and complex texts constitute a particularly challenging material with a potential to develop new models for automated text classification. The project combines fractal analysis, sentiment classification and advanced language models with deep neural networks to describe the internal coherence of texts based on the hypothesis that a successful literary work exhibits a particular variation between predictability and unpredictability. This variation is particularly reflected in the dynamic properties of the narrative. The overall model can be used to classify texts as high/low quality and successful/unsuccessful, which is supported by preliminary studies of, for example, H. C. Andersen’s fairy tales and J. K. Rowling’s novels. The project is multilingual and works with a very large corpus in English, Danish and Chinese in collaboration with a number of experts who help to validate the automated analysis results. The application possibilities for this technology are wide-ranging and it will be relevant for both libraries and publishers for searching and evaluating texts, and in research to understand and compare large collections of texts from world literature at a level higher than compiled single analyzes. The application can also be developed for other types of texts and contribute to increase the quality of e.g. automated text generation.
Artificial intelligence predicts literary success
What determines whether a book becomes a success? Many authors, publishers, librarians and book enthusiasts have probably asked themselves this question over the years – and we may now be closer to an answer.
Using machine learning and AI, a team of researchers from literary studies, linguistics and informatics at Aarhus University have developed a technology that can predict how likely it is that a literary work will be successful. This has been done through Fabula-NET, a project supported by VELUX FOUNDATION’s Core Group programme.
Three parameters are essential to literary success
The aim of the project is to provide a more profound knowledge of literary quality and facilitate a more qualified system for assessing literary works. The project is an exciting example of how basic research in the humanities can create new perspectives on literature and connect knowledge across disciplines.
The research group has focused on three success parameters for a literary work, and will make parts of the technology behind Fabula-NET available via a web application, where editors, authors and researchers can upload texts and learn more about their potential.
So should books be written and selected by machines? No. As with other AI solutions, Fabula-NET does not replace humans. It is a supplement that can, for example, help publishers and editors screen the many manuscripts they receive. This may help them find overlooked gems, while contributing to greater diversity among authors by selecting based on the qualities of the literature rather than the author’s profile.
