Deutsch Intern
    Data Science Chair

    Our paper "One Graph to Rule them All: Using NLP and Graph Neural Networks to analyse Tolkien's Legendarium" has been accepted at CHR 2022

    10/18/2022

    In this paper, we combine NLP with Graph Learning to advance computational literary studies - using Tolkien's Legendarium as a case study.

    We have successfully kicked off our co-operation with the Chair for Machine Learning for Complex Networks by getting our joint paper "One Graph to Rule them All: Using NLP and Graph Neural Networks to analyse Tolkien's Legendarium" accepted at Computational Humanities Research 2022!

    In this work, we combine our NLP methods with their Graph Learning models to enable new insights for computational literary studies. We extract character networks and other information from the most well-known texts in Tolkien's Legendarium - The Lord of the Rings, The Hobbit and The Silmarillion -, providing both visualisations and analysis of the extracted networks.

    A preprint of the paper is available at arXiv.

    Abstract:

    Natural Language Processing and Machine Learning have considerably advanced Computational Literary Studies. Similarly, the construction of co-occurrence networks of literary characters, and their analysis using methods from social network analysis and network science, have provided insights into the micro- and macro-level structure of literary texts. Combining these perspectives, in this work we study character networks extracted from a text corpus of J.R.R. Tolkien's Legendarium. We show that this perspective helps us to analyse and visualise the narrative style that characterises Tolkien's works. Addressing character classification, embedding and co-occurrence prediction, we further investigate the advantages of state-of-the-art Graph Neural Networks over a popular word embedding method. Our results highlight the large potential of graph learning in Computational Literary Studies.

    Back