?
Machine Learning and Philology: An Overview of Methods and Applications
The paper provides an overview of tasks and methods associated with the term artificial intelligence, namely its interrelated field regarding machine learning algorithms as ones of the growing popularity among scholars in digital humanities, that are applicable to the philological studies, as well as the most insightful and successful cases of such work. Although due to the textual nature of the material, the tasks discussed mostly have to do with the area of natural language processing, we focus our attention on the questions that are purely philological and the works that explore the phenomena of literary texts. The reviewed papers show how the techniques such as automatic text classification and clustering, named entity recognition, or sentiment analysis not only help to explore the large collections of texts but also to provide a new way to look at fiction and to redefine some literary concepts, such as genre and style. The review results in the conclusion that applying computation models to fictional texts allows to enrich the understanding of literature and to provide some insights for further qualitative analysis. We are currently testing some of the discussed methods on the Corpus of Russian short stories of the first third of the 20th century.