Recently, considerable attention has been paid to word embedding algorithms inspired by neural network models. Given a large textual corpus, these algorithms attempt to derive a set of vectors which represent the corpus vocabulary in a new embedded space. This representation can provide a useful means of measuring the underlying similarity between words. Here we investigate this property in the context of annotated texts of 19th-century fiction by the authors Jane Austen, Charles Dickens, and Arthur Conan Doyle. We demonstrate that building word embeddings on these texts can provide us with an insight into how characters group differently under different conditions, allowing us to make comparisons across different novels and authors. These results suggest that word embeddings can potentially provide a useful tool in supporting quantitative literary analysis.
