Abstract
The analysis of literary works has experienced a surge in computer-assisted processing. To obtain insights into the community structures and social interactions portrayed in novels, the creation of social networks from novels has gained popularity. Many methods rely on identifying named entities and relations for the construction of these networks, but many of these tools are not specifically created for the literary domain. Furthermore, many of the studies on information extraction from literature typically focus on 19th and early 20th century source material. Because of this, it is unclear if these techniques are as suitable to modern-day literature as they are to those older novels. We present a study in which we evaluate natural language processing tools for the automatic extraction of social networks from novels as well as their network structure. We find that there are no significant differences between old and modern novels but that both are subject to a large amount of variance. Furthermore, we identify several issues that complicate named entity recognition in our set of novels and we present methods to remedy these. We see this work as a step in creating more culturally-aware AI systems.
Highlights
The characters and their relations can be seen as the backbone of any story, and explicitly creating and analysing a network from these relationships can provide insights into the community structures and social interactions portrayed in novels (Moretti, 2013)
We present our evaluation of four different NER systems on 20 classic and 20 modern novels in the section ‘Named Entity Recognition Experiments and Results’, followed by the creation and analysis of social networks in the section ‘Network Analysis’
We set out to close a gap in the literature when it comes to the evaluation of NER for the creation of social networks from fiction literature
Summary
The characters and their relations can be seen as the backbone of any story, and explicitly creating and analysing a network from these relationships can provide insights into the community structures and social interactions portrayed in novels (Moretti, 2013). Quantitative approaches to social network analysis to examine the overall structure of these social ties, are borrowed from modern sociology and have found their way into many other research fields such as computer science, history, and literary studies (Scott, 2012). The most commonly used approach for extracting such networks, is to first identify characters in the novel through Named Entity Recognition (NER) and identifying relationships between the characters through for example measuring how often two or more characters are mentioned in the same sentence or paragraph. Evaluating named entity recognition tools for extracting social networks from novels.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have