Extraction of Character Profiles from the Gutenberg Archive.

Online text repositories such as Gutenberg.org have been increasing in number, size and adoption. This growing availability prompts new investigations for insights into the knowledge emerging from the content of e.g. literature and drama. However, the process relies upon the repositories’ ability to fulfill FAIR principles. We present the preparatory work on the semantic analysis of drama literature in Gutenberg, aiming at the extraction and profiling of fictional characters and their narrative roles. Our preliminary analysis matches such characters and their corresponding profiles in knowledge bases such as DBpedia and Wikidata.