
Cross-Topic Author Identification -- a Case Study on Swedish Literature
Author(s) -
Niklas Zechner
Publication year - 2021
Publication title -
linköping electronic conference proceedings
Language(s) - English
Resource type - Conference proceedings
eISSN - 1650-3740
pISSN - 1650-3686
DOI - 10.3384/ecp184177
Subject(s) - identification (biology) , computer science , word (group theory) , natural language processing , word identification , artificial intelligence , speech recognition , linguistics , data science , information retrieval , reading (process) , word recognition , philosophy , botany , biology
Using material from the Swedish Literature Bank, we investigate whether common methods of author identification using word frequencies and part of speech frequencies are sensitive to differences in topic. The results show that this is the case, thereby casting doubt on much previous work in author identification. This sets the stage for a broader future study, comparing other methods and generalising the results.