Can you fool AI by doing a 180? — A case study on authorship analysis of texts by Arata Osada

作者：

Highlights：

• A shift in writer’s opinions poses a challenge to author analysis solutions.

• Time-related changes have to be considered in an authorship analysis task.

• Drop in performance of solution highest for fiction books due to topical diversity.

摘要

•A shift in writer’s opinions poses a challenge to author analysis solutions.•Time-related changes have to be considered in an authorship analysis task.•Drop in performance of solution highest for fiction books due to topical diversity.

论文关键词：Authorship analysis,Single authorship identification,Authorship verification,Similarity detection,Binary text classification,Transformers,Personal ethics

论文评审过程：Received 30 October 2020, Revised 25 April 2021, Accepted 18 May 2021, Available online 3 June 2021, Version of Record 3 June 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102644