DeepStyle: User style embedding for authorship attribution of short texts

• Main Authors: HU, Zhiqiang, LEE, Roy Ka-Wei, WANG, Lei, LIM, Ee-Peng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Authorship attribution; Style embedding; Triplet loss; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/6018; https://ink.library.smu.edu.sg/context/sis_research/article/7021/viewcontent/DeepStyleUserStyleEmbedding_av_2020.pdf; https://ink.library.smu.edu.sg/context/sis_research/article/7021/filename/0/type/additional/viewcontent/505687_1_En_17_MOESM1_ESM.pdf
• Institution: Singapore Management University

Authorship attribution (AA), which is the task of finding the owner of a given text, is an important and widely studied research topic with many applications. Recent works have shown that deep learning methods could achieve significant accuracy improvement for the AA task. Nevertheless, most of these proposed methods represent user posts using a single type of features (e.g., word bi-grams) and adopt a text classification approach to address the task. Furthermore, these methods offer very limited explainability of the AA results. In this paper, we address these limitations by proposing DeepStyle, a novel embedding-based framework that learns the representations of users’ salient writing styles. We conduct extensive experiments on two real-world datasets from Twitter and Weibo. Our experiment results show that DeepStyle outperforms the state-of-the-art baselines on the AA task.