Visible to the public Authorship Attribution vs. Adversarial Authorship from a LIWC and Sentiment Analysis Perspective

TitleAuthorship Attribution vs. Adversarial Authorship from a LIWC and Sentiment Analysis Perspective
Publication TypeConference Paper
Year of Publication2018
AuthorsGaston, J., Narayanan, M., Dozier, G., Cothran, D. L., Arms-Chavez, C., Rossi, M., King, M. C., Xu, J.
Conference Name2018 IEEE Symposium Series on Computational Intelligence (SSCI)
KeywordsAdversarial Authorship, authorship attribution, Computer science, feature extraction, feature selection, GEFeS, Human Behavior, LIWC, Metrics, psychology, pubcrawl, Semantics, sentiment analysis, Steady-state, Steady-State Genetic Algorithm, stylometry, Writing
AbstractAlthough Stylometry has been effectively used for Authorship Attribution, there is a growing number of methods being developed that allow authors to mask their identity [2, 13]. In this paper, we investigate the usage of non-traditional feature sets for Authorship Attribution. By using non-traditional feature sets, one may be able to reveal the identity of adversarial authors who are attempting to evade detection from Authorship Attribution systems that are based on more traditional feature sets. In addition, we demonstrate how GEFeS (Genetic & Evolutionary Feature Selection) can be used to evolve high-performance hybrid feature sets composed of two non-traditional feature sets for Authorship Attribution: LIWC (Linguistic Inquiry & Word Count) and Sentiment Analysis. These hybrids were able to reduce the Adversarial Effectiveness on a test set presented in [2] by approximately 33.4%.
DOI10.1109/SSCI.2018.8628769
Citation Keygaston_authorship_2018