State of the Art in Authorship Attribution With Impact Analysis of Stylometric Features on Style Breach Prediction

Abstract

The most influential research was studied that spans over the domains from Authorship attribution and stylometry. The reference material contributes robust classifiers with reasonable array of feature extraction techniques, such as Dirichlet–multinomial change point regression to extract the progress of inscription elegance with time, comprising plodding variations in stylishness as the author ages and unexpected vicissitudes. This paper presents quantifiable evaluation of the research in terms of year-wise research output, diversity of applications, nature of collaboration, characteristics of highly productive techniques and the benchmark of performance criteria by eminent high impact researchers. The outcomes of this study can by deployed for dialectology analysis and corpus linguistics, stylistics, natural language processing, classification, and literary and historical analysis, forensic analysis etc.

Information Retrieval and Machine Learning Methods for Academic Expert Finding

“…This assumption was objective yet conservative, as it was reasonable to assume that other researchers working on the same or similar topics could also possess expertise in them. Consequently, our evaluation method resembled authorship attribution [67,68], in which the aim is to identify the authors of a test article (it is worth mentioning that we solely focus on the content of texts and do not employ stylometric features for this purpose, as is usual for authorship attribution [69]).…”