Combining Text and Linguistic Document Representations for Authorship Attribution
Andreas Kaster, Stefan Siersdorfer, Gerhard Weikum · 2005
In this paper, we provide several alternatives to the classical Bag-Of-Words model for automatic authorship attribution. To this end, we consider linguistic and writing style infor- mation such as grammatical structures to construct di®er- ent document representations. Furthermore we describe two techniques to combine the obtained representations: combi- nation vectors and ensemble based meta classi¯cation. Our experiments show the viability of our approach.