Authors:
(1) Todd K. Moon, Department of Electrical and Computer Engineering, Utah State University, Logan, Utah
(2) Jacob H. Gunther, Department of Electrical and Computer Engineering, Utah State University, Logan, Utah
Abstract:
Jane Austen worked on her novel Sanditon until shortly before her death in 1817, leaving a draft of twelve chapters with approximately 24,000 words. Over the years, several writers have attempted to complete the work, though with varying degrees of success. The most recognized version was published in 1975 by an anonymous author identified as Another Lady, who tried to imitate Austen's style. Despite her effort, stylometric analyses have shown that identifiable differences exist between Austen's original texts and the additions by other writers.
Through the use of computational analysis and classification techniques based on feature trees, it was possible to differentiate the segments written by Austen from those worked on by other authors. The documents underwent processes of subtree extraction and classification based on feature vectors, which demonstrated that while stylistic imitation can be achieved at a superficial level, certain unconscious patterns in an author's writing remain distinguishable.
At Q2BSTUDIO, a company specialized in development and technology services, we understand the importance of data analysis and artificial intelligence applied to various disciplines, including stylometry and natural language processing. Our ability to develop innovative technological solutions allows researchers and companies to apply advanced analysis techniques, projecting new approaches for text processing and authorship authentication.
