Abstract
Finding the author of a writing among a group of authors whose authorship is unknown or questioned is known as “authorship identification.” Finding the proper author attributes to obtain stylistic data is the major component of this task. From the standpoint of machine learning, it can be viewed as a multiclass, single-label text classification problem in which the author’s name represents a text document's class label. This type of problem, which identifies patterns in the writings of the same author, is solved using stylistic elements. Many aspects, including vocabulary, syntactic, semantic, and n-grams, can be utilised to record the style information of writers. The authors of this study developed convolutional neural network (CNN) models that use character-level N-grams, such as 1-g, 2-g, and 3-g, to identify the authors of a given text. Experimental studies on three different datasets: novels extracted from Project Gutenberg of different authors and genres and Stamatatos 06 Author Identification: C10-Attribution—confirm that this model facilitates author identification.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Diederich J, Kindermann J, Leopold E, P G (2003) Attribution with support vector machines. J Appl Intell. https://doi.org/10.1023/A:1023824908771
Houvardas J, Stamatatos E (2006) N-Gram feature selection for authorship identification. In: Euzenat J, Domingue J (eds) Artificial intelligence: methodology, systems, and applications, AIMSA 2006. Lecture notes in computer science, vol 4183. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11861461_10
Keˇselj V, Peng F, Cercone N, Thoma C (2003) N-Gram-based author profiles for authorship attribution. In: Pacific association for computational linguistics, pp 255–264
Mohsen AM, El-Makky NM, Ghanem N (2016) Author identification using deep learning. In: 15th IEEE international conference on machine learning and applications (ICMLA), pp 898–903. https://doi.org/10.1109/ICMLA.2016.0161
Segarra S, Eisen M, Ribeiro A (2015) Authorship attribution through function word adjacency networks. IEEE Trans Sig Process 63(20):5464–5478
Neocleous A, Loizides A (2021) Machine learning and feature selection for authorship attribution: the case of mill, Taylor mill and Taylor, in the nineteenth century. In: IEEE Access vol 9, pp 7143–7151
Rocha A et al (2014) Authorship attribution for social media forensics. In: IEEE transactions on Inf10. Kim Y. Convolutional neural networks for sentence classification (2014), https://arxiv.org/pdf/1408.5882.pdf
PAN Dataset-stamatatos06-authorship-attribution-dataset-c10. https://doi.org/10.5281/zenodo.3759064
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Alamanda, S., Pabboju, S., Gugulothu, N. (2023). N-Gram based Convolutional Neural Network Approach for Authorship Identification. In: Kumar, A., Ghinea, G., Merugu, S. (eds) Proceedings of the 2nd International Conference on Cognitive and Intelligent Computing. ICCIC 2022. Cognitive Science and Technology. Springer, Singapore. https://doi.org/10.1007/978-981-99-2746-3_12
Download citation
DOI: https://doi.org/10.1007/978-981-99-2746-3_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-2745-6
Online ISBN: 978-981-99-2746-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)