Abstract
Text contents generated by social networking platforms tend to be short. The problem of authorship attribution on short texts is to determine the author of a given collection of short posts, which is more challenging than that on long texts. Considering the textual characteristics of sparsity and using informal terms, we propose a method of learning text representations using a mixture of words and character n-grams, as input to the architecture of deep neural networks. In this way we make full use of user mentions and topic mentions in posts. We also focus on the textual implicit characteristics and incorporate ten latent posting styles into the models. Our experimental evaluations on tweets show a significant improvement over baselines. We achieve a best accuracy of 83.6%, which is 7.5% improvement over the state-of-the-art. Further experiments with increasing number of authors also demonstrate the superiority of our models.
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
Bagnall, D.: Author identification using multi-headed recurrent neural network. arXiv preprint arXiv:1506.04891 (2015)
Chen, J., Hu, Y., Liu, J., et al.: Deep short text classification with knowledge powered attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6252–6259 (2019)
Hua, W., Wang, Z., Wang, H., et al.: Short text understanding through lexical-semantic analysis. In: 31st International Conference on Data Engineering, pp. 495–506. IEEE (2015)
Koppel, M., Winter, Y.: Determining if two documents are written by the same author. J. Assoc. Inf. Sci. Technol. 65(1), 178–187 (2014)
Layton, R., Watters, P., Dazeley, R.: Authorship attribution for twitter in 140 characters or less. In: 2nd Cybercrime and Trustworthy Computing Workshop, pp. 1–8. IEEE (2010)
Leepaisomboon, P., Iwaihara, M.: Utilizing latent posting style for authorship attribution on short texts. In: Intl Conf CBDCom 2019, pp. 1015–1022. IEEE (2019)
Lin, Y., Wang, X., Zhou, A.: Opinion Analysis for Online Reviews, vol. 4. World Scientific (2016)
Malik, U.: Python for NLP: introduction to the textblob library. Stack Abuse https://stackabuse.com/python-for-nlp-introduction-to-the-textblob-library/. Accessed 15 Apr 2019
Rhodes, D.: Author attribution with CNNs (2015). https://www.semanticscholar.org/paper/Author-Attribution-with-Cnn-s-Rhodes/0a904f9d6b47dfc574f681f4d3b41bd840871b6f/pdf. Accessed 22 Aug 2016
Ruder, S., Ghaffari, P., Breslin, J.G.: Character-level and multi-channel convolutional neural networks for large-scale authorship attribution. arXiv preprint arXiv:1609.06686 (2016)
Schwartz, R., Tsur, O., Rappoport, A., et al.: Authorship attribution of micromessages. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1880–1891 (2013)
Shrestha, P., Sierra, S., González, F.A., et al.: Convolutional neural networks for authorship attribution of short texts. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, vol. 2, pp. 669–674. Valencia (2017)
Stamatatos, E.: A survey of modern authorship attribution methods. J. Am. Soc. Inform. Sci. Technol. 60(3), 538–556 (2009)
Tai, K.S., Socher, R., Manning, C.D.: Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075 (2015)
Tang, D., Qin, B., Liu, T.: Document modeling with gated recurrent neural network for sentiment classification. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1422–1432 (2015)
Wang, J., Wang, Z., Zhang, D., et al.: Combining knowledge with deep convolutional neural networks for short text classification. In: IJCAI, pp. 2915–2921 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, W., Su, R., Iwaihara, M. (2020). Contribution of Improved Character Embedding and Latent Posting Styles to Authorship Attribution of Short Texts. In: Wang, X., Zhang, R., Lee, YK., Sun, L., Moon, YS. (eds) Web and Big Data. APWeb-WAIM 2020. Lecture Notes in Computer Science(), vol 12318. Springer, Cham. https://doi.org/10.1007/978-3-030-60290-1_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-60290-1_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60289-5
Online ISBN: 978-3-030-60290-1
eBook Packages: Computer ScienceComputer Science (R0)