Authorship Attribution for English Short Texts

Authors

  • Tawfeeq Alsanoosy Department of Computer Science, College of Computer Science and Engineering, Taibah University, Madinah 42353, Saudi Arabia https://orcid.org/0000-0003-2630-5972
  • Bodor Shalbi Department of Computer Science, College of Computer Science and Engineering, Taibah University, Madinah 42353, Saudi Arabia
  • Ayman Noor Department of Computer Science, College of Computer Science and Engineering, Taibah University, Madinah 42353, Saudi Arabia https://orcid.org/0000-0002-3344-2847
Volume: 14 | Issue: 5 | Pages: 16419-16426 | October 2024 | https://doi.org/10.48084/etasr.8302

Abstract

Internet and social media explosive growth has led to the rapid and widespread dissemination of information, which often takes place anonymously. This anonymity has fostered the rise of uncredited copying, posing a significant threat of copyright infringement and raising serious concerns in fields where verifying information's authenticity is paramount. Authorship Attribution (AA), a critical classification task within Natural Language Processing (NLP), aims to mitigate these concerns by identifying the original source of content. Although extensive research exists for longer texts, AA for short texts, namely informal texts like tweets, remains challenging due to the latter’s brevity and stylistic variation. Thus, this study aims to investigate and measure the performance of various Machine Learning (ML) and Deep Learning (DL) methods deployed for feature extraction from short text data, using tweets. The employed feature extraction methods were: Bag-of-Words (BoW), TF-IDF, n-grams, word-level, and character-level features. These methods were evaluated in conjunction with six ML classifiers, i.e. Naive Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT), Logistic Regression (LR), K-Nearest Neighbors (KNN), and Random Forest (RF) along with two DL architectures, i.e. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). The highest accuracy achieved with an ML model was 92.34%, using an SVM with TF-IDF features. Even though the basic CNN DL model reached 88% accuracy, this outcome still surpassed the previously established baseline for this task. The findings of this research not only advance the technical capabilities of AA, but also extend its practical applications, providing tools that can be adapted across various domains to ensure proper attribution and expose copyright infringement.

Keywords:

natural language processing, authorship attribution, machine learning, deep learning, authorship identification

Downloads

Download data is not yet available.

References

S. Shao, C. Tunc, A. Al-Shawi, and S. Hariri, "An Ensemble of Ensembles Approach to Author Attribution for Internet Relay Chat Forensics," ACM Transactions on Management Information Systems, vol. 11, no. 4, Jul. 2020, Art. no. 24.

L. Chen, E. Gonzalez, and C. Nantermoz, "Authorship Attribution with Limited Text on Twitter," 2017, [Online]. Available: https://cs229.stanford.edu/proj2017/final-reports/5241953.pdf.

C. Grier, K. Thomas, V. Paxson, and M. Zhang, "@spam: the underground on 140 characters or less," in 17th ACM Conference on Computer and Communications Security, Chicago, IL, USA, Oct. 2010, pp. 27–37.

K. Lagutina and N. Lagutina, "A Survey of Models for Constructing Text Features to Classify Texts in Natural Language," in 29th Conference of Open Innovations Association, Tampere, Finland, Dec. 2021, pp. 222–233.

E. Aydogan and S. Sen, "Android Authorship Attribution Using Source Code-Based Features," IEEE Access, vol. 12, pp. 6569–6589, Jan. 2024.

A. Fedotova, A. Kurtukova, A. Romanov, and A. Shelupanov, "Semantic Clustering and Transfer Learning in Social Media Texts Authorship Attribution," IEEE Access, vol. 12, pp. 39783–39803, Jan. 2024.

W. Zheng and M. Jin, "A review on authorship attribution in text mining," WIREs Computational Statistics, vol. 15, no. 2, 2023, Art. no. e1584.

R. Azimov, "Analysis of the Use of Methods and Feature Groups for Author Recognition on the Example of Texts in the Azerbaijani Language," in 5th International Conference on Problems of Cybernetics and Informatics, Baku, Azerbaijan, Aug. 2023, pp. 1–4.

E. Ferracane, S. Wang, and R. Mooney, "Leveraging Discourse Information Effectively for Authorship Attribution," in Eighth International Joint Conference on Natural Language Processing, Taipei, Taiwan, Dec. 2017, pp. 584–593.

R. Hou and C.-R. Huang, "Robust stylometric analysis and author attribution based on tones and rimes," Natural Language Engineering, vol. 26, no. 1, pp. 49–71, Jan. 2020.

M. Kestemont et al., "Overview of the author identification task at PAN-2018: Cross-domain authorship attribution and style change detection," in Conference and Labs of the Evaluation Forum, Avignon, France, Sep. 2018, pp. 1–25.

M. Llorens and S. J. Delany, "Deep Level Lexical Features for Cross-lingual Authorship Attribution," in First Workshop on Modeling, Learning and Mining for Cross/Multilinguality, Padova, Italy, Mar. 2016.

S. Ruder, P. Ghaffari, and J. G. Breslin, "Character-level and Multi-channel Convolutional Neural Networks for Large-scale Authorship Attribution." arXiv, Sep. 21, 2016.

Y. Sari, A. Vlachos, and M. Stevenson, "Continuous N-gram Representations for Authorship Attribution," in 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, Apr. 2017, pp. 267–273.

A. Sharma, A. Nandan, and R. Ralhan, "An Investigation of Supervised Learning Methods for Authorship Attribution in Short Hinglish Texts using Char & Word N-grams." arXiv, Dec. 26, 2018.

K. Y. Tai, J. Dhaliwal, and S. M. Shariff, "Online Social Networks and Writing Styles-A Review of the Multidisciplinary Literature," IEEE Access, vol. 8, pp. 67024–67046, Jan. 2020.

A. Pandey and A. Jain, "Detection of Compromised Accounts using Machine Learning Based Boosting Algorithms- AdaBoost, XGBoost, and CatBoost," in 14th International Conference on Computing Communication and Networking Technologies, Delhi, India, Jul. 2023, pp. 1–6.

C. Suman, A. Raj, S. Saha, and P. Bhattacharyya, "Authorship Attribution of Microtext Using Capsule Networks," IEEE Transactions on Computational Social Systems, vol. 9, no. 4, pp. 1038–1047, Dec. 2022.

M. Hajja, A. Yahya, and A. Yahya, "Authorship Attribution of Arabic Articles," in International Conference on Arabic Language Processing, Nancy, France, Oct. 2019, pp. 194–208.

S. H. H. Ding, B. C. M. Fung, F. Iqbal, and W. K. Cheung, "Learning Stylometric Representations for Authorship Analysis," IEEE Transactions on Cybernetics, vol. 49, no. 1, pp. 107–121, Jan. 2019.

O. Aborisade and M. Anwar, "Classification for Authorship of Tweets by Comparing Logistic Regression and Naive Bayes Classifiers," in International Conference on Information Reuse and Integration, Salt Lake City, UT, USA, Jul. 2018, pp. 269–276.

E. Dauber, R. Overdorf, and R. Greenstadt, "Stylometric Authorship Attribution of Collaborative Documents," in International Symposium on Cyber Security, Cryptology, and Machine Learning, Beer-Sheva, Israel, Jun. 2017, pp. 115–135.

M. Eder, "Short Samples in Authorship Attribution: A New Approach," in ADHO 2017, Montreal, Canada, 2017.

S. Minaee, N. Kalchbrenner, E. Cambria, N. Nikzad, M. Chenaghlu, and J. Gao, "Deep Learning--based Text Classification: A Comprehensive Review," ACM Computing Surveys, vol. 54, no. 3, Dec. 2021, Art. no. 62.

M. Sage, P. Cruciata, R. Abdo, J. C. K. Cheung, and Y. F. Zhao, "Investigating the influence of selected linguistic features on authorship attribution using German news articles," in 5th Swiss Text Analytics Conference (SwissText) & 16th Conference on Natural Language Processing (KONVENS), Zurich, Switzerland, Jun. 2020, pp. 1–6.

B. Alsulami, E. Dauber, R. Harang, S. Mancoridis, and R. Greenstadt, "Source Code Authorship Attribution Using Long Short-Term Memory Based Networks," in European Symposium on Research in Computer Security, Oslo, Norway, Sep. 2017, pp. 65–82.

N. Saha, P. Das, and H. N. Saha, "Authorship attribution of short texts using multi-layer perceptron," International Journal of Applied Pattern Recognition, vol. 5, no. 3, pp. 251–259, Jan. 2018.

Z. Hu, R. K.-W. Lee, L. Wang, E. Lim, and B. Dai, "DeepStyle: User Style Embedding for Authorship Attribution of Short Texts," in Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data, Tianjin, China, Aug. 2020, pp. 221–229.

R. Schwartz, O. Tsur, A. Rappoport, and M. Koppel, "Authorship attribution of micro-messages: 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013," in Conference on Empirical Methods in Natural Language Processing, Seattle, WA, USA, Oct. 2013, pp. 1880–1891.

A. Modupe, T. Celik, V. Marivate, and O. O. Olugbara, "Post-Authorship Attribution Using Regularized Deep Neural Network," Applied Sciences, vol. 12, no. 15, Jan. 2022, Art. no. 7518.

M. Joshi and N. Zincir-Heywood, "Classification of Micro-Texts Using Sub-Word Embeddings," in International Conference on Recent Advances in Natural Language Processing, Varna, Bulgaria, Sep. 2019, pp. 526–533.

X. Tang, S. Liang, and Z. Liu, "Authorship Attribution of The Golden Lotus Based on Text Classification Methods," in 3rd International Conference on Innovation in Artificial Intelligence, Suzhou, China, Mar. 2019, pp. 69–72.

W. Huang, R. Su, and M. Iwaihara, "Contribution of Improved Character Embedding and Latent Posting Styles to Authorship Attribution of Short Texts," in Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data, Tianjin, China, Aug. 2020, pp. 261–269.

S. Aykent and G. Dozier, "Author Identification of Micro-Messages via Multi-Channel Convolutional Neural Networks," in IEEE International Conference on Systems, Man, and Cybernetics, Toronto, ON, Canada, Oct. 2020, pp. 675–681.

P. Shrestha, S. Sierra, F. González, M. Montes, P. Rosso, and T. Solorio, "Convolutional Neural Networks for Authorship Attribution of Short Texts," in 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, Apr. 2017, pp. 669–674.

F. Ullah, J. Wang, S. Jabbar, F. Al-Turjman, and M. Alazab, "Source Code Authorship Attribution Using Hybrid Approach of Program Dependence Graph and Deep Learning Model," IEEE Access, vol. 7, pp. 141987–141999, 2019.

A. Alqurafi and T. Alsanoosy, "Measuring Customers’ Satisfaction Using Sentiment Analysis: Model and Tool," Journal of Computer Science, vol. 20, no. 4, pp. 419–430, Feb. 2024.

A. Rabab’ah, M. Al-Ayyoub, Y. Jararweh, and M. Aldwairi, "Authorship attribution of Arabic tweets," in 13th International Conference of Computer Systems and Applications, Agadir, Morocco, Dec. 2016, pp. 1–6.

A. S. Hossain, N. Akter, and Md. S. Islam, "A Stylometric Approach for Author Attribution System Using Neural Network and Machine Learning Classifiers," in International Conference on Computing Advancements, Dhaka, Bangladesh, Jan. 2020, pp. 1–7.

H. A. Chowdhury, M. A. H. Imon, S. M. Hasnayeen, and M. S. Islam, "Authorship Attribution in Bengali Literature using Convolutional Neural Networks with fastText’s word embedding model," in 1st International Conference on Advances in Science, Engineering and Robotics Technology, Dhaka, Bangladesh, Dec. 2019, pp. 1–5.

M. Madhukar and S. Verma, "Hybrid Semantic Analysis of Tweets: A Case Study of Tweets on Girl-Child in India," Engineering, Technology & Applied Science Research, vol. 7, no. 5, pp. 2014–2016, Oct. 2017.

SaraML00, "Authorship-Attribution." [Online]. Available: https://github.com/SaraML00/authorship-attribution.git.

Downloads

How to Cite

[1]
Alsanoosy, T., Shalbi, B. and Noor, A. 2024. Authorship Attribution for English Short Texts. Engineering, Technology & Applied Science Research. 14, 5 (Oct. 2024), 16419–16426. DOI:https://doi.org/10.48084/etasr.8302.

Metrics

Abstract Views: 118
PDF Downloads: 140

Metrics Information