UrduAI: Writeprints for Urdu Authorship Identification

Abstract

The authorship identification task aims at identifying the original author of an anonymous text sample from a set of candidate authors. It has several application domains such as digital text forensics and information retrieval. These application domains are not limited to a specific language. However, most of the authorship identification studies are focused on English and limited attention has been paid to Urdu. However, existing Urdu authorship identification solutions drop accuracy as the number of training samples per candidate author reduces and when the number of candidate authors increases. Consequently, these solutions are inapplicable to real-world cases. Moreover, due to the unavailability of reliable POS taggers or sentence segmenters, all existing authorship identification studies on Urdu text are limited to the word n-grams features only. To overcome these limitations, we formulate a stylometric feature space, which is not limited to the word n-grams feature only. Based on this feature space, we use an authorship identification solution that transforms each text sample into a point set, retrieves candidate text samples, and relies on the nearest neighbors classifier to predict the original author of the anonymous text sample. To evaluate our solution, we create a significantly larger corpus than existing studies and conduct several experimental studies that show that our solution can overcome the limitations of existing studies and report an accuracy level of 94.03%, which is higher than all previous authorship identification works.

AGI-P: A Gender Identification Framework for Authorship Analysis Using Customized Fine-Tuning of Multilingual Language Model

“…In forensics, language-based profiles can be examined, and the writers of letters, emails, and other documents used in an inquiry can be identified. Author gender identification is the initial step in author profiling investigations [39]- [43]. This task has been extensively investigated, however, automatically determining stylistic differences between men and women, on the other hand, is far from ideal [38], [44]- [46].…”

Author Identification from Literary Articles with Visual Features: A Case Study with Bangla Documents

“…The aim was to advance the existing approaches and evaluate them on new standard datasets. Sarwar and Hassan [16] worked with stylometric features to overcome the limitations of having only n-gram features for Urdu texts; their experimental results showed an accuracy of 94.03%, indicating a discriminative power of the stylometric features used.…”

“…Qian et al [4] Deep learning 89.20 Mohsen et al [5] Deep learning 95.12 Zhang et al [6] Semantic relationship 95.30 Benzebouchi et al [7] Word embeddings and MLP 95.83 Anwar et al [9] LDA model with n-grams 93.17 and cosine similarity Rexha et al [10] Content and stylometric features 72.00 Confidence Nirkhi et al [12] Unigram and SVM 88.00 López-Monroy et al [13] Bag-of-words model with SVM 80.80 Sarwar and Hassan [16] Stylometric features 94.03 Chakraborty and Choudhury [17] Graph-based algorithm 94.98 Digamberrao and Prasad [18] SMO with J48 algorithm 80.00 Rakshit et al [19] Stylistic feature and SVM 92.30 Anisuzzaman and Salam [20] n-gram and NB 95.00…”