Automatic Categorization of Ottoman Literary Texts by Poet and Time Period

Abstract

Millions of manuscripts and printed texts are available in the Ottoman language. The automatic categorization of Ottoman texts would make these documents much more accessible in various applications ranging from historical investigations to literary analyses. In this work, we use transcribed version of Ottoman literary texts in the Latin alphabet and show that it is possible to develop effective Automatic Text Categorization techniques that can be applied to the Ottoman language. For this purpose, we use two fundamentally different machine learning methods: Naïve Bayes and Support Vector Machines, and employ four style markers: most frequent words, token lengths, two-word collocations, and type lengths. In the experiments, we use the collected works (divans) of ten different poets: two poets from five different hundred-year periods ranging from the 15th to 19th century. The experimental results show that it is possible to obtain highly accurate classifications in terms of poet and time period. By using statistical analysis we are able to recommend which style marker and machine learning method are to be used in future studies.

Designing Punjabi Poetry Classifiers Using Machine Learning and Different Textual Features

“…The best precision achieved was 79% using Hyperpipes. Can et al [4] investigated two fundamentally different machine learning text categorization methods, SVM and NB, for categorization of Ottoman poems according to their poets and time periods. The result shows that SVM outperformed NB.…”

Emotion Detection and Sentiment Analysis in Text Corpus: A Differential Study with Informal and Formal Writing Styles

“…Literary Pieces, lyrics and unsolicited bulk mails [27] can be mined for views/ feelings/emotions. Liu [1,3,9,11,16,17,22,23,25], Naïve Bayes (NB) [1,3,4,17,19,23], K-Nearest Neighbor (KNN) [14,23,26], Maximum Entropy (ME) [3], Winnow Classifier [21] and Centroid [21] were experimented by different research on different kinds of dataset.…”

“…Can E.F et.al [9] investigated two fundamentally different machine learning text categorization methods, Support Vector Machines (SVM) and Naïve Bayes (NB), for categorization of Ottoman poems according to their poets and time periods. Dataset comprises of the collected works (divans) of ten different Ottoman poets.…”

Determining translation invariant characteristics of James Joyce’s Dubliners

“…We also have a similar study for the İnce Memed tetralogy of Yaşar Kemal . In our recent work (Can et al 2011) we provide the first style-centered text categorization study on the Ottoman language using the poems of ten poets from five different centuries. Within the context of this language, we evaluate the performance of two different machine learning methods.…”