Author Identification for Telugu Classical Poems

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Artist finding is the errand of distinguishing the creator of a given test from an arrangement of suspects. The free worry of this errand is to characterize a fitting portrayal of test that catches the composition styles of creators. In this task, weka based machine learning instruments are utilized for distinguishing proof of creator for highlight extraction of reports spoke to utilizing variable size character n-grams. We wrote our own java program to extract the features like number of words, sentences etc. From, the poem which in turn fed as input to weka tool for the identification of author then after testing the input with all the algorithm all the accuracy rates are noted down to see which algorithm is given us the best accuracy rate. Now to find the author name for an anonymous poem the poem features are extracted using the java code and the output is taken in the java file given to the weka tool and tested with the algorithms and then the author name is given to the anonymous poems.



  • Keywords

    Author Attribution, Stylometry, Telugu dataset, Natural Language Processing, Word n-gram, Char n- gram.

  • References

      [1] Dr.A. Pandian and M.A.K. Sadiq (2013). “Authorship attribution in email investigations using Fisher’s linear discriminate method with radical basis function,” International Journal of Computer Science.

      [2] Dr.A. Pandian, V.V. Ramalingam R. Preet and Dr.R. Varadharajan (2016). “Authorship identification for tamil classical(mukkoodar pallu) using bayes net algorithm.” INDJST..

      [3] S. Nagaprasad, P. Vijayapal Reddy and A. Vinaya Babu (2015) “Authorship Attribution based on Data Compression for Telugu text.” International Journal of Computer Applications (0975-8887) volume 110-No.1,january 2015.

      [4] Shanta Phani, Shibamouli Lahiri and Arindam Biswas (2015).“Authorship Attribution based on n-grams, feauture selection for bengali language,”.


      [6] Navinder Kaur and Amandeep Verma (2015), “Authorship Attribution of Punjabi Poetry using SVM Classifier.” kaur et al.,International Journal of advance Research in Computer Science and Software Enginnering 5(5),May-2015,pp.1055-1061.

      [7] Aishwarya Sahini, Kaustubh Sarang, Susmitha Umredkar, and Mihir Patil, “Automtic Text Categorization of Marathi Language Documents.” Aishwarya Sahani et al, / (IJCSIT) International Journal of Computer Science and Information Technologies,Vol. 7(5) ,2016,2297-2301.

      [8] Ibrahim S.I. Abuhaiba and Mohammed F.Eltibi (2016). “Author Attribution of Arabic Texts using Extended Probabilistic Context Free Grammar Language Model.” I.J.Intelligent Systems and Applications,2016,6, 27-39 Published Online June 2016 in MECS( 10.5815/ijisa.2016.06.04

      [9] Feryal I. Haj Hassan and Mousmi A.Chaurasia. “Author Verfication of Arabic Language using n-gram analysis method for Classifying text.” 2012 International Conference on Innovation and Information Management (ICIIM 2012) IPCSIT vol.36 (2012) © (2012) IACSIT Press, Singapore.

      [10] Shabeeb PK (2017). “Authorship Attribution Technique for Malayalam transcripts based on n-gram model.” International Journal of Innovative Research in Science,Engineering and Technology, Website: Vol. 6, Issue 2,February 2017.

      [11] Ahmed M. Mohsen, Nagwa M. El-Makky and Nagia Ghanem (2016). “author indentification using deep learning.” Machine learning and applications(ICMLA)15th IEEE international conference.

      [12] Pandian, V.V. Ramalingam and R. Preet (2016b). “Authorship identification for tamil classical poem(mukkoodar pallu) using c4.5 algorithm,”INDJST

      [13] Parth Mehta, Prasenjit Majumder (2013). “Authorship Attribution based on Optimum parameter selection for K.L.D for Gujarati.” International Joint Conference on Natural Language Processing, pages 1102-1106,Nagoya,Japan,14-18 October 2013.

      [14] Panidian. A, V.V.Ramalingam and R.P.Vishnu Preet,2016, “Authorship Identification for Tamil Classical Poem (Mukkkoodar Pallu) using C4.5 Algorithm”,Indian Journal of science and Technology,Vol 9(47),DOI:10.17485/ijst/2016/v9i47/107944,December 2016

      [15] Pandian, A., and Md. Abdul Karim Sadiq, 2012, “Detection of Fraudulent Emails by Authorship Extraction”, International Journal of Computer Application Vol.41, No.7, pp.7 – 12.

      [16] Pandian, A., and Md. Abdul Karim Sadiq, 2013, “Authorship Attribution In Tamil Language Email For Forensic Analysis”, International Review on Computers and Software, Vol. 8, No. 12 , pp.2882-2888, (SNIP: 1.178).




Article ID: 21990
DOI: 10.14419/ijet.v7i4.19.21990

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.