Advertisement

Model for Classification of Poems in Hindi Language Based on Ras

  • Kaushika PalEmail author
  • Biraj V. Patel
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 141)

Abstract

The developed model will classify poem into Shringar, Hasya, Adbhuta, Shanta, Raudra, Veera, Karuna, Bhayanaka, Vibhasta rasas, which will use mix of part-of-speech-based feature and emotional features to classify the poem. Emotional features are features, which are responsible for particular emotion and it is represented in 9 categories. We have 9 classes each class-containing feature for one class, overlapping of feature is possible and is dealt with term frequency in the document. The classifiers used are support vector machine and naive Bayes. The model has used 55 poems as a dataset of all 9 genres consisting of 10531 words.

Keywords

Machine learning Feature selection Classification NLP Ras 

References

  1. 1.
    Harikrishnna, D.M., Sreenivasa Rao, K.: Emotion-specific features for classifying emotions in story text. In: IEEE 22nd National Conference on Communication (NCC) (2016)Google Scholar
  2. 2.
    Harikrishnna, D.M., Sreenivasa Rao, K.: Classification of children stories in hindi using keywords and POS density. In: Proceedings of IEEE International Conference on Computer, Communication and Control (2015)Google Scholar
  3. 3.
    Harikrishnna, D.M.K., Sreenivasa Rao, K.: Children story classification based on structure of the story. In: IEEE International Conference on Advances in Computing, Communications and Informatics 1485–1490 (2015)Google Scholar
  4. 4.
    Harikrishnna, D.M., Sreenivasa Rao, K.: Multi-stage children story speech synthesis for hindi. In: IEEE 2015 8th International Conference on Contemporary Computing (IC3) (2015)Google Scholar
  5. 5.
    Garg, M., Sinha, B.: Identification of relations from IndoWordNet for indian languages using support vector machine. In: IEEE International Conference on Computing and Network Communications, pp 547–552 (2015)Google Scholar
  6. 6.
    Nanda, G., Dua, M.: A hindi question answering system using machine learning approach. In: IEEE International Conference on Computational Techniques in Information and Communication Technologies (2016)Google Scholar
  7. 7.
    Jha, V., Manjunath, N.: HOMS: hindi opinion mining system. In: 2015 IEEE 2nd International Conference on Recent Trends in Information Systems, pp. 366−371 (2015)Google Scholar
  8. 8.
    Pundlik, S., Kasbekar, P.: Multiclass classification and class based sentiment analysis for hindi language. In: IEEE International Conference on Advances in Computing, Communications and Informatics, pp. 512–518 (2016)Google Scholar
  9. 9.
    Singh, P., Verma, A., Chaudhari, N.S.: Performance analysis of flexible zone based features to classify hindi numerals. In: 2011 3rd International Conference on Electronics Computer Technology, pp. 292−296 (2011)Google Scholar
  10. 10.
    Gaur, A., Yadav, S.: Handwritten hindi character recognition using K-means clustering and SVM. In: 4th International Symposium on Emerging Trends and Technology in Libraries and Information Services (2015)Google Scholar
  11. 11.
    Sharma, Richa, Nigam, Shweta: Opinion mining in hindi language: a survey. Int. J. Found. Comput. Sci. Technol. 4(2), 41–47 (2014)CrossRefGoogle Scholar
  12. 12.
    Pandey, Pooja, Govilkar, Sharvari: A Framework for sentiment analysis in hindi using HSWN. Int. J. Comput. Appl. 119(19), 23–26 (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Sarvajanik College of Engineering and TechnologySuratIndia
  2. 2.G.H. Patel, P.G. Department of Computer Science and TechnologySardar Patel UniversityAnandIndia

Personalised recommendations