Advertisement

Subjective Answer Grader System Based on Machine Learning

  • Avani SakhaparaEmail author
  • Dipti Pawade
  • Bhakti Chaudhari
  • Rishabh Gada
  • Aakash Mishra
  • Shweta Bhanushali
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 898)

Abstract

According to experts, a good test paper should have a combination of objective and subjective questions. But the current online examinations mainly consist of only objective questions. This is because an accurate computerized grading is possible for such questions. But achieving an accurate computerized grading for the subjective questions is still a matter of concern. To address this problem, in this paper, we have designed and implemented a machine learning-based subjective answer grader system (SAGS) using two algorithms, namely latent semantic analysis (LSA) and information gain (IG) for the generation of grades. We have proposed the enhancement of these algorithms through synonym replacement using WordNet, and the accuracy of these algorithms is measured by comparing the generated scores with the scores given by human evaluators.

Keywords

Subjective answer evaluation Machine learning Latent semantic analysis (LSA) Information gain (IG) WordNet 

References

  1. 1.
    Pooja, K., Amitkumar, M., Kavita, D., Tejaswini, D.: Online examination with short text matching. In: IEEE Global Conference on Wireless Computing and Networking, pp. 56–60, Lonavala, India (2014)Google Scholar
  2. 2.
    Li, B., Lu, J., Yao, J., Zhu, Q.: Automated essay scoring using the KNN algorithm. In: IEEE Proceedings of the International Conference on Computer Science and Software Engineering, pp. 735–738, Hubei, China (2008)Google Scholar
  3. 3.
    Himani, M., Syamala Devi, M.: Subjective evaluation using LSA technique. Int. J. Comput. Distrib. Syst. (2013)Google Scholar
  4. 4.
    Arun, P., Parshu, D., Karma, W., Kesang, W., Uttar, R., Yeshi, J.: Automatic answer evaluation: NLP approach. In: ResearchGate, pp. 1–5 (2016).  https://doi.org/10.13140/RG.2.1.2563.6726
  5. 5.
    James, A.: Natural language processing. In: Encyclopedia of Computer Science, 4th edn., ACM Digital Library, pp. 1218–1222. Wiley, Chichester (2003)Google Scholar
  6. 6.
    Syamala Devi, M., Himani, M.: Machine learning techniques with ontology for subjective answer evaluation. Int. J. Nat. Lang. Comput. 5(2), 1–11 (2016)Google Scholar
  7. 7.
    Thomas, L.: Latent semantic analysis. In: Major Reference Works, Wiley Online Library (2006)Google Scholar
  8. 8.
    Nicholas, E., Xiaoni, Z., Victor, P.: Latent semantic analysis: five methodological recommendations. Eur. J. Inf. Syst. 21(1), 70–86 (2010) (Special Issue on Quantitative Methodology)Google Scholar
  9. 9.
    Kishore, P., Salim, R., Todd, W., Wei-Jing, Z.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–318, Philadelphia (2002)Google Scholar
  10. 10.
    Jana S.: Using a MaxEnt classifier for the automatic content scoring of free-text responses. In: Proceedings of the 30th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering, pp. 41–48. AIP Press (2011)Google Scholar
  11. 11.
    Md. Monjurul, I., Latiful Hoque, A.S.M.: Automated essay scoring using generalized latent semantic analysis. J. Comput. 7(3), 616 – 626 (2012)Google Scholar
  12. 12.
    Fabian, P., Gael, V., Alexandre, G., Vincent, M., Bertrand, T., Olivier, G., Mathieu, B., Peter, P., Ron, W., Vincent, D., Jake, V., Alexandre, P., David, C., Matthieu, B., Matthieu, P., Edouard, D.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. (JMLR) 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Kaggle Dataset, The Hewlett Foundation: Short Answer Scoring. https://www.kaggle.com/c/asap-sas. Accessed 11 April 2018
  14. 14.
    Martin, P.: An algorithm for suffix stripping. Program 14(3), 130–137 (1980).  https://doi.org/10.1108/eb046814CrossRefGoogle Scholar
  15. 15.
    Harun, U.: A two-stage feature selection method for text categorization by using information gain, principal component analysis and genetic algorithm. Knowl. Based Syst. 24(7), 1024–1032 (2011) (Elsevier)Google Scholar
  16. 16.
    George, M.: WordNet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Avani Sakhapara
    • 1
    Email author
  • Dipti Pawade
    • 1
  • Bhakti Chaudhari
    • 1
  • Rishabh Gada
    • 1
  • Aakash Mishra
    • 1
  • Shweta Bhanushali
    • 1
  1. 1.Department of ITK.J. Somaiya College of EngineeringMumbaiIndia

Personalised recommendations