N-Gram Accuracy Analysis in the Method of Chatbot Response

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Chatbot is a computer program designed to simulate interactive conversations or communication to users. In this study, chatbot was created as a customer service that functions as a public health service in Malang. This application is expected to facilitate the public to find the desired information. The method for user input in this application used N-Gram. N-gram consists of unigram, bigram and trigram. Testing of this application is carried out on  3 N-gram methods, so that the results of the tests  have been done obtain the results for unigram 0.436, bigram 0.28, and trigram 0.26. From these results it can be seen that trigrams are faster in answering questions.


  • Keywords

    Chatbot,TF-IDF,Cosine Similarity, N-gram, Bot Line

  • References

      [1] Bayu Setiaji. 2016. “Chatbot Using A Knowledge in Database Human-to-Machine Conversation Modeling”. International Conference on Intelligent Systems, Modelling and Simulation. https://doi.org/10.1109/ISMS.2016.53

      [2] Nirmala Shinde, 2018. “Chatbot using TensorFlow for small Businesses”. Proceedings of the 2nd International Conference on Inventive Communication and Computational Technologies (ICICCT 2018).

      [3] Bhavika R. Ranoliya. 2017. “Chatbot for University Related FAQs”. IEEE

      [4] Varvara Logacheva. 2018. “A Dataset of Topic-Oriented Human-to-Chatbot Dialogues”. Bayan Abu Shawar. 2011. “A Chatbot as a Natural Web Interface to Arabic Web QA”. International Journal of Emerging Technologies in Learning. Vol. 6, No. 1. http://dx.doi.org/10.3991/ijet.v6i1.1502

      [5] Aniket Dole. 2015. “Intelligent Chat Bot for Banking System”. International Journal of Emerging Technologies in Learning. Volume 4, Issue 5(2).

      [6] Shunichi Ishihara. 2014. “A Comparative Study of Likelihood Ratio Based Forensic Text Comparison Procedures”. Fifth Cybercrime and Trustworthy Computing Conference. https://doi.org/10.1109/CTC.2014.9

      [7] Ranjeet Kumar. 2014. “A Trigram Word Selection Methodology to Detect Textual Similarity with Comparative Analysis of Similar Techniques”. Fourth International Conference on Communication Systems and Network Technologies. https://doi.org/10.1109/CSNT.2014.82

      [8] Sixing Wu. 2018. “A Fully Character-level Encoder-Decoder Model for Neural Responding Conversation”. IEEE International Conference on Computer Software & Applications.




Article ID: 28991
DOI: 10.14419/ijet.v7i4.36.28991

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