N-Gram Accuracy Analysis in the Method of Chatbot Response
Keywords:Chatbot, TF-IDF, Cosine Similarity, N-gram, Bot Line
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.
 Bayu Setiaji. 2016. â€œChatbot Using A Knowledge in Database Human-to-Machine Conversation Modelingâ€. International Conference on Intelligent Systems, Modelling and Simulation. https://doi.org/10.1109/ISMS.2016.53
 Nirmala Shinde, 2018. â€œChatbot using TensorFlow for small Businessesâ€. Proceedings of the 2nd International Conference on Inventive Communication and Computational Technologies (ICICCT 2018).
 Bhavika R. Ranoliya. 2017. â€œChatbot for University Related FAQsâ€. IEEE
 Varvara Logacheva. 2018. â€œA Dataset of Topic-Oriented Human-to-Chatbot Dialoguesâ€. Bayan Abu Shawar. 2011. â€œA Chatbot as a Natural Web Interface to Arabic Web QAâ€. International Journal of Emerging Technologies in Learning. Vol. 6, No. 1. http://dx.doi.org/10.3991/ijet.v6i1.1502
 Aniket Dole. 2015. â€œIntelligent Chat Bot for Banking Systemâ€. International Journal of Emerging Technologies in Learning. Volume 4, Issue 5(2).
 Shunichi Ishihara. 2014. â€œA Comparative Study of Likelihood Ratio Based Forensic Text Comparison Proceduresâ€. Fifth Cybercrime and Trustworthy Computing Conference. https://doi.org/10.1109/CTC.2014.9
 Ranjeet Kumar. 2014. â€œA Trigram Word Selection Methodology to Detect Textual Similarity with Comparative Analysis of Similar Techniquesâ€. Fourth International Conference on Communication Systems and Network Technologies. https://doi.org/10.1109/CSNT.2014.82
 Sixing Wu. 2018. â€œA Fully Character-level Encoder-Decoder Model for Neural Responding Conversationâ€. IEEE International Conference on Computer Software & Applications.
View Full Article:
How to Cite
LicenseAuthors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under aÂ Creative Commons Attribution Licensethat allows others to share the work with an acknowledgement of the work''s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal''s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (SeeÂ The Effect of Open Access).