Open AccessLiteration Hearing Impairment (I-Chat Bot): Natural Language Processing (NLP) and Naïve Bayes Method
Author(s) -
Merry Anggraeni,
Mohammad Syafrullah,
Hillman Akhyar Damanik
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1201/1/012057
Subject(s) - chatbot , computer science , artificial intelligence , naive bayes classifier , natural language processing , conversation , turing test , question answering , test (biology) , the internet , natural language , machine learning , speech recognition , world wide web , support vector machine , psychology , paleontology , communication , biology
A part from advances in Artificial Intelligence and Natural Language Processing, designed CHATBOT will try to understand user requests accurately, so that they do not give the wrong answer or no response. The difficulty of getting specific information about hearing impairments that can be asked properly is asking someone who understands that it still cannot be found on search engines on the internet which is a favorite tool for most people in obtaining information. By using Machine Learning and with the help of Artificial Intelligence, a question and answer (conversation) interaction mechanism is created to gain literacy knowledge that supports the educational process. Therefore, the CHATBOT application was developed in this study as a media for retrieving information about hearing loss. Using the NLP method and the Naïve Bayes Algorithm for classifications used to get input classes to I-Chat Bot, as well as to test hypotheses using the Technology Acceptance Model developed (extended). The result is an I-Chat Bot with artificial intelligence that understands user input and provides an appropriate response and produces a preferred and easy system model to be used in the search for information about required hearing impairments. This result paper also gets the value of the test accuracy with Precision 98.6%, Recall 88.75% and Accuracy 88.75%.