Hary Witriyono
Unknown Affiliation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Implementasi Metode Pattern-Based Natural Language Processing (NLP) Pada Chatbot Rahayu, Tri; Agung Kharisma Hidayah; Hary Witriyono; Khairullah; RG Guntur Alam
JSAI (Journal Scientific and Applied Informatics) Vol 7 No 3 (2024): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v7i3.6739

Abstract

Natural Language Processing (NLP) based chatbots are increasingly used in various applications, ranging from customer service to education. One simple yet effective approach to implementing NLP on a chatbot is the pattern-based method, which uses language patterns to understand and respond to user input. This research aims to implement the pattern-based NLP method on a chatbot and evaluate its performance using the BLEU metric. Conversation data is collected and analyzed to identify common patterns, which are then mapped into appropriate responses. Testing was done by measuring the level of bigram match between the chatbot response and the reference response, where the BLEU-2 precision reached a value of 0.75 or 75%. These results show that the pattern-based method is capable of generating relevant responses but still requires refinement to achieve higher accuracy.