Responsive Chatbot Using Named Entity Recognition and Cosine Similarity

Entin Martiana Kusumaningtyas, Ekky Laurentino, Ali Barakbah

2022

Abstract

Most of the higher education student service systems in Indonesia still use conventional and web-based system to provide academic information to students. This reduces the effectiveness of students in obtaining academic information. In the conventional system, students must visit the academic service center only to obtain academic information. In the web-based system, students can access information anywhere, but students also have to look for the right menu to obtain the academic information needed. This research proposes a chatbot application to help students of Electronic Engineering Institute o Surabaya (EEPIS) obtain information effectively and interactively. This application allows students to ask questions related to academic regulations, grades, class schedules, and attendance recap. This research processes student question using Named Entity Recognition method, this method can recognize the entities contained in the questions asked by the user. To improve the ability of Named Entity Recognition (NER) method to handle words, we also implement synonym checking and keyword matching process. The result entities of previous process will be calculated its proximity to the keywords in the database using cosine similarity to find the right answer. The result of this study showed an accuracy of 84.5% with testing 84 questions obtain 71 accurate answer.

Paper Citation

in Harvard Style

Martiana Kusumaningtyas E., Laurentino E. and Barakbah A. (2022). Responsive Chatbot Using Named Entity Recognition and Cosine Similarity. In Proceedings of the 5th International Conference on Applied Science and Technology on Engineering Science - Volume 1: iCAST-ES; ISBN 978-989-758-619-4, SciTePress, pages 239-245. DOI: 10.5220/0011756300003575

in Bibtex Style

@conference{icast-es22,
author={Entin Martiana Kusumaningtyas and Ekky Laurentino and Ali Barakbah},
title={Responsive Chatbot Using Named Entity Recognition and Cosine Similarity},
booktitle={Proceedings of the 5th International Conference on Applied Science and Technology on Engineering Science - Volume 1: iCAST-ES},
year={2022},
pages={239-245},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011756300003575},
isbn={978-989-758-619-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Conference on Applied Science and Technology on Engineering Science - Volume 1: iCAST-ES
TI - Responsive Chatbot Using Named Entity Recognition and Cosine Similarity
SN - 978-989-758-619-4
AU - Martiana Kusumaningtyas E.
AU - Laurentino E.
AU - Barakbah A.
PY - 2022
SP - 239
EP - 245
DO - 10.5220/0011756300003575
PB - SciTePress