Replies Identification in Question Answering System using Vector Space Model

DOI

10.2991/icst-18.2018.96How to use a DOI?

Keywords

question answering system; vector space model; information retrieval; data mining

Abstract

Automatic question answering system is an information retrieval system designed to return an answer to a specific question. It is a base system for a chatbot application. This research aims to identify responses in a question answering system using Vector Space Model (VSM). The system compared query questions to possible answers stored in the repository, and the top ten highest similarity results are returned. Dataset used is from students’ questionnaires about final project essay and field practice, which are specific topics of interest often asked to program coordinator. There are 100 questions and answers, and the result gives 0.413 average precision, 0.893 average recall, and 0.563 average F-Measure.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Intan Yuniar Purbasari
AU  - Fetty Tri Anggraeny
AU  - Masti Fatchiyah Maharani
PY  - 2018/12
DA  - 2018/12
TI  - Replies Identification in Question Answering System using Vector Space Model
BT  - Proceedings of the International Conference on Science and Technology (ICST 2018)
PB  - Atlantis Press
SP  - 459
EP  - 464
SN  - 2589-4943
UR  - https://doi.org/10.2991/icst-18.2018.96
DO  - 10.2991/icst-18.2018.96
ID  - Purbasari2018/12
ER  -