Explicit and Implicit Aspect Extraction using Whale Optimization Algorithm and Hybrid Approach

DOI

10.2991/icoiese-18.2019.37How to use a DOI?

Keywords

explicit aspect; implicit aspect; rule patterns; rule pattern selection

Abstract

Huge volume of reviews by customers published on different products websites has become an important source of information for both customers and companies. Customers require the information to help them in decision making for buying products, while companies analyze these reviews to improve their products. However, reading and analyzing huge amount of reviews manually are impossible and cumbersome. Thus, an automatic technique known as sentiment analysis or opinion mining has been used to analyze these reviews and extract the relevant information according to different users’ needs. The growth of sentiment analysis has resulted in the emergence of various techniques for explicit aspect extraction and implicit aspect extraction. In this paper, we proposed new approaches for both explicit and implicit aspect extraction. For explicit aspect extraction, we proposed to use Whale Optimization Algorithm (WOA) for selecting the best dependency relation patterns from the list of hand-craft patterns with the help of web based similarity. As for the implicit aspect extraction, we proposed a hybrid approach based on the use of corpus co-occurrence, dictionary-based, and web based similarity. To measure the performance of the proposed approaches, the approaches will tested and evaluated using standard datasets and will be compared to other baseline methods.

Copyright

© 2019, 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  - Mohammad Tubishat
AU  - Norisma Idris
PY  - 2019/03
DA  - 2019/03
TI  - Explicit and Implicit Aspect Extraction using Whale Optimization Algorithm and Hybrid Approach
BT  - Proceedings of the 2018 International Conference on Industrial Enterprise and System Engineering (IcoIESE 2018)
PB  - Atlantis Press
SP  - 208
EP  - 213
SN  - 2589-4943
UR  - https://doi.org/10.2991/icoiese-18.2019.37
DO  - 10.2991/icoiese-18.2019.37
ID  - Tubishat2019/03
ER  -