Aspect Term Extraction Using Deep Learning-Based Approach on Indonesian Restaurant Reviews
Total View This Week0
Total View This Week0
Institusion
Universitas Telkom
Author
RACHMANSYAH ADHI WIDHIANTO
Subject
Natural language processing
Datestamp
2021-07-23 00:00:00
Abstract :
Aspect extraction is a fundamental process in aspect-based sentiment analysis that aims to extract aspects from opinion texts. In this paper, we present an aspect extraction on Indonesian restaurant reviews using a deep learning-based approach. We collected and annotated Indonesian restaurant reviews dataset from one of the well-known restaurant reviews website, namely Zomato. We performed the annotation on token-level and used the following aspect labels to annotate the reviews: FOOD, PRICE, AMBIENCE, SERVICE, and MISCELLANEOUS. The experimental result shows that the LSTM model gave the best performance with micro average F1-score of aspect extraction is 55,1%.
Aspect extraction is a fundamental process in aspect-based sentiment analysis that aims to extract aspects from opinion texts. In this paper, we present an aspect extraction on Indonesian restaurant reviews using a deep learning-based approach. We collected and annotated Indonesian restaurant reviews dataset from one of the well-known restaurant reviews website, namely Zomato. We performed the annotation on token-level and used the following aspect labels to annotate the reviews: FOOD, PRICE, AMBIENCE, SERVICE, and MISCELLANEOUS. The experimental result shows that the LSTM model gave the best performance with micro average F1-score of aspect extraction is 55,1%.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
