Aspect Term Extraction Using Deep Learning-Based Approach on Indonesian Restaurant Reviews
RACHMANSYAH ADHI WIDHIANTO
Informasi Umum
Kode
21.04.1362
Klasifikasi
C -
Jenis
Karya Ilmiah - Skripsi (S1) - Reference
Subjek
Natural Language Processing
Dilihat
384 kali
Informasi Lainnya
Abstraksi
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%.
Koleksi & Sirkulasi
Seluruh 1 koleksi sedang dipinjam
Anda harus log in untuk mengakses flippingbook
Pengarang
| Nama | RACHMANSYAH ADHI WIDHIANTO |
| Jenis | Perorangan |
| Penyunting | |
| Penerjemah |
Penerbit
| Nama | Universitas Telkom |
| Kota | |
| Tahun | 2021 |
Sirkulasi
| Harga sewa | IDR 0,00 |
| Denda harian | IDR 0,00 |
| Jenis | Non-Sirkulasi |
