Pengambilan Keputusan Multi Kriteria Berbasis Aspect Based Sentiment Analysis untuk Mengoptimalkan Pemilihan Restoran

Firmanto, Ari (2019) Pengambilan Keputusan Multi Kriteria Berbasis Aspect Based Sentiment Analysis untuk Mengoptimalkan Pemilihan Restoran. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 05111750010001-Master_Thesis.pdf Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Ulasan produk dapat digunakan sebagai saran bagi perusahaan untuk meningkatkan layanan mereka di era digitalisasi ini. Ulasan ini dapat disajikan secara lebih rinci menggunakan aspect-based sentiment analysis. Dari aspek berbasis sentiment analisis ini, rekomendasi berbasis multikriteria dapat digunakan dalam pemilihan produk. Di dalam penelitian ini, metode analisis sentimen berbasis aspek diusulkan menggunakan aturan tata bahasa, kesamaan kata, dan SentiCircle. Metode ini dimulai dengan mengekstraksi aturan aspek kandidat berdasarkan pendeteksian frasa di constituency parse. Aspek kandidat dikategorikan menggunakan kesamaan kata. Kesamaan kata menghitung nilai kesamaan antara aspek kandidat dan kata kunci yang diperoleh dari Wikipedia. Untuk menentukan polaritas sentimen, SentiCircle digunakan. SentiCircle dapat menangkap sentimen kontekstual dari data. Dan hasil dari sentiment analisis berbasis aspek ini digunakan sebagai nilai kriteria pada metode Multi Criteria Decision Making (MCDM) dalam memberikan rekomendasi yang optimal kepada pengguna. Hasil penelitian menunjukkan bahwa metode yang diusulkan mampu mengkategorikan aspek dengan benar, dengan nilai ukuran f1-measure tertinggi 84%, sedangkan analisis sentimen menghasilkan ukuran f1-measure tertinggi 87%. Sedangkan untuk MCDM, akurasi terbaik diperoleh metode ARAS dengan akurasi sebesar 88%, MOORA dengan akurasi sebesar 84%, dan TOPSIS dengan akurasi sebesar 72%.
=====================================================================================================================================
Product reviews can be used as suggestion for companies to improve their services in this digitalization era. These reviews can be presented in more detail using aspect-based sentiment analysis. From this sentiment-based analysis aspect, multicriteria based recommendations can be used in product selection. In this research, aspect-based sentiment analysis method is proposed using grammatical rules, word similarity, and SentiCircle. This method began with extracting the candidate aspects rules based on phrase detection in constituency parse. The candidate aspects were categorized using word similarity. Word similarity calculated the similarity value between the candidate aspects and the keywords obtained from Wikipedia. To determine sentiment polarity, SentiCircle is used. SentiCircle can capture the contextual sentiment from the data. The results of aspect-based analysis sentiment are used as criteria values in the Multi Criteria Decision Making (MCDM) method in providing optimal recommendations to users. The result showed that the proposed method was able to categorize aspects correctly, with the highest f1-measure value of 84%, while sentiment analysis produced the highest f1-measure of 87%. As for MCDM, the best accuracy was obtained by the ARAS method with an accuracy of 88%, MOORA with an accuracy of 84%, and TOPSIS with an accuracy of 72%.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	aspect-based sentiment analysis, pengambilan keputusan multikriteria, aspect categorization, word similarity, senticircle
Subjects:	T Technology > T Technology (General) > T58.6 Management information systems T Technology > T Technology (General) > T58.62 Decision support systems
Divisions:	Faculty of Information and Communication Technology > Informatics > 55101-(S2) Master Thesis
Depositing User:	Ari Firmanto
Date Deposited:	23 Jul 2026 07:52
Last Modified:	23 Jul 2026 07:52
URI:	http://repository.its.ac.id/id/eprint/68332

Actions (login required)

View Item