Analisis Sentimen Pada Ulasan Hotel Dengan Fitur Score Representation Dan Identifikasi Aspek Pada Ulasan Menggunakan K-Modes

Azhar, Muhammad Hafiz (2018) Analisis Sentimen Pada Ulasan Hotel Dengan Fitur Score Representation Dan Identifikasi Aspek Pada Ulasan Menggunakan K-Modes. Sarjana thesis, Universitas Brawijaya.

Abstract

Dengan meningkatnya jumlah data ulasan yang masuk, perlu dibuat sebuah sistem yang dapat melakukan klasifikasi suatu ulasan termasuk ke dalam kelas apa, dalam kasus ini terdapat kelas positif dan negatif. Selain itu, perlu diketahui juga ulasan tersebut cenderung membahas tentang aspek apa. Pada penelitian ini dilakukan analisis sentimen pada tingkat aspek dengan klasterisasi menggunakan fitur Bag of Nouns untuk mendapatkan aspek dan klasifikasi sentimen dengan fitur score representation untuk melakukan analisis sentimen. Dengan tipe atribut yang berupa kategoris pada fitur Bag of Nouns, untuk melakukan klasterisasi lebih cocok digunakan algoritme K-Modes yang merupakan modifikasi K-Means. Pada klasifikasi sentimen, fitur score representation digunakan untuk LVQ2 yang dapat menangani hubungan antar atribut dan dapat menjadi alternatif dari algoritme pembelajaran mesin yang lain. Hasil dari penelitian ini menunjukkan jumlah klaster optimal adalah 7 klaster untuk data dengan kelas seimbang dan 5 klaster untuk data dengan kelas tidak seimbang. Kemudian, nilai rata-rata precision, recall, dan f1-score untuk data dengan kelas seimbang memberikan hasil precision 89,2%, recall 89,13%, dan f1-score 89,12% dengan menggunakan parameter optimal. Untuk data dengan kelas tidak seimbang memberikan hasil precision 87,38%, recall 73,07%, dan f1-score 76,46% dengan menggunakan parameter optimal. Bisa disimpulkan bahwa ekstraksi fitur dengan score representation ini dapat digunakan untuk proses klasifikasi sentimen.

English Abstract

As the number of review is rising, there is a need to make a system that can do classify a review belong to which class, in this case there are positive and negative classes. Furthermore, we also need to know what aspect that commented in the review. In this research, sentiment analysis at aspect level, Bag of Nouns feature has been used for clustering to get aspect and sentiment classification with score representation feature to classify sentiment. With categorical attribute for Bag of Nouns feature, K-Modes as the modification of K-Means is considered capable for clustering. In sentiment classification, score representation has been used for LVQ2 that can handle the correlation between attribute and also become alternative for another machine learning algorithm. Based on the evaluation with Silhouette Coefficient, the optimal number for clustering balanced data set is 7 cluster and 5 cluster for unbalanced data set. Based on the evaluation with precision, recall, and f1-score, the performance of the balanced data set are 89,2% for precision, 89,13% for recall, and 89,12% for f1-score. The evaluation for unbalanced data set are 87,38% for precision, 73,07% for recall, and 76,46% for f1-score. It can be concluded feature extraction with score representation can be used for sentiment classification process.

Item Type:	Thesis (Sarjana)
Identification Number:	SKR/FTIK/2018/180/051801202
Uncontrolled Keywords:	Analisis Sentimen, Ulasan Hotel, K-Modes, Jaringan Saraf Tiruan, LVQ2, Ekstraksi Fitur
Subjects:	000 Computer science, information and general works > 005 Computer programming, programs, data > 005.1 Programming
Divisions:	Fakultas Ilmu Komputer > Teknik Informatika
Depositing User:	Yusuf Dwi N.
Date Deposited:	24 May 2018 06:57
Last Modified:	26 Oct 2021 09:27
URI:	http://repository.ub.ac.id/id/eprint/11014

	Text BAB V.pdf Download (952kB)
	Text Lampiran.pdf Download (753kB)
	Text BAB VI.pdf Download (861kB)
	Text Daftar Pustaka.pdf Download (392kB)
	Text BAB VII.pdf Download (543kB)
	Text Bagian Depan.pdf Download (821kB)
	Text BAB II.pdf Download (885kB)
	Text BAB I.pdf Download (555kB)
	Text BAB IV.pdf Download (1MB)
	Text BAB III.pdf Download (888kB)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (54kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (20kB)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (8kB)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (1kB)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (40kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (13kB)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (4kB)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (1kB)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (28kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (10kB)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (4kB)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (1kB)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (36kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (12kB)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (4kB)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (1kB)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (15kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (6kB)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (3kB)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (1kB)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (32kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (11kB)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (4kB)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (1kB)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (15kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (7kB)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (2kB)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (1kB)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (21kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (8kB)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (3kB)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (1kB)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (22kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (9kB)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (3kB)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (1kB)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (34kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (12kB)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (4kB)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (1kB)

Actions (login required)

View Item