COMPARISON ACCURACY OF WORD EMBEDDING WORD2VEC, GLOVE, DAN FASTTEXT USING SUPPORT VECTOR MACHINE FOR SENTIMENT ANALYSIS SPOTIFY APP REVIEWS

Margaretha Anjani, . (2023) COMPARISON ACCURACY OF WORD EMBEDDING WORD2VEC, GLOVE, DAN FASTTEXT USING SUPPORT VECTOR MACHINE FOR SENTIMENT ANALYSIS SPOTIFY APP REVIEWS. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (36kB)
[img] Text
AWAL.pdf
Download (1MB)
[img] Text
BAB 1.pdf
Download (143kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (384kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (308kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (497kB)
[img] Text
BAB 5.pdf
Download (105kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (170kB)
[img] Text
DAFTAR RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (43kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (10MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (328kB)

Abstract

Spotify is an application that is used as a digital audio streaming service platform that presents a variety of music and podcasts and can be downloaded for free on the Google Play Store. Reviews are a feature of the Google Play Store that can be used by users to rate an application. The reviews that an app can receive may affect the users who will download the app. Characteristics of unstructured review texts will be a challenge in the text processing process. To produce a valid sentiment analysis, it is necessary to apply word embedding. The data set that is owned is divided by a ratio of 80:20 for training data and testing data. The method used for the expansion of the Word2Vec, GloVe, and FastText features and the method used in the classification is the Support Vector Machine (SVM). The three word embedding methods were chosen because they can capture the semantic, syntactic, and contextual meanings around words when compared to traditional engineering features such as Bag of Word. The best performance evaluation results show that the GloVe model produces the best performance compared to other word embeddings with an accuracy value of 85%, a precision value of 90%, a recall value of 79%, and an f1-score of 85%.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil : 1910511108] [Pembimbing : Helena Nurramdhani Irmanda] [Penguji 1 : Bambang Saras Yulistiawan] [Penguji 2 : Ati Zaidiah]
Uncontrolled Keywords: word2vec, glove, fasttext, support vector machine, classification, sentiment analysis
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Margaretha Anjani
Date Deposited: 25 Jul 2023 06:40
Last Modified: 25 Jul 2023 06:40
URI: http://repository.upnvj.ac.id/id/eprint/24529

Actions (login required)

View Item View Item