ANALISIS SENTIMEN ULASAN PENGGUNA PADA APLIKASI GOOGLE CLASSROOM MENGGUNAKAN METODE SUPPORT VECTOR MACHINE DAN SELEKSI FITUR PARTICLE SWARM OPTIMIZATION

Ghaitsa Amany Mursianto, . (2022) ANALISIS SENTIMEN ULASAN PENGGUNA PADA APLIKASI GOOGLE CLASSROOM MENGGUNAKAN METODE SUPPORT VECTOR MACHINE DAN SELEKSI FITUR PARTICLE SWARM OPTIMIZATION. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (134kB)
[img] Text
AWAL.pdf
Download (819kB)
[img] Text
BAB 1.pdf
Download (88kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (239kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (217kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (450kB)
[img] Text
BAB 5.pdf
Download (71kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (89kB)
[img] Text
DAFTAR RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (27kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (9MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (525kB)

Abstract

The PSBB policy requires the implementation of online distance learning activities using online-based applications such as Google Classroom. Using Google Classroom facilitates its users to distribute, collect, and assess assignments given to students and students across the country. This study aims to determine the sentiment of public opinion towards the Google Classroom application. In conducting sentiment analysis, this study used the Support Vector Machine (SVM) method and the Particle Swarm Optimization (PSO) optimization method as a feature selection. Data collection was carried out using scraping techniques with a total of 950 comments in Indonesian. Then the data will provide labeling between the positive label and the negative label by the anatator, after being given the labeling will be continued with pre-processing data such as, case folding, data cleaning, normalization, stemming, stopword removal, and tokenizing then the data that has gone through that process will proceed to the process of weighting words with Term Frequency – Inverse Document Frequency (TF -DF). Then the data that has been obtained will be divided into 80% of training data (train) and 20% of test data (testing). The algorithm used in this classification is the Support Vector Machine (SVM) using the Particle Swarm Optimization (PSO) optimization method against Google Classroom sentiment analysis. The classification results obtained from the average evaluation of confussion matrix with the SVM method are accuracy of 79%, precision of 78%, recall of 67% and using the PSO optimization method obtains accuracy results of 83%, precision of 86%, recall of 67% with an iteration of 950. From the results of this classification, the SVM method coupled with the PSO optimization method is able to increase the accuracy value by 4%.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1810511041] [Pembimbing 1: Didit Widiyanto] [Pembimbing 2: Bambang Tri Wahyono] [Penguji 1: Bayu Hananto] [Penguji 2: Nurul Chamidah]
Uncontrolled Keywords: Sentiment analysis, Classification, TF-IDF, Pre-processing, Google Classroom, Support Vector Machine (SVM), Particle Swarm Optimization (PSO).
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Ghaitsa Amany Mursianto
Date Deposited: 10 Aug 2022 05:15
Last Modified: 10 Aug 2022 06:31
URI: http://repository.upnvj.ac.id/id/eprint/19677

Actions (login required)

View Item View Item