Fisya Alifia Fawwazi Siregar, . (2024) ANALISIS SENTIMEN BERBASIS ASPEK PADA ULASAN APLIKASI MYTELKOMSEL MENGGUNAKAN ALGORITMA NAÏVE BAYES DAN METODE TF-IDF. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
Text
ABSTRAK.pdf Download (238kB) |
|
Text
AWAL.pdf Download (1MB) |
|
Text
BAB I.pdf Download (279kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (389kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (4MB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB V.pdf Download (187kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (197kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (14kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (2MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (687kB) |
Abstract
MyTelkomsel is a service in the form of an application provided by Telkomsel as one of the cellular operators that is widely used in Indonesia. Through reviews on the Google Play Store, users can find out the experiences of other users. However, the presence of a high rating with positive and negative reviews on MyTelkomsel does not guarantee that user expectations are met, so evaluation must still be carried out. This happens because it is not uncommon for users to give high ratings but with negative reviews. Apart from that, the development team can also find out which aspects have advantages and disadvantages, so they must be paid attention to as material for future evaluation. In this research, the Naïve Bayes algorithm and the TF-IDF method were used to carry out aspect-based sentiment analysis on reviews of the MyTelkomsel application, with the aim of knowing the performance of the Naïve Bayes algorithm by grouping reviews into four aspects of Nielsen's Model, namely learnability, efficiency, error, and satisfaction and two classes, namely positive and negative. Nielsen's Model is used as a benchmark to determine the strengths and weaknesses of the MyTelkomsel application. In this research, 1000 data were used in the form of user reviews taken using scrapping techniques on the Google Play Store. The results of this research obtained accuracy ranging from 79% to 93%. Apart from that, it was found that the advantages of this application were in the learnability aspect. Meanwhile, the weaknesses in this application are in the aspects of satisfaction, learnability and errors.
Item Type: | Thesis (Skripsi) |
---|---|
Additional Information: | [No.Panggil: 2010512060] [Pembimbing 1 : Ika Nurlaili Isnainiyah, S.Kom., M.Sc] [Pembimbing 2 : Bambang Tri Wahyono, S.Kom., M.Si] [Penguji 1 : I Wayan Widi Pradnyana, S.Kom., MTI] [Penguji 2 : Sarika, S.Kom., M.Kom] |
Uncontrolled Keywords: | Aspect-Based Sentiment Analysis, Naïve Bayes, TF-IDF, Nielsen Model, MyTelkomsel |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1) |
Depositing User: | FISYA ALIFIA FAWWAZI SIREGAR |
Date Deposited: | 09 Sep 2024 04:23 |
Last Modified: | 09 Sep 2024 04:23 |
URI: | http://repository.upnvj.ac.id/id/eprint/31520 |
Actions (login required)
View Item |