Muhammad Zul Fikar, . (2024) ANALISIS SENTIMEN PENGGUNA CHATGPT BERDASARKAN ULASAN PADA GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA NAÏVE BAYES. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (254kB) |
|
Text
AWAL.pdf Download (695kB) |
|
Text
BAB 1.pdf Download (274kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (356kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (363kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (4MB) |
|
Text
BAB 5.pdf Download (255kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (266kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (164kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (4MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (4MB) |
Abstract
Artificial Intelligence (AI) has achieved remarkable advancements in recent years. ChatGPT, developed by OpenAI, is an AI that can generate text, translate languages, write various types of creative content, and answer questions in an informative manner. With its growing popularity, there is a need to understand how users perceive and experience this application. The quality evaluation can be conducted through sentiment analysis, a technique for identifying and understanding users' opinions or sentiments based on their reviews. This study employs the Naïve Bayes method to analyze user sentiment towards the ChatGPT application based on reviews from the Google Play Store. The review data collected ranges from July 2023 to February 2024 and is manually labeled by three annotators. The data undergoes various stages before classification, including preprocessing, word weighting using the Term Frequency – Inverse Document Frequency (TF-IDF) method, and data splitting. The results of the study show that the Naïve Bayes classification model produces good accuracy, with an accuracy rate of 86%, precision of 82%, recall of 98%, and an F1-score of 89% using an 80:20 training and test data ratio. In addition to the classification results, the study also creates data visualizations in the form of word clouds to identify key words frequently appearing in positive and negative reviews. Another outcome of the study is a simple system to predict labels based on the given review data.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010512091] [Pembimbing 1: Nurhafifah Matondang] [Pembimbing 2: Sarika] [Penguji 1: Iin Ernawati] [Penguji 2: Bambang Triwahyono] |
| Uncontrolled Keywords: | Sentiment Analysis, ChatGPT, Naïve Bayes, Artificial Intelligence |
| 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: | MUHAMMAD ZUL FIKAR |
| Date Deposited: | 09 Sep 2024 04:19 |
| Last Modified: | 09 Sep 2024 04:19 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31875 |
Actions (login required)
 |
View Item |