Dwi Sri Rahayu, - (2024) ANALISIS SENTIMEN CHATGPT MENGGUNAKAN ALGORITMA MULTINOMIAL NAIVE BAYES CLASSIFIER (NBC). Skripsi thesis, Universitas Islam Negeri Sultan Syarif Kasim Riau.
|
Text
tugasakhir.pdf Download (16MB) | Preview |
Abstract
Dwi Sri Rahayu (2024): ANALISIS SENTIMEN CHATGPT MENGGUNAKAN ALGORITMA MULTINOMIAL NAIVE BAYES CLASSIFIER (NBC) Chatbots have become one of the most popular solutions to improve customer service. One well-known chatbot is ChatGPT, a language model developed by OpenAI. As time goes by and more and more people use ChatGPT, sentiment analysis is needed regarding user opinions regarding the ChatGPT service. Therefore, it is necessary to carry out sentiment analysis of the ChatGPT service on Twitter to find out how users respond to this chatbot service. One algorithm of the sentiment analysis method that can be used is the Multinominal Naïve Bayes Classifier (NBC) algorithm. The advantage of this algorithm is that it is relatively easy to implement and runs fast in processing. In this research, the results showed a positive sentiment of 57%, a negative sentiment of 29%, and a neutral sentiment of 14%. Obtained topics for each sentiment and sentiment prediction results from 40% of test data, with results of 96% positive, 3.5% negative, and 0.5% neutral with a test accuracy of 63%.
| Item Type: | Thesis (Skripsi) | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||
| Subjects: | 000 Karya Umum > 004 Pemrosesan Data, Ilmu Komputer, Teknik Informatika 000 Karya Umum |
||||||||
| Divisions: | Fakultas Sains dan Teknologi > Sistem Informasi | ||||||||
| Depositing User: | fsains - | ||||||||
| Date Deposited: | 09 Jul 2024 02:54 | ||||||||
| Last Modified: | 09 Jul 2024 02:54 | ||||||||
| URI: | http://repository.uin-suska.ac.id/id/eprint/80813 |
Actions (login required)
 |
View Item |