Abdullah Aqil Athallah, . (2025) IMPLEMENTASI CHATBOT LAYANAN PENGGUNA UNTUK MENINGKATKAN PENGALAMAN PENGGUNA PADA PT ORBIT EKA SEMESTA. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (82kB) |
|
Text
AWAL.pdf Download (706kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (132kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (286kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (215kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (5MB) |
|
Text
BAB 5.pdf Download (120kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (117kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (104kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (18MB) |
|
Text
ARTIKEL.pdf Restricted to Repository staff only Download (869kB) |
Abstract
The rapid development of information technology encourages companies to improve the quality of digital services, including through the implementation of Artificial Intelligence (AI) based chatbots. This study aims to design and implement a user service chatbot using the Rasa framework on the website of PT Orbit Eka Semesta, a company engaged in fiber optic-based internet services. The chatbot was developed through the stages of planning, designing, developing, and testing performance evaluation using the Confusion Matrix method, and functional testing and user satisfaction through Black Box Testing and User Acceptance Testing (UAT). In addition, a performance comparison was carried out between the DIETClassifier and SklearnIntentClassifier algorithms, where DIETClassifier showed superior results in Precision of 92.4% (Macro Averaged) and 92.8% (Weighted Averaged), and F1-score of 93.5% (Macro Averaged) and 94.0% (Weighted Averaged). The results of Black Box Testing on 22 chatbot features produced a 100% success rate, which shows the effectiveness of the chatbot in responding to user questions and increasing the efficiency of information services. UAT by 29 respondents showed a high level of user satisfaction, with an average score of 4.2 out of 5. Thus, the implementation of this chatbot has been proven to improve user experience and operational efficiency of the company.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110511005] [Pembimbing: Indra Permana Solihin] [Penguji 1: Bayu Hananto] [Penguji 2: Novi Trisman Hadi] |
| Uncontrolled Keywords: | Keyword: Chatbot, Rasa Framework, Confusion Matrix, UAT, Black Box Testing |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | ABDULLAH AQIL ATHALLAH |
| Date Deposited: | 11 Aug 2025 01:35 |
| Last Modified: | 11 Aug 2025 01:35 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37424 |
Actions (login required)
 |
View Item |