Febby Milani, . (2024) RANCANG BANGUN MODEL CHATBOT PADA SISTER BKD KEMDIKBUD MENGGUNAKAN METODE LONG SHORT-TERM MEMORY. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (181kB) |
|
Text
AWAL.pdf Download (855kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (24kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (237kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (165kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (9kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (79kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (35kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (476kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (9MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (423kB) |
Abstract
The Directorate of Resources under the Ministry of Education, Culture, Research, and Technology manages academic resources by providing services such as Credit Point Assessment (PAK), Lecturer Certification, Lecturer Workload (BKD), and Credit Point Assessment for Educational Personnel (Tendik). The Integrated Resource Information System (SISTER) is designed to integrate these services, focusing on BKD management for educators in Indonesia. Currently, the reliance on email for helpdesk consultations results in inefficiencies and slow manual responses. To address this issue, this research proposes the development of a chatbot utilizing Long Short-Term Memory (LSTM) to enhance the flexibility and accessibility of information services. LSTM is chosen for its effectiveness in handling sequential data, which improves the chatbot's ability to understand and respond to user queries quickly and accurately. This study aims to develop an LSTM-based chatbot specifically for frequently asked questions related to BKD within SISTER Kemendikbud. Evaluations show promising results, with the LSTM achieving up to 100% accuracy and a loss as low as 2.11%. Enhancements in model architecture and the diversity of training data significantly contribute to this accuracy improvement. The findings of this research demonstrate great potential for improving the functionality and efficiency of information services within SISTER.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010511060] [Pembimbing: Ika Nurlaili Isnainiyah] [Penguji 1: Indra Permana Solihin] [Penguji 2: Kraugusteeliana] |
| Uncontrolled Keywords: | LSTM, Chatbot, Deep Learning, Integrated System, Information Services |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | FEBBY MILANI |
| Date Deposited: | 04 Sep 2024 07:59 |
| Last Modified: | 05 Sep 2024 02:28 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31698 |
Actions (login required)
 |
View Item |