PUTRA, AMRULLAH VALENTINO CAESAR (2026) PENERAPAN EMBODIED CONVERSATIONAL AGENT (ECA) UNTUK MENINGKATKAN SOCIAL PRESENCE DAN USER EXPERIENCE PADA SISTEM CHATBOT FASILKOM UMB. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (558kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 Bab 1.pdf Restricted to Registered users only Download (65kB) |
|
|
Text (BAB II)
03 Bab 2.pdf Restricted to Registered users only Download (283kB) |
|
|
Text (BAB III)
04 Bab 3.pdf Restricted to Registered users only Download (345kB) |
|
|
Text (BAB IV)
05 Bab 4.pdf Restricted to Registered users only Download (157kB) |
|
|
Text (BAB V)
06 Bab 5.pdf Restricted to Registered users only Download (30kB) |
|
|
Text (DAFTAR PUSTAKA)
08 Daftar Pustaka.pdf Restricted to Registered users only Download (149kB) |
|
|
Text (LAMPIRAN)
09 Lampiran.pdf Restricted to Registered users only Download (214kB) |
Abstract
The advancement of information technology has accelerated the digital transformation of academic services in higher education institutions. However, academic information services at the Faculty of Computer Science, Mercu Buana University, are still primarily conducted through text-based communication via WhatsApp, which depends on the availability of administrative staff and does not provide a natural user interaction experience. This research aims to design and implement an Embodied Conversational Agent (ECA) interface based on a three dimensional (3D) avatar for the Faculty of Computer Science Virtual Assistant Chatbot. The implementation utilizes React Three Fiber as the primary technology for rendering a web-based 3D avatar, Avaturn for avatar generation, and Microsoft Azure Cognitive Speech Services to support Speech-to-Text (STT), Text-to-Speech (TTS), and procedural lip-sync features, enabling the avatar to communicate verbally and nonverbally in real time. This research adopts the Prototype development method, consisting of requirement analysis, system design, implementation, and evaluation. System functionality was evaluated using the Black Box Testing method to ensure that all features operated according to the specified functional requirements. The results indicate that the Virtual Assistant Chatbot interface was successfully implemented as a web-based application. All primary features, including user login, guest access, text and voice input, 3D avatar visualization, Speech-to-Text, Text-to-Speech, procedural lip-sync, avatar animation, and conversation history, functioned successfully according to the predefined testing scenarios. The integration of a three-dimensional avatar with voice-based communication provides a more natural and engaging interaction compared to conventional text-based chatbot interfaces. Therefore, the proposed system offers an alternative approach to developing more interactive academic information services within the Faculty of Computer Science, Mercu Buana University. Keywords: Embodied Conversational Agent, Virtual Assistant, React Three Fiber, 3D Avatar, Speech-to-Text, Text-to-Speech, Procedural Lip sync, Microsoft Azure Cognitive Speech Services, Black Box Testing. Perkembangan teknologi informasi telah mendorong transformasi digital pada layanan akademik di perguruan tinggi. Namun, penyampaian informasi akademik di Fakultas Ilmu Komputer Universitas Mercu Buana masih didominasi oleh komunikasi berbasis pesan teks melalui aplikasi WhatsApp yang bergantung pada ketersediaan petugas administrasi dan belum mampu memberikan pengalaman interaksi yang lebih alami. Penelitian ini bertujuan untuk merancang dan mengimplementasikan antarmuka Embodied Conversational Agent (ECA) berbasis avatar tiga dimensi (3D) pada sistem Virtual Assistant Chatbot Fasilkom UMB. Implementasi dilakukan menggunakan React Three Fiber sebagai teknologi utama dalam menampilkan avatar 3D berbasis web, Avaturn sebagai penyedia model avatar, serta Microsoft Azure Cognitive Speech Services untuk mendukung fitur Speech-to-Text, Text-to-Speech, dan procedural lip sync sehingga avatar mampu berkomunikasi secara verbal dan nonverbal secara real-time. Penelitian menggunakan metode Prototype dalam proses pengembangan sistem yang meliputi analisis kebutuhan, perancangan, implementasi, serta evaluasi. Pengujian sistem dilakukan menggunakan metode Black Box Testing untuk memastikan seluruh fungsi aplikasi berjalan sesuai kebutuhan fungsional. Hasil penelitian menunjukkan bahwa antarmuka Virtual Assistant Chatbot berhasil diimplementasikan dengan baik pada platform web. Seluruh fitur utama, meliputi login, akses sebagai guest, pengiriman pertanyaan melalui teks maupun suara, tampilan avatar tiga dimensi, Text-to-Speech, Speech-to-Text, procedural lip sync, animasi avatar, dan riwayat percakapan dapat berfungsi sesuai dengan skenario pengujian. Implementasi avatar tiga dimensi yang dipadukan dengan komunikasi berbasis suara menghasilkan interaksi yang lebih natural dibandingkan antarmuka chatbot berbasis teks, sehingga dapat menjadi alternatif pengembangan layanan informasi akademik yang lebih interaktif di lingkungan Fakultas Ilmu Komputer Universitas Mercu Buana. Kata kunci: Embodied Conversational Agent, Virtual Assistant, React Three Fiber, Avatar 3D, Speech-to-Text, Text-to-Speech, Procedural Lip sync, Microsoft Azure Cognitive Speech Services, Black Box Testing.
Actions (login required)
 |
View Item |
