HIDAYAT, ADIKA FARIS MURTADHA (2026) PENGEMBANGAN AI TO-DO ANALYZER MENGGUNAKAN METODE NAMED ENTITY RECOGNITION BERBASIS INDOBERT UNTUK OTOMASI PENJADWALAN TUGAS. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (581kB) | 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 (100kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (110kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (60kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (454kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (28kB) |
|
|
Text (DAFTAR PUSTAKA)
07 Daftar Pustaka.pdf Restricted to Registered users only Download (153kB) |
|
|
Text (LAMPIRAN)
08 Lampiran.pdf Restricted to Registered users only Download (802kB) |
Abstract
Unstructured task management often leads to high cognitive load and academic procrastination. Although many to-do list apps have been developed, most are still passive and require inefficient manual data entry. This study aims to develop an AI To-Do Analyzer using an IndoBERT-based Named Entity Recognition (NER) method to automate task scheduling in Indonesian. This study produced three models built through fine-tuning IndoBERT: a NER model to extract key entities such as task names, times, and locations from natural language input; a classifier model to classify task priorities based on the Eisenhower Matrix into four quadrants (Q1–Q4); and a classifier model to determine the need to decompose tasks into subtasks. The methodology used was quantitative experimental, encompassing primary data collection via surveys, data annotation using the BIO format, and model training using the Transformer architecture. The research results show that the NER model achieved an F1-Score of 0.92, the Eisenhower classifier achieved 93% accuracy, and the subtask classifier achieved 99% accuracy, as evaluated using the Precision, Recall, and F1-Score metrics. All three models were implemented in a Flutter-based mobile app prototype with a FastAPI backend. The contribution of this research is to provide an AI model capable of understanding variations in informal Indonesian to reduce decision fatigue and automatically improve time management efficiency. Kata kunci: Artificial Intelligence, IndoBERT, Named Entity Recognition, Task Scheduling, Indonesian Language. Manajemen tugas yang tidak terstruktur sering kali menyebabkan beban kognitif tinggi dan prokrastinasi akademik. Meskipun aplikasi to-do list telah banyak dikembangkan, sebagian besar masih bersifat pasif dan memerlukan entri data manual yang tidak efisien. Penelitian ini bertujuan untuk mengembangkan AI ToDo Analyzer menggunakan metode Named Entity Recognition (NER) berbasis IndoBERT untuk otomasi penjadwalan tugas dalam Bahasa Indonesia. Penelitian ini menghasilkan tiga model yang dibangun melalui fine-tuning IndoBERT, yaitu model NER untuk mengekstraksi entitas penting seperti nama tugas, waktu, dan lokasi dari input bahasa alami; model classifier untuk mengklasifikasikan prioritas tugas berdasarkan Eisenhower Matrix ke dalam empat kuadran (Q1–Q4); serta model classifier untuk menentukan kebutuhan dekomposisi tugas menjadi subtugas. Metodologi yang digunakan adalah eksperimental kuantitatif, mencakup pengumpulan data primer melalui survei, anotasi data dengan format BIO, dan pelatihan model menggunakan arsitektur Transformer. Hasil penelitian menunjukkan model NER mencapai F1-Score 0,92, classifier Eisenhower mencapai akurasi 93%, dan classifier sub-tugas mencapai akurasi 99%, yang dievaluasi menggunakan metrik Precision, Recall, dan F1-Score. Ketiga model diimplementasikan dalam prototipe aplikasi mobile berbasis Flutter dengan backend FastAPI. Kontribusi penelitian ini adalah menyediakan model AI yang mampu memahami variasi bahasa Indonesia non-formal guna mengurangi decision fatigue dan meningkatkan efisiensi manajemen waktu secara otomatis. Kata kunci: Artificial Intelligence, IndoBERT, Named Entity Recognition, Penjadwalan Tugas, Bahasa Indonesia.
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41822010137 |
| Uncontrolled Keywords: | Artificial Intelligence, IndoBERT, Named Entity Recognition, Penjadwalan Tugas, Bahasa Indonesia. |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.3 Artificial Intelligence/Kecerdasan Buatan 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.4 Computer Pattern Recognition/Pola Pengenalan Komputer |
| Divisions: | Fakultas Ilmu Komputer > Sistem Informasi |
| Depositing User: | khalimah |
| Date Deposited: | 07 Sep 2026 02:18 |
| Last Modified: | 07 Sep 2026 02:18 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/103666 |
Actions (login required)
 |
View Item |
