NABILA, PUTRI (2026) PENERAPAN SEMANTIC TEXT MATCHING BERBASIS SENTENCE-BERT PADA FITUR LOST AND FOUND UNTUK MENINGKATKAN AKURASI PENCARIAN DI APLIKASI DORMI UNIVERSITAS MERCU BUANA. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (532kB) | 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 (43kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (200kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (179kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (957kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (31kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (94kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (781kB) |
Abstract
This study focuses on the development of a Lost and Found feature for the Dormi (Smart Dormitory Management System) platform by implementing a Semantic Text Matching technique based on the Sentence-BERT (S-BERT) model. The feature aims to overcome the limitations of conventional lost-item reporting systems, which rely on exact keyword matching and do not consider the semantic meaning of item descriptions. The research adopts the Design Science Research (DSR) framework, with an Agile–Iterative approach employed as the technical development methodology. The development process includes problem identification, system design, implementation, and iterative evaluation. Technically, the S-BERT model is used to generate 768-dimensional semantic vector representations of item descriptions, while cosine similarity is applied to measure the semantic similarity between lost and found item reports. The expected outcome of this study is a Lost and Found feature that operates accurately, responsively, and is fully integrated into the Dormi ecosystem, thereby supporting the digitalization of dormitory management and significantly enhancing the resident experience. Kata kunci: Sentence-BERT, Semantic Text Matching, Lost and Found, Smart Dormitory, NLP. Penelitian ini berfokus pada pengembangan fitur Lost and Found dalam platform Dormi (Smart Dormitory Management System) dengan menerapkan teknik Semantic Text Matching yang didukung model Sentence-BERT (S-BERT). Fitur ini hadir sebagai jawaban atas keterbatasan sistem pelaporan barang hilang yang selama ini hanya mampu mencocokkan kata secara harfiah, tanpa mempertimbangkan kesamaan makna di balik kalimat yang digunakan. Pengembangan sistem dilaksanakan menggunakan kerangka Design Science Research (DSR) dengan pendekatan Agile-Iterative sebagai metode pengembangan teknisnya, mencakup tahap identifikasi masalah, perancangan sistem, implementasi, dan evaluasi secara bertahap. Pada sisi teknis, model S-BERT berperan dalam menghasilkan representasi semantik kalimat dalam bentuk vektor berdimensi 768, sedangkan cosine similarity dimanfaatkan untuk mengukur kedekatan makna antar deskripsi barang. Luaran yang diharapkan dari penelitian ini adalah sebuah fitur Lost and Found yang mampu bekerja secara akurat, responsif, dan terintegrasi penuh dalam ekosistem Dormi, sehingga pengelolaan asrama menjadi lebih terdigitalisasi dan pengalaman penghuni meningkat secara signifikan. Kata kunci: Sentence-BERT, Semantic Text Matching, Lost and Found, Smart ormitory, NLP.
Actions (login required)
 |
View Item |
