The Sriwijaya University Library

  • Home
  • Information
  • News
  • Help
  • Login
  • Librarian
  • Member Area
  • Select Language :
    Arabic Bengali Brazilian Portuguese English Espanol German Indonesian Japanese Malay Persian Russian Thai Turkish Urdu

Search by :

ALL Author Subject ISBN/ISSN Advanced Search

Last search:

{{tmpObj[k].text}}
Image of SISTEM REKOMENDASI BOARD GAME HYBRID MENGGUNAKAN JARINGAN SIAMESE DENGAN FUNGSI CONTRASTIVE DAN TRIPLET LOSS
Bookmark Share

Skripsi

SISTEM REKOMENDASI BOARD GAME HYBRID MENGGUNAKAN JARINGAN SIAMESE DENGAN FUNGSI CONTRASTIVE DAN TRIPLET LOSS

Diansyah, M. Zaky - Personal Name;

This research addresses the challenge users face in discovering board games that align with their preferences, particularly when those preferences are expressed descriptively in text. Traditional recommendation systems often struggle to capture the semantic nuances within natural language queries and effectively balance these with specific attribute criteria. To overcome this limitation, this study develops and evaluates a hybrid recommendation system integrating deep semantic understanding with structured attribute filtering. The system employs a Siamese DistilBERT network architecture, fine-tuned to learn semantic representations from board game descriptions. Eight model configurations were systematically evaluated, comparing the effectiveness of Contrastive Loss and Triplet Loss functions using a holistic suite of custom evaluation metrics. Experimental results indicate that the model trained with Contrastive Loss using a margin of 0.5 (Configuration 2) significantly outperformed other variants, achieving the highest Hybrid Relevance Score of 0.9397. This configuration demonstrated robustness and stability across diverse query types, confirming its superior ability to interpret thematic user intent through a "semantic-first" design philosophy. This research validates an effective architecture for a text-based board game recommender system, yielding a contextually intelligent solution capable of delivering more satisfying recommendations.


Availability
#
Central Library (Reference) T1899342025
T189934
Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1899342025
Publisher
Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025
Collation
xii, 145 hlm.; ilus.; tab.; 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
005.107
Content Type
Text
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
Rekayasa perangkat lunak
Prodi Teknik Informatika
Specific Detail Info
-
Statement of Responsibility
MI
Other version/related

No other version available

File Attachment
  • SISTEM REKOMENDASI BOARD GAME HYBRID MENGGUNAKAN JARINGAN SIAMESE DENGAN FUNGSI CONTRASTIVE DAN TRIPLET LOSS
Comments

You must be logged in to post a comment

The Sriwijaya University Library
  • Information
  • Services
  • Librarian
  • Member Area

About Us

As a complete Library Management System, SLiMS (Senayan Library Management System) has many features that will help libraries and librarians to do their job easily and quickly. Follow this link to show some features provided by SLiMS.

Search

start it by typing one or more keywords for title, author or subject

Keep SLiMS Alive Want to Contribute?

© 2026 — Senayan Developer Community

Powered by SLiMS
Select the topic you are interested in
  • Computer Science, Information & General Works
  • Philosophy & Psychology
  • Religion
  • Social Sciences
  • Language
  • Pure Science
  • Applied Sciences
  • Art & Recreation
  • Literature
  • History & Geography
Icons made by Freepik from www.flaticon.com
Advanced Search
Where do you want to share?