<?xml version="1.0" encoding="UTF-8" ?>
<modsCollection xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.loc.gov/mods/v3" xmlns:slims="http://slims.web.id" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-3.xsd">
<mods version="3.3" ID="20387">
<titleInfo>
<title><![CDATA[PENGEMBANGAN SISTEM REKOMENDASI GAME DENGAN PENDEKATAN CONTENT-BASED FILTERING DAN METODE K-MEANS CLUSTERING]]></title>
</titleInfo>
<name type="Personal Name" authority="">
<namePart>120160503 - Nur Fitrianti Fahrudin, S.Kom., M.T.</namePart>
<role><roleTerm type="text">Dosen Pembimbing 1</roleTerm></role>
</name>
<name type="Personal Name" authority="">
<namePart>NICHOLAS RYAN GUNAWAN / 162021037</namePart>
<role><roleTerm type="text">Penulis</roleTerm></role>
</name>
<typeOfResource manuscript="yes" collection="yes"><![CDATA[mixed material]]></typeOfResource>
<genre authority="marcgt"><![CDATA[bibliography]]></genre>
<originInfo>
<place><placeTerm type="text"><![CDATA[Sistem Informasi]]></placeTerm></place>
<publisher><![CDATA[FTI]]></publisher>
<dateIssued><![CDATA[2025]]></dateIssued>
<issuance><![CDATA[monographic]]></issuance>
<edition><![CDATA[0]]></edition>
</originInfo>
<language>
<languageTerm type="code"><![CDATA[en]]></languageTerm>
<languageTerm type="text"><![CDATA[English]]></languageTerm>
</language>
<physicalDescription>
<form authority="gmd"><![CDATA[Text]]></form>
<extent><![CDATA[]]></extent>
</physicalDescription>
<note>Pertumbuhan pesat platform distribusi game digital seperti Steam membuat
pengguna semakin sulit menemukan game yang sesuai dengan preferensi dan
minat mereka. Penelitian ini bertujuan mengembangkan sistem rekomendasi
berbasis konten untuk game Steam dengan memanfaatkan TF-IDF, BERT, dan KMeans
Clustering untuk menghasilkan rekomendasi yang lebih akurat. Tiga
skema rekomendasi dievaluasi: model tiga variabel (Categories, Genres, dan
Tags), model berbasis About-the-Game saja, dan model teks hibrid, dengan Mean
Average Precision (MAP) dan Normalized Discounted Cumulative Gain (NDCG)
sebagai metrik evaluasi. Hasil eksperimen menunjukkan bahwa model tiga
variabel memberikan performa terbaik dengan NDCG sebesar 0,88 dan MAP
sebesar 0,71. Sebaliknya, model About-the-Game saja menunjukkan performa
terendah dengan NDCG sebesar 0,73 dan MAP sebesar 0,61 yang menunjukkan
bahwa informasi deskripsi game saja tidak cukup untuk menghasilkan
rekomendasi yang relevan. Penelitian selanjutnya disarankan untuk fokus pada
optimasi representasi TF-IDF dan BERT, peningkatan proses pra-pemrosesan
teks, penambahan fitur tambahan seperti rating pengguna, komentar, atau
metadata lain, serta eksplorasi metode hibrid yang menggabungkan penyaringan
berbasis konten dan kolaboratif, sehingga sistem rekomendasi dapat lebih tepat
dan sesuai dengan preferensi pengguna

The rapid growth of digital game distribution platforms such as Steam has made
it increasingly difficult for users to find games that match their preferences and
interests. This study aims to develop a content-based recommendation system for
Steam games by leveraging TF-IDF, BERT, and K-Means Clustering to generate
more accurate recommendations. Three recommendation schemes were evaluated:
a three-variable model (Categories, Genres, and Tags), an About-the-Game-only
model, and a hybrid textual model, using Mean Average Precision (MAP) and
Normalized Discounted Cumulative Gain (NDCG) as evaluation metrics.
Experimental results show that the three-variable model achieved the best
performance with an NDCG of 0.88 and a MAP of 0.71. In contrast, the Aboutthe-
Game-only model exhibited the lowest performance with an NDCG of 0.73
and a MAP of 0.61, indicating that game description information alone is
insufficient to generate relevant recommendations. Future research is
recommended to focus on optimizing TF-IDF and BERT representations,
improving text preprocessing, adding additional features such as user ratings,
comments, or other metadata, and exploring hybrid methods that combine
content-based and collaborative filtering, enabling the recommendation system to
provide more accurate suggestions aligned with user preferences.</note>
<subject authority=""><topic><![CDATA[Recommendation System, Content-Based Filtering]]></topic></subject>
<subject authority=""><topic><![CDATA[TF-IDF, BERT]]></topic></subject>
<subject authority=""><topic><![CDATA[Sistem Rekomendasi, Content-Based Filtering, TF-ID]]></topic></subject>
<classification><![CDATA[]]></classification><identifier type="isbn"><![CDATA[20250912]]></identifier><location>
<physicalLocation><![CDATA[Setiadi Open Source ETD System]]></physicalLocation>
<shelfLocator><![CDATA[089IS/25]]></shelfLocator>
<holdingSimple>
<copyInformation>
<numerationAndChronology type="1"><![CDATA[089IS/25]]></numerationAndChronology>
<sublocation><![CDATA[]]></sublocation>
<shelfLocator><![CDATA[089IS/25]]></shelfLocator>
</copyInformation>
</holdingSimple>
</location>
<slims:digitals>
<slims:digital_item id="22401" url="" path="/162021037_089IS.pdf" mimetype="application/pdf"><![CDATA[PENGEMBANGAN SISTEM REKOMENDASI GAME DENGAN PENDEKATAN CONTENT-BASED FILTERING DAN METODE K-MEANS CLUSTERING]]></slims:digital_item>
</slims:digitals><recordInfo>
<recordIdentifier><![CDATA[20387]]></recordIdentifier>
<recordCreationDate encoding="w3cdtf"><![CDATA[2025-11-11 11:07:17]]></recordCreationDate>
<recordChangeDate encoding="w3cdtf"><![CDATA[2025-11-11 11:07:35]]></recordChangeDate>
<recordOrigin><![CDATA[machine generated]]></recordOrigin>
</recordInfo></mods></modsCollection>