<?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="20307">
<titleInfo>
<title><![CDATA[EVALUASI GENERATIVE PRE-TRAINED TRANSFORMER DALAM EKSTRAKSI FITUR UNTUK MODEL REGRESI LOGISTIK DALAM DETEKSI EMAIL SPAM]]></title>
</titleInfo>
<name type="Personal Name" authority="">
<namePart>0411105902 - Uung Ungkawa, Ir., M.T., Dr.</namePart>
<role><roleTerm type="text">Dosen Pembimbing 1</roleTerm></role>
</name>
<name type="Personal Name" authority="">
<namePart>MOCHAMAD REVI ALFIANSYAH / 152020001</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[Teknik Informatika]]></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>Deteksi email spam merupakan tantangan dalam pengelolaan komunikasi digital baik dimasa lalu, masa kini, maupun masa mendatang. Model regresi logistik sering digunakan untuk klasifikasi email spam karena kesederhanaannya dan fleksibilitasnya. Namun, efektivitasnya sangat bergantung pada kualitas fitur yang digunakan. Penelitian ini mengeksplorasi penerapan Generative Pre-trained Transformer (GPT) dalam ekstraksi fitur untuk meningkatkan performa model regresi logistik dalam mendeteksi email spam. GPT digunakan untuk mengekstrak fitur kontekstual dari teks email, yang kemudian diintegrasikan ke dalam model regresi logistik sebagai representasi fitur yang lebih bermakna. Eksperimen dilakukan dengan membandingkan performa model regresi logistik berbasis fitur GPT dan tanpa ekstraksi fitur Hasil penelitian menunjukkan bahwa pendekatan berbasis GPT memberikan peningkatan akurasi dan daya klasifikasi dibandingkan metode konvensional. Dengan demikian, penelitian ini menunjukkan bahwa pemanfaatan model bahasa besar seperti GPT dapat meningkatkan kualitas fitur dalam deteksi email spam menggunakan regresi logistik.

Spam email detection has been a challenge in digital communication management in the past, present, and future. Logistic regression models are commonly used for spam email classification due to their simplicity and flexibility. However, their effectiveness heavily depends on the quality of the extracted features. This study explores the application of Generative Pre-trained Transformer (GPT) for feature extraction to enhance the performance of logistic regression in spam email detection. GPT is utilized to extract contextual features from email text, which are then integrated into the logistic regression model as more meaningful feature representations. Experiments were conducted by comparing the performance of logistic regression models using GPT-based features with and without feature. The results indicate that the GPT-based approach improves accuracy and classification capability compared to conventional methods. Thus, this study demonstrates that leveraging large language models like GPT can enhance feature quality in spam email detection using logistic regression.</note>
<subject authority=""><topic><![CDATA[deteksi spam, regresi logistik, ekstraksi fitur]]></topic></subject>
<subject authority=""><topic><![CDATA[pemrosesan bahasa alami]]></topic></subject>
<subject authority=""><topic><![CDATA[Generative Pre-trained Transformer (GPT)]]></topic></subject>
<classification><![CDATA[]]></classification><identifier type="isbn"><![CDATA[20250904]]></identifier><location>
<physicalLocation><![CDATA[Setiadi Open Source ETD System]]></physicalLocation>
<shelfLocator><![CDATA[919IF/25]]></shelfLocator>
<holdingSimple>
<copyInformation>
<numerationAndChronology type="1"><![CDATA[919IF/25]]></numerationAndChronology>
<sublocation><![CDATA[]]></sublocation>
<shelfLocator><![CDATA[919IF/25]]></shelfLocator>
</copyInformation>
</holdingSimple>
</location>
<slims:digitals>
<slims:digital_item id="22321" url="" path="/152020001_919IF.pdf" mimetype="application/pdf"><![CDATA[EVALUASI GENERATIVE PRE-TRAINED TRANSFORMER DALAM EKSTRAKSI FITUR UNTUK MODEL REGRESI LOGISTIK DALAM DETEKSI EMAIL SPAM]]></slims:digital_item>
</slims:digitals><recordInfo>
<recordIdentifier><![CDATA[20307]]></recordIdentifier>
<recordCreationDate encoding="w3cdtf"><![CDATA[2025-11-10 13:55:04]]></recordCreationDate>
<recordChangeDate encoding="w3cdtf"><![CDATA[2025-11-11 13:02:07]]></recordChangeDate>
<recordOrigin><![CDATA[machine generated]]></recordOrigin>
</recordInfo></mods></modsCollection>