<mets:mets OBJID="eprint_31754" LABEL="Eprints Item" xsi:schemaLocation="http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/mets.xsd http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-3.xsd" xmlns:mets="http://www.loc.gov/METS/" xmlns:mods="http://www.loc.gov/mods/v3" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><mets:metsHdr CREATEDATE="2026-07-05T22:22:04Z"><mets:agent ROLE="CUSTODIAN" TYPE="ORGANIZATION"><mets:name>EPrints Universitas Amikom Yogyakarta</mets:name></mets:agent></mets:metsHdr><mets:dmdSec ID="DMD_eprint_31754_mods"><mets:mdWrap MDTYPE="MODS"><mets:xmlData><mods:titleInfo><mods:title>PENERAPAN DAN EVALUASI MODEL MACHINE &#13;
LEARNING TERLATIH ANTAR DOMAIN PADA ANALISIS&#13;
SENTIMEN ULASAN APLIKASI KEUANGAN DIGITAL</mods:title></mods:titleInfo><mods:name type="personal"><mods:namePart type="given">Ashari</mods:namePart><mods:namePart type="family">Rama</mods:namePart><mods:role><mods:roleTerm type="text">author</mods:roleTerm></mods:role></mods:name><mods:abstract>Penelitian ini mengevaluasi model machine learning (SVM, ANN, dan &#13;
LSTM) untuk analisis sentimen lintas domain (cross-domain) pada ulasan aplikasi&#13;
keuangan digital Livin' by Mandiri. Tujuan penelitian adalah (1) membandingkan&#13;
performa model sebelum dan sesudah hyperparameter tuning pada dataset publik ,&#13;
(2) mengukur kemampuan generalisasi model dari dataset publik ke dataset&#13;
spesifik Livin' by Mandiri , dan (3) menentukan model yang paling andal. Metode&#13;
penelitian menggunakan supervised learning yang mencakup preprocessing teks,&#13;
pembobotan kata FastText , penanganan data tidak seimbang menggunakan&#13;
SMOTE , dan hyperparameter tuning.&#13;
Hasil penelitian pada dataset publik menunjukkan hyperparameter tuning&#13;
berhasil meningkatkan akurasi ketiga model hingga di atas 94%. LSTM (Tuned)&#13;
mencapai akurasi tertinggi (0.9422) , namun analisis statistik menunjukkan tidak&#13;
ada perbedaan performa yang signifikan (p-value &gt; 0.05) di antara ketiga model.&#13;
Saat model publik diuji pada data Livin', terjadi penurunan performa drastis&#13;
(akurasi 39-42%) , yang membuktikan adanya masalah domain shift parah.&#13;
Sebaliknya, saat model dilatih secara langsung pada dataset Livin', model ANN&#13;
(Artificial Neural Network) menunjukkan performa terbaik dengan akurasi&#13;
91.21% , mengungguli LSTM (90.89%) , SVM (86.35%) , dan penelitian&#13;
terdahulu.&#13;
Kesimpulannya, hyperparameter tuning krusial untuk data publik, namun&#13;
ketiga model memiliki performa yang setara. Model yang dilatih pada data publik&#13;
gagal digeneralisasi ke domain spesifik. Untuk domain aplikasi Livin' by Mandiri,&#13;
ANN terbukti menjadi model yang paling optimal dan unggul secara signifikan.</mods:abstract><mods:classification authority="lcc">000 Ilmu komputer, informasi dan pekerjaan umum</mods:classification><mods:originInfo><mods:dateIssued encoding="iso8061">2025-10-08</mods:dateIssued></mods:originInfo><mods:originInfo><mods:publisher>Universitas AMIKOM Yogyakarta;Pascasarjana Magister Informatika</mods:publisher></mods:originInfo><mods:genre>Thesis</mods:genre></mets:xmlData></mets:mdWrap></mets:dmdSec><mets:amdSec ID="TMD_eprint_31754"><mets:rightsMD ID="rights_eprint_31754_mods"><mets:mdWrap MDTYPE="MODS"><mets:xmlData><mods:useAndReproduction>
<p xmlns="http://www.w3.org/1999/xhtml"><strong>For work being deposited by its own author:</strong> 
In self-archiving this collection of files and associated bibliographic 
metadata, I grant EPrints Universitas Amikom Yogyakarta the right to store 
them and to make them permanently available publicly for free on-line. 
I declare that this material is my own intellectual property and I 
understand that EPrints Universitas Amikom Yogyakarta does not assume any 
responsibility if there is any breach of copyright in distributing these 
files or metadata. (All authors are urged to prominently assert their 
copyright on the title page of their work.)</p>

<p xmlns="http://www.w3.org/1999/xhtml"><strong>For work being deposited by someone other than its 
author:</strong> I hereby declare that the collection of files and 
associated bibliographic metadata that I am archiving at 
EPrints Universitas Amikom Yogyakarta) is in the public domain. If this is 
not the case, I accept full responsibility for any breach of copyright 
that distributing these files or metadata may entail.</p>

<p xmlns="http://www.w3.org/1999/xhtml">Clicking on the deposit button indicates your agreement to these 
terms.</p>
    </mods:useAndReproduction></mets:xmlData></mets:mdWrap></mets:rightsMD></mets:amdSec><mets:fileSec><mets:fileGrp USE="reference"><mets:file ID="eprint_31754_319534_1" SIZE="5409660" OWNERID="https://eprints.amikom.ac.id/id/eprint/31754/1/23.55.1410%20-%20Rama%20Ashari.pdf" MIMETYPE="application/pdf"><mets:FLocat LOCTYPE="URL" xlink:type="simple" xlink:href="https://eprints.amikom.ac.id/id/eprint/31754/1/23.55.1410%20-%20Rama%20Ashari.pdf"></mets:FLocat></mets:file></mets:fileGrp></mets:fileSec><mets:structMap><mets:div DMDID="DMD_eprint_31754_mods" ADMID="TMD_eprint_31754"><mets:fptr FILEID="eprint_31754_document_319534_1"></mets:fptr></mets:div></mets:structMap></mets:mets>