<?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="20412">
<titleInfo>
<title><![CDATA[AUTOMASI TEMATIK ANALISIS MENGGUNAKAN PENDEKATAN NLP SEMANTIC DAN COOCCURRENCE UNTUK OPEN DAN AXIAL CODING]]></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>0429088207 - Corry Caromawati, S.S., M.A.</namePart>
<role><roleTerm type="text">Dosen Pembimbing 2</roleTerm></role>
</name>
<name type="Personal Name" authority="">
<namePart>WAFIE ABIYYA EL HANIF / 162021057</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>Analisis data kualitatif manual, khususnya pada fase coding dalam metodologi
seperti Grounded Theory, sering kali memakan waktu lama, membutuhkan banyak
sumber daya, serta rentan terhadap bias subjektif, terlebih pada dataset yang besar.
Perkembangan Natural Language Processing (NLP) dan Large Language Models
(LLMs), seperti DECOTA, menunjukkan potensi besar dalam mengotomatisasi
proses tersebut untuk meningkatkan efisiensi dan objektivitas. Penelitian ini
bertujuan untuk mengembangkan serta membandingkan model otomasi berbasis
NLP pada fase open coding dan axial coding dalam thematic analysis menggunakan
pendekatan semantik (KeyBERT, BERTopic) dan ko-okurensi (RAKE, LDA).
Data penelitian berupa transkrip wawancara yang telah melalui tahap preprocessing,
kemudian diolah menggunakan KeyBERT dan RAKE untuk open
coding, serta BERTopic dan LDA untuk axial coding. Evaluasi dilakukan dengan
cosine similarity pada open coding dan coherence score (c_v) pada axial coding,
dengan empat kombinasi model: KeyBERT+BERTopic, RAKE+BERTopic,
KeyBERT+LDA, dan RAKE+LDA. Hasil penelitian menunjukkan bahwa
pendekatan semantik memberikan kinerja yang lebih baik, di mana KeyBERT
mencapai lebih dari 80% cosine similarity dan BERTopic memperoleh skor
koherensi 0,80, sementara pendekatan ko-okurensi (RAKE+LDA) tetap menjadi
alternatif yang layak dengan skor koherensi hingga 0,68. Kualitas dataset terbukti
berpengaruh signifikan terhadap performa model; data yang lebih terstruktur
menghasilkan hasil yang lebih tinggi. Kesimpulannya, model NLP berbasis
semantik lebih efektif dalam mengotomatisasi open coding dan axial coding,
sehingga mampu meningkatkan efisiensi dan objektivitas analisis. Penelitian
selanjutnya disarankan untuk menyoroti heterogenitas data, karakteristik bahasa
tertentu, serta mengeksplorasi potensi model generatif dalam menghasilkan
ringkasan topik yang lebih deskriptif. 

Manual qualitative data analysis, particularly in the coding phases of
methodologies such as Grounded Theory, is often time-consuming, resourceintensive,
and prone to subjective bias, especially when dealing with large datasets.
Recent advancements in Natural Language Processing (NLP) and Large Language
Models (LLMs), such as DECOTA, have shown significant potential in automating
these processes to improve both efficiency and objectivity. This study aims to
develop and compare NLP-based automation models for the open coding and axial
coding phases within thematic analysis, using semantic approaches (KeyBERT,
BERTopic) and co-occurrence approaches (RAKE, LDA). The research data
consisted of interview transcripts that underwent pre-processing, followed by
implementation of KeyBERT and RAKE for open coding, and BERTopic and LDA
for axial coding. Model evaluation was conducted using cosine similarity for open
coding and coherence score (c_v) for axial coding, across four model
combinations: KeyBERT+BERTopic, RAKE+BERTopic, KeyBERT+LDA, and
RAKE+LDA. The results indicate that semantic approaches consistently
outperformed co-occurrence approaches, with KeyBERT achieving over 80%
cosine similarity and BERTopic reaching a coherence score of 0.80, while
RAKE+LDA remained a viable alternative with coherence scores up to 0.68.
Dataset quality was found to significantly influence performance, with more
structured data yielding higher results. In conclusion, semantic-based NLP models
proved more effective in automating open and axial coding, offering substantial
improvements in efficiency and objectivity. Future research is encouraged to
address data heterogeneity, language-specific characteristics, and to further
explore the potential of generative models in producing more descriptive topic
summaries.</note>
<subject authority=""><topic><![CDATA[Axial Coding, Topic Modeling, Semantic Similarity]]></topic></subject>
<subject authority=""><topic><![CDATA[Natural Language Processing, Open Coding,]]></topic></subject>
<subject authority=""><topic><![CDATA[Automated Thematic Analysis, Natural Language Proc]]></topic></subject>
<classification><![CDATA[]]></classification><identifier type="isbn"><![CDATA[20250912]]></identifier><location>
<physicalLocation><![CDATA[Setiadi Open Source ETD System]]></physicalLocation>
<shelfLocator><![CDATA[101IS/25]]></shelfLocator>
<holdingSimple>
<copyInformation>
<numerationAndChronology type="1"><![CDATA[101IS/25]]></numerationAndChronology>
<sublocation><![CDATA[]]></sublocation>
<shelfLocator><![CDATA[101IS/25]]></shelfLocator>
</copyInformation>
</holdingSimple>
</location>
<slims:digitals>
<slims:digital_item id="22427" url="" path="/162021057_101IS.pdf" mimetype="application/pdf"><![CDATA[AUTOMASI TEMATIK ANALISIS MENGGUNAKAN PENDEKATAN NLP SEMANTIC DAN COOCCURRENCE UNTUK OPEN DAN AXIAL CODING]]></slims:digital_item>
</slims:digitals><recordInfo>
<recordIdentifier><![CDATA[20412]]></recordIdentifier>
<recordCreationDate encoding="w3cdtf"><![CDATA[2025-11-11 13:40:19]]></recordCreationDate>
<recordChangeDate encoding="w3cdtf"><![CDATA[2025-11-11 13:40:35]]></recordChangeDate>
<recordOrigin><![CDATA[machine generated]]></recordOrigin>
</recordInfo></mods></modsCollection>