Abstract:Penggunaan dompet digital yang terus meningkat menghasilkan banyak ulasan pengguna yang dapat dimanfaatkan untuk mengevaluasi kualitas layanan. Penelitian ini bertujuan meningkatkan akurasi klasifikasi sentimen pengguna…
dompet digital menggunakan metode Stacking Ensemble Machine Learning yang mengombinasikan Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), dan AdaBoost dengan Logistic Regression sebagai meta-learner. Data ulasan diproses melalui tahapan text preprocessing meliputi case folding, cleaning, tokenizing, stopword removal, stemming, dan pembobotan fitur menggunakan TF-IDF. Penyeimbangan data dilakukan dengan SMOTE, sedangkan evaluasi model menggunakan 5-Fold Cross-Validation. Hasil penelitian menunjukkan bahwa model Stacking Ensemble memperoleh akurasi rata-rata 80,55%, lebih tinggi dibandingkan algoritma dasar. Evaluasi menggunakan Confusion Matrix, Classification Report, dan ROC Curve juga menunjukkan peningkatan nilai precision, recall, F1-score, dan kemampuan diskriminasi model. Hasil ini menunjukkan bahwa pendekatan Stacking Ensemble Machine Learning efektif untuk meningkatkan akurasi klasifikasi sentimen pengguna dompet digital serta mendukung evaluasi kualitas layanan berbasis opini pengguna.
The rapid growth of digital wallet usage has generated a large volume of user reviews that can be utilized to evaluate service quality. This study aims to improve the accuracy of digital wallet user sentiment classification using a Stacking Ensemble Machine Learning approach that combines Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), and AdaBoost with Logistic Regression as the meta-learner. User reviews were processed through text preprocessing stages, including case folding, text cleaning, tokenization, stopword removal, stemming, and TF-IDF feature weighting. Synthetic Minority Over-sampling Technique (SMOTE) was employed to address class imbalance, while model performance was evaluated using 5-Fold Cross-Validation. The experimental results show that the proposed Stacking Ensemble model achieved an average accuracy of 80.55%, outperforming the individual base learners. Furthermore, evaluations based on the Confusion Matrix, Classification Report, and Receiver Operating Characteristic (ROC) Curve demonstrated improvements in precision, recall, F1-score, and the model's discriminative capability. These findings indicate that the proposed Stacking Ensemble Machine Learning approach is effective in improving the accuracy of digital wallet user sentiment classification and can serve as a reliable tool for supporting service quality evaluation based on user opinions.
Abstract:PayLater services are one of the rapidly growing digital financial innovations widely utilised in fintech apps in Indonesia, including Kredivo and Akulaku. User reviews on the Google Play Store reflect a range of experiences,…
nces, from satisfaction with the ease of use of the service to complaints regarding bills, interest rates, late payment fees, credit limits, and app performance. This study aims to classify the sentiment of user reviews regarding PayLater services on the Kredivo and Akulaku apps using the Multinomial Naïve Bayes algorithm. Data was collected via web scraping from the Google Play Store and automatically labelled based on user ratings, with ratings of 1-2 classified as negative sentiment and ratings of 4-5 as positive sentiment, whilst a rating of 3 was excluded as it was considered ambiguous. Following a preprocessing stage comprising cleaning, case folding, tokenisation, stopword removal, and stemming, as well as feature extraction using TF-IDF, 3,652 reviews were obtained with a training-to-test data split ratio of 80:20. The results indicate that positive sentiment dominates the dataset at 56.49%, whilst negative sentiment accounts for 43.51%. Analysis by application revealed that Kredivo was dominated by positive sentiment (68.20%), whilst Akulaku was dominated by negative sentiment (51.70%). The Naïve Bayes multinomial model achieved an accuracy of 84.13%, with average precision, recall, and F1-score values of 0.84, demonstrating good and balanced classification performance across both sentiment classes.
Abstract:The emergence of consumer boycotts driven by socio-political issues reflects a fundamental shift in consumer behavior in the digital era. In Indonesia, a country characterized by high religiosity and extensive social media…
ia engagement, the rapid dissemination of negative information through electronic word of mouth (e-WOM) can trigger strong emotional reactions toward brands. Starbucks Indonesia represents a salient case in which the brand became associated with the Israel–Palestine conflict, generating moral debates, religious sentiments, and intense brand-related hostility in digital spaces. In this context, consumers act not merely as rational economic actors, but as moral agents whose purchasing decisions are influenced by deeply held values and beliefs. This study aims to examine the effects of e-WOM and religiosity on purchase intention, with brand hate serving as a moderating variable among Starbucks consumers in Indonesia. Specifically, the research investigates how exposure to negative online narratives and consumers’ religiosity shape emotional responses in the form of brand hate, and how these responses influence purchasing intentions within a boycott context. A quantitative research design was employed using a survey method targeting Starbucks consumers in Indonesia who were aware of the boycott related to the Israel–Palestine conflict. Data were collected through structured questionnaires and analyzed using structural equation modeling to assess both direct and indirect relationships among variables, including the moderating role of brand hate. This approach enables a comprehensive understanding of the psychological and behavioral mechanisms underlying consumer responses to value-laden and morally sensitive issues. The findings reveal that electronic word of mouth has a significant effect on purchase intention. Religiosity also influences purchase intention, both directly and indirectly through the formation of brand hate. Moreover, brand hate significantly moderates the relationship between e-WOM and purchase intention, such that higher levels of brand hate intensify the decline in consumers’ willingness to purchase. These results highlight the critical role of morally driven negative emotions in explaining reduced purchase intention during boycott movements. This study contributes theoretically by extending consumer behavior literature through the integration of digital communication, religiosity, and negative brand emotions within a single conceptual framework. Practically, the findings suggest that global brand managers should adopt culturally and religiously sensitive communication strategies and proactively manage digital narratives to mitigate the escalation of brand hate amid socio-political controversies.
Abstract:Democracy in Indonesia faces problems such as the disruption of freedom of expression in criticizing the government, physical violence committed by a junior high school principal against a teacher in Jombang Regency, East…
t Java. Principals who are far from democratic values such as deliberation or expressing opinions, Public Junior High Schools in Merauke are less able to control subordinates. This study aims to analyze the implementation of quality-based democratic leadership by Public Junior High School principals in Merauke Regency and identify supporting and inhibiting factors. The method used in this study is a qualitative descriptive approach with primary data sources in the form of in-depth interviews, direct observation, and documentation in five Public Junior High Schools in Merauke, as well as secondary data in the form of archives and educational regulations. The results show that a quality-based democratic leadership style can create a collaborative work climate that improves teacher performance and the quality of educational services, if balanced with effective coordination, continuous motivation, and transparency in decision-making. However, obstacles were also found in the form of a lack of firmness of leaders in enforcing discipline, weak consistency in providing examples, and the influence of local culture that gives rise to personal sentiments. Supporting factors include active teacher involvement in school program planning, support from local government policies, and school accreditation that encourages quality improvement. The conclusion of this study is that democratic leadership of quality-oriented school principals is effectively implemented if accompanied by increased managerial competence, strengthening the role of the school principal as a motivator, and a commitment to transparency and professionalism.
Abstract:The development of technology, especially in social media, is increasingly developing every year, which is commonly used daily by the public with the aim of obtaining information. The approach used in this study is the Social…
ocial Media Analytics (SMA) framework to analyze sentiment using NoLimit Indonesia software. Sentiment Analysis is a measurement of sentiment or emotion of social media users based on content analysis (positive/negative/neutral). This study aims to determine the sentiment analysis using the keywords "contraceptives" and "condoms" on the opinions of social media users regarding the policy of using contraceptives for students and adolescents with a period of one week. The results showed that neutral sentiment was 6,232 X account users, negative sentiment was 359 X account users, and 86 X account users were in a negative position. The conclusion of the study is that the response of social media X users was more neutral at 93%, 5.4% negative and 1.3% positive towards the policy on the use of contraceptives for teenagers or students in regulation 28 of 2024 concerning the Implementing Regulations of Law (UU) Number 17 concerning health which includes several health programs including in the reproductive system in article 103, especially in paragraph (4) point e, namely the provision of contraceptives, this is what is problematic and invites public attention
Abstract:Penelitian ini mengkaji reaksi publik terhadap keputusan Mahkamah Konstitusi (MK) Indonesia yang mempertahankan batasan umur minimal 35 tahun untuk calon presiden dan wakil presiden. Dengan menggunakan metode Naïve Bayes…
s untuk menganalisis sentimen dari data Twitter, penelitian ini bertujuan untuk mengungkap persepsi publik terhadap regulasi ini. Analisis menunjukkan mayoritas sentimen negatif (90.9%), dengan hanya 6.6% sentimen positif dan 2.5% sentimen netral, menandakan ketidakpuasan yang dominan di kalangan publik. Akurasi analisis sentimen yang dihasilkan mencapai 67.98%, menegaskan efektivitas Naïve Bayes dalam konteks ini. Penelitian menghasilkann betapa pentingnya akan pembahasan lebih mendalam mengenai syarat pencalonan yang dapat mencerminkan aspirasi masyarakat agar mempertimbangkan aspek pengalaman dan kedewasaan. Dalam konteks yang lebih luas, temuan ini memberikan wawasan berharga tentang dinamika opini publik dan potensi revisi peraturan terkait, merekomendasikan kajian lebih lanjut untuk memahami dampak kebijakan tersebut terhadap struktur demokrasi Indonesia
Abstract:Abstract: In this study, an analysis of the use of the Naive Bayes algorithm for sentiment analysis of reviews from Shopee app users on the Google Play Store was conducted, with classification divided into three categories:…
es: positive, negative, and neutral. To improve data quality, a preprocessing process was carried out with stages of cleaning, case folding, normalization, stop word removal, stemming, and tokenizing. Next, the text is formatted using the TF-IDF method to facilitate classification. For this data, the Naive Bayes model is used, which has an accuracy rate of 87% in detecting sentiment. Positive and negative categories can be easily identified compared to neutral sentiments due to the smaller amount of neutral data. Overall, the Naive Bayes algorithm successfully analyzed user sentiments well. The research can be developed with other algorithm methods, such as SVM, K-NN, or Decision Tree, in order to compare the performance of various algorithms.
Keywords: sentiment analysis; naive bayes; user reviews; e-commerce; shopee
Abstrak: Dalam penelitian ini dilakukan analisis penggunaan algoritma Naive Bayes untuk analisis sentimen review dari pengguna aplikasi Shopee di Google Play Store, klasifikasi dibagai menjadi 3 kategori yaitu positif, negatif, dan netral. Untuk meningkatkan kualitas data, dilakukam proses preprocessing dengan tahap cleanimg, case folding, normalisasi, stopword removal, stemming, dan tekonezing. Selanjutnya, teks diformat menggunakan metode TF-IDF untuk memudahkan klasifikasi. Untuk data ini, model Naive Bayes digunakan, yang memiliki tingkat akurasi 87% dalam mendeteksi sentimen. Kategori positif dan negatif dapat dengan mudah diidentifikasi dibadingkan sentiemen netral karena jumlah data netral yang lebih sedikit. Secara keseluruhan, algoritma Naive Bayes berhasil menganalisis perasaan pengguna dengan baik. Penelitian dapat dikembangkan dengan algoritma metode lain, seperti SVM, K-NN, atau Decision Tree, guna membandingkan kinerja berbagai algoritma.
Kata kunci: analisis sentiment; naive bayes; ulasan pengguna; e-commerce; shopee
Abstract:Tujuan penelitian ini adalah untuk mengetahui cara menganalisis sentimen dari ulasan pengguna pada game Roblox dan untuk mengetahui hasil perbandingan performa klasifikasi dengan menggunakan metode Support Vector Machine…
Dan Naive Bayes dalam menganalisis sentimen ulasan pengguna pada game Roblox. Data yang digunakan pada penelitian ini berjumlah sebanyak 10000 record data ulasan yang di ambil pada tanggal 15 Juni 2024. Hasil yang di peroleh dalam menganalisis sentimen data ulasan pada aplikasi Roblox cenderung mendapatkan sentimen positif dengan persentase 65,06% sedangkan untuk sentimen negatif dengan persentase 34,94%. Support Vector Machine merupakan algoritma terbaik dalam menganalisis sentimen data ulasan pada aplikasi Roblox dengan tingkat akurasi yang paling tinggi pada perbandingan data 90:10 yaitu 90 %, untuk precision, recall, dan f1-score yang dihasilkan pada sentimen positif yaitu 88%, 85%, dan 86%, sedangkan pada sentimen negatif adalah 91%, 93%, dan 92%. Algoritma Naïve Bayes mendapatkan tingkat akurasi yang paling tinggi pada perbandingan data 90:10 yaitu 72,4%, untuk precision, recall, dan f1-score yang dihasilkan pada sentimen positif yaitu 88%, 34%, dan 49%, sedangkan pada sentimen negatif adalah 70%, 97%, dan 81%.
Abstract:Pemerintah Indonesia menghadapi sejumlah problematika dalam bidang perekonomian, memerlukan solusi tepat untuk meningkatkan kondisi ekonomi. Keterlibatan langsung pemerintah dalam merespon dan memecahkan masalah tersebut…
memerlukan pemahaman mendalam terhadap problematika yang dihadapi masyarakat. Pasar, sebagai pusat ekonomi, mengalami transformasi signifikan dengan adanya platform online seperti TikTok, yang sebelumnya menyediakan fitur belanja yang populer. Dalam menghadapi dampak positif dan negatif dari fitur belanja TikTok, pemerintah memutuskan untuk menutup fitur tersebut. Penelitian ini bertujuan untuk menganalisis sentimen masyarakat terhadap kebijakan tersebut menggunakan Lexicon Based sebagai metode pelabelan, serta Naïve Bayes dan Random Forest sebagai model klasifikasi. Dengan menggunakan teknik crawling data, penelitian ini akan menyajikan analisis sentimen untuk memahami pandangan masyarakat terkait penutupan fitur belanja TikTok dan implikasinya terhadap perekonomian Indonesia.
Abstract:Abstract: The rapid growth of e-commerce mobile applications has generated large volumes of user reviews, making manual sentiment analysis increasingly impractical. This study aims to compare the effectiveness of three machine…
achine learning algorithms Support Vector Machine (SVM), Random Forest, and Naive Bayes for automated sentiment classification of Indonesian-language mobile application reviews. A dataset of 3,000 user reviews from the RupaRupa application on the Google Play Store was collected and preprocessed through normalization, tokenization, stopword removal, and stemming. TF-IDF vectorization was applied for feature extraction, while the Synthetic Minority Over-sampling Technique (SMOTE) was used to address class imbalance across three sentiment categories: positive, negative, and neutral. The results show that SVM achieved the highest accuracy of 90.02%, while Random Forest obtained the best F1-score of 88.08% when sufficient training data were available. Naive Bayes demonstrated relatively stable performance across varying training data sizes. Furthermore, TF-IDF keyword analysis revealed that negative reviews were primarily associated with delivery issues, technical problems, and pricing concerns. These findings demonstrate the effectiveness of machine learning approaches for sentiment classification and provide practical insights for improving mobile application services.
Keywords: sentiment analysis; machine learning; SMOTE; TF-IDF; text classification
Abstrak: Pertumbuhan pesat aplikasi mobile e-commerce telah menghasilkan volume ulasan pengguna yang sangat besar, sehingga analisis sentimen secara manual menjadi semakin tidak praktis. Penelitian ini bertujuan untuk membandingkan efektivitas tiga algoritma machine learning Support Vector Machine (SVM), Random Forest, dan Naive Bayes dalam melakukan klasifikasi sentimen otomatis terhadap ulasan aplikasi mobile berbahasa Indonesia. Dataset yang digunakan terdiri dari 3.000 ulasan pengguna aplikasi RupaRupa yang dikumpulkan dari Google Play Store. Data kemudian diproses melalui tahapan preprocessing yang meliputi normalisasi, tokenisasi, penghapusan stopword, dan stemming. Ekstraksi fitur dilakukan menggunakan metode Term Frequency–Inverse Document Frequency (TF-IDF), sedangkan ketidakseimbangan kelas ditangani menggunakan Synthetic Minority Over-sampling Technique (SMOTE) pada tiga kategori sentimen, yaitu positif, negatif, dan netral. Hasil penelitian menunjukkan bahwa SVM mencapai tingkat akurasi tertinggi sebesar 90,02%, sementara Random Forest memperoleh nilai F1-score terbaik sebesar 88,08% ketika tersedia data pelatihan yang memadai. Naive Bayes menunjukkan performa yang relatif stabil pada berbagai ukuran data pelatihan. Selain itu, analisis kata kunci berbasis TF-IDF mengungkapkan bahwa ulasan negatif terutama berkaitan dengan masalah pengiriman, kendala teknis aplikasi, dan isu harga. Temuan ini menunjukkan bahwa pendekatan machine learning efektif untuk klasifikasi sentimen serta memberikan wawasan yang bermanfaat dalam meningkatkan kualitas layanan aplikasi mobile.
Kata Kunci: analisis sentimen; pembelajaran mesin; SMOTE; TF-IDF; klasifikasi teks.