Abstract:Abstract: Monotonous learning in elementary schools, teachers do not use a learning model to improve numeracy literacy in elementary schools. To overcome this problem, namely by using a cooperative learning model. Cooperative…
ative learning model is a learning model in which students learn and work in small groups collaboratively with 4-5 members with heterogeneous group structures. This service aims to find out how to improve the application of cooperative learning models based on local wisdom in elementary schools in order to increase numeracy literacy. This method is a participatory action study, namely the implementation of the method by considering the existence of a problem study stage by involving students in elementary schools, as well as looking for the most appropriate alternative solution in overcoming the problem. The result of this service is students' understanding of the cooperative learning model which can be seen from discussions and questions and answers. In addition, the results of this service increase students' ability to work together to improve numeracy literacy.
Keywords: cooperative learning; local wisdom; numerical literacy
Abstrak: Pembelajaran di Sekolah Dasar yang monoton, guru tidak menggunakan sebuah model pembelajaran untuk meningkatkan literasi numerasi di Sekolah Dasar. Untuk mengatasi masalah tersebut yakni dengan menggunakan model cooperative learning. Model cooperative learning adalah suatu model pembelajaran dimana siswa belajar dan bekerja dalam kelompok kecil secara kolaboratif yang anggotanya 4–5 orang dengan struktur kelompok heterogen. Pengabdian ini bertujuan untuk mengetahui bagaimana meningkatkan penerapan model pembelajaran kooperatif berbasis kearifan lokal di sekolah dasar dalam rangka peningkatan literasi numerasi. Metode ini yaitu kaji tindak partisipatif yaitu pengimplementasian metode dengan mempertimbangkan adanya tahap kajian masalah dengan melibatkan siswa di Sekolah Dasar, serta mencari alternatif solusi yang paling tepat dalam mengatasi permasalahan. Hasil dari pengabdian ini adalah pemahaman siswa mengenai model pembelajaran Cooperative Learning yang dapat dilihat dari diskusi dan tanya jawab. Selain itu hasil dari pengabdian ini menambah kemampuan siswa dalam bekerja sama untuk meningkatkan literasi numerasi.
Kata Kunci : cooperative learning; kearifan lokal; literasi numerasi
Abstract:Abstract: Along development process of teaching activities in classroom has many challenges and demands. The increasing number information channels that can be accessed by students so that teacher often lags far behind the…
he updated information that has been received. Therefore teacher is forced to compensate by looking for various additional information. One of the learning strategies that has not been widely applied today is the e-learning strategy. Edmodo is a paid e-learning website that can be utilized teachers implementing learning strategies. But there are still many teachers who do not know and utilize it to fullest helping learning process in the classroom. The method used this training is lecture, discussion and direct practice. The lecture method and discussion are used to convey information relating the theories and benefits of applying edmodo. With direct practice, teachers will be more understanding in applying edmodo. It is expected that after this training, teachers are able compile learning materials in e-learning online so that teachers are not only fixated on conventional learning models. After that, the teacher can implement e-learning in the class he is teaching. Starting from listening material, making assignments given through assignments and online quizzes for the subjects they teach.
Keywords: Learning Strategy, e-Learning, Edmodo
Abstrak: Seiring perkembangan zaman proses kegiatan mengajar di kelas memiliki banyak tantangan dan tuntutan. Semakin banyaknya jalur informasi yang dapat diakses oleh siswa sehingga tidak jarang guru tertinggal jauh dari updatenya informasi yang sudah diterima oleh siswa. Oleh karena itu guru dipaksa harus mengimbanginya dengan mencari berbagai informasi tambahan. Salah satu strategi belajar yang belum banyak diterapkan saat ini adalah strategi belajar e-learning. Edmodo merupakan website e-learning tidak berbayar yang dapat dimanfaatkan oleh guru dalam menerapkan strategi belajar e-learning. Namun masih banyak guru yang belum mengetahui dan memanfaatkannya secara maksimal dalam membantu proses belajar mengajar di kelas. Metode yang digunakan dalam pelatihan ini yaitu ceramah, diskusi dan praktek langsung. Metode ceramah dan diskusi digunakan untuk menyampaikan informasi yang berkaitan dengan teori-teori dan manfaat menerapkan edmodo. Dengan praktek langsung, guru-guru akan lebih memahami dalam menerapkan edmodo. Diharapkan setelah diadakan pelatihan ini, guru-guru SMA IT Plus Bazma Brilliant mampu menyusun materi pembelajaran secara e-learning online sehingga guru tidak hanya terpaku pada model pembelajaran konvensional saja. Setelah itu, guru dapat mengimplementasikan pembelajaran e-learning di dalam kelas yang diampunya. Mulai dari menguploud materi, membuat tugas yang diberikan melalui fitur assignment dan kuis online untuk mata pelajaran yang diajarnya.
Kata kunci: Strategi Belajar, e-Learning, Edmodo
Abstract:Some housewives in Batam City do not work, relying solely on income from their husbands. During this time, housewives use their free time to socialize and have a good time with their neighbors without producing anything…
useful, so it's time to take advantage of these habits in order to produce something to support their family's economy. In order for income housewives to have new knowledge and abilities, crafting activities are carried out by using patchwork. This training is carried out to use patchwork to have more selling value such as hijab accessories. This training was carried out twice, which was given the understanding of housewives about the use of patchwork and then given the practice of learning by doing. In the implementation of the service carried out by practicing directly how to make a brooch with several models of patchwork. Aside from the guidance of making brooches from patchwork, researchers also provide assistance in managing financial management, so that in the future it can be used as a home business that can help support the family's economy. From the results of the evaluation at the service of the mothers, thousands of households have been able to make patchwork brooches with several variations and models
Abstract:Abstract: Student graduation is an urgent matter that is an indicator of the success of a university in producing its learning output. Several factors influence student graduation such as GPA, attendance, late taking credits,…
dits, and lack of student involvement in academic activities. The urgency of this research, universities need a method that is able to predict student graduation early so that it can provide academic intervention to students who have the potential to experience delays or fail to graduate. However, limited access to real academic data is often an obstacle in the development of predictive models, Therefore, this study aims to implement the XGBoost algorithm to predict student graduation based on several academic variables, namely the Cumulative Grade Point Average (GPA), the number of credits taken, the percentage of attendance, and the average grade of students. Model training using the XGBoost algorithm using a simulation dataset of 500 students who are labeled as graduating into two classes, namely passed and failed. The results of the study showed that the classification performance was very good with an accuracy value of 99.6%, Precision 99.7%, recall 99.4%.
Keywords: xgboost algorithm; data mining; student graduation
Abstrak: Kelulusan mahasiswa merupakan hal urgensi yang menjadi indikator keberhasilan sebuah perguruan tinggi dalam menghasilkan output pembelajarannya. Beberapa Faktor yang mempengaruhi kelulusan mahasiswa seperti IPK, kehadiran, keterlambatan pengambilan SKS, serta kurangnya keterlibatan mahasiswa dalam aktifitas akademik. Yang menjadi urgensi penelitian ini, Perguruan tinggi memerlukan suatu metode yang mampu memprediksi kelulusan mahasiswa secara dini sehingga dapat memberikan intervensi akademik kepada mahasiswa yang berpotensi mengalami keterlambatan atau tidak lulus. Namun, keterbatasan akses terhadap data akademik riil sering menjadi kendala dalam pengembangan model prediksi, Oleh karena itu, penelitian ini bertujuan mengimplementasikan algoritma XGBoost untuk memprediksi kelulusan mahasiswa berdasarkan beberapa variabel akademik, yaitu Indeks Prestasi Kumulatif (IPK), jumlah SKS yang ditempuh, persentase kehadiran, dan nilai rata-rata mahasiswa. Pelatihan model menggunakan algoritma XGBoost dengan menggunakan dataset simulasi 500 mahasiswa yang diberi label kelulusan menjadi dua kelas yaitu lulus dan tidak lulus. Hasil penelitian menunjukan bahwa performance klasifikasi yang sangat baik dengan nilai accurasi sebesar 99,6%, Precision 99,7%, recall 99,4%.
Kata kunci: algoritma xgbosst; kelulusan mahasiswa; penambangan data
Abstract:Abstract: Manual meeting documentation risks losing important information due to cognitive fatigue. Although automated summarization models have evolved, integrated end-to-end systems for Indonesian spoken language remain…
n highly limited. This study aims to design and evaluate an end-to-end automated meeting summarization architecture that directly integrates Automatic Speech Recognition (ASR) via OpenAI Whisper for transcription and the IndoT5 language model for abstractive summarization. IndoT5 was fine-tuned using a dataset of 486 Indonesian spoken language transcript pairs. Testing was conducted on a CPU infrastructure using MP4, MP3, and WAV formats. Results show the optimal fine-tuning configuration significantly improved accuracy, achieving ROUGE-1 (0.4167), ROUGE-2 (0.1973), and ROUGE-L (0.2701) scores. Computationally, the system achieved a Real-Time Factor below 1, processing data faster than the actual recording duration. Conclusively, integrating Whisper and IndoT5 shows potential in producing coherent meeting summaries with lightweight computational overhead, making it viable for local infrastructure implementation to ensure data privacy.
Keywords: abstractive summarization; ASR; end-to-end pipeline; IndoT5; real-time factor
Abstrak: Dokumentasi rapat manual rentan menghilangkan informasi penting akibat keterbatasan kognitif. Meskipun model peringkas otomatis telah berkembang, implementasi sistem terintegrasi (end-to-end) khusus percakapan lisan berbahasa Indonesia masih sangat terbatas. Penelitian ini bertujuan merancang dan mengevaluasi arsitektur peringkas rapat otomatis end-to-end yang mengintegrasikan langsung Automatic Speech Recognition (ASR) melalui OpenAI Whisper untuk transkripsi dan model bahasa IndoT5 untuk peringkasan abstraktif. Adaptasi domain dilakukan melalui fine-tuning IndoT5 menggunakan 486 pasang dataset transkrip lisan berbahasa Indonesia. Pengujian pada infrastruktur CPU menggunakan format MP4, MP3, dan WAV. Hasil pengujian menunjukkan konfigurasi fine-tuning optimal berhasil meningkatkan akurasi, dengan skor ROUGE-1 (0,4167), ROUGE-2 (0,1973), dan ROUGE-L (0,2701). Sistem mendemonstrasikan efisiensi komputasi dengan nilai Real-Time Factor di bawah 1, mengindikasikan waktu pemrosesan lebih cepat dari durasi rekaman asli. Kesimpulannya, integrasi Whisper dan IndoT5 menunjukkan potensi dalam menghasilkan ringkasan yang koheren dengan beban komputasi ringan, sehingga layak diimplementasikan pada infrastruktur lokal organisasi untuk menjaga privasi data.
Kata kunci: ASR; end-to-end pipeline; IndoT5; peringkasan abstraktif; real-time factor
Abstract:Abstract: The growing intensity of cyber attacks, marked by rapid, large-scale, automated, and adaptive execution, requires analytical methods that represent the diversity of network environments, including variations in…
target platforms such as IoT, traditional networks, and hybrid infrastructures. This study compares machine learning models for cyber attack classification under heterogeneous environmental conditions and formulates a conceptual optimization framework based on model performance. Four publicly available benchmark datasets were used, namely UNB CIC IoT 2023, UNB CIC IDS-2018, UNSW-NB15, and a Kaggle cyber security attacks dataset, comprising approximately 40,000 to over 3.6 million records and 25 to 80 features across IoT, conventional, and mixed network environments. Random Forest, XGBoost, Multilayer Perceptron, and Transformer were implemented within a unified pipeline involving preprocessing, feature selection, and Bayesian Optimization-based hyperparameter tuning. All models achieved F1-score and Cohen's Kappa above 96%, with XGBoost performing best (97.80%, 97.26%), followed by Random Forest (97.78%, 96.96%) and Transformer (97.44%, 96.82%), while MLP scored lowest (96.74%, 96.00%), a gap below one percentage point. Confusion matrix analysis revealed persistent misclassification in minority and overlapping attack classes, informing a proposed adaptive cyber attack simulation optimization framework.
Keywords: cyber attacks; optimization; machine learning; environmental variability.
Abstrak: Meningkatnya intensitas serangan siber yang berlangsung cepat, masif, otomatis, dan adaptif menuntut pendekatan analitis yang merepresentasikan keragaman lingkungan jaringan, termasuk perbedaan karakteristik platform sasaran seperti Internet of Things (IoT), jaringan konvensional, dan infrastruktur hibrida. Penelitian ini membandingkan model machine learning untuk klasifikasi serangan siber pada kondisi lingkungan heterogen, sekaligus menyusun kerangka optimasi konseptual berdasarkan performa model. Empat dataset benchmark publik digunakan, yaitu UNB CIC IoT 2023, UNB CIC IDS-2018, UNSW-NB15, serta dataset Kaggle cyber security attacks, dengan jumlah data berkisar 40.000 hingga lebih dari 3,6 juta rekaman dan 25 sampai 80 fitur, mewakili lingkungan IoT, konvensional, dan campuran. Random Forest, XGBoost, Multilayer Perceptron, dan Transformer diimplementasikan melalui pipeline terpadu mencakup pra-pemrosesan, seleksi fitur, dan optimasi hyperparameter berbasis Bayesian Optimization. Seluruh model mencapai F1-score dan Cohen's Kappa di atas 96%, dengan XGBoost menunjukkan performa terbaik (97,80%, 97,26%), diikuti Random Forest (97,78%, 96,96%) dan Transformer (97,44%, 96,82%), sementara MLP mencatat skor terendah (96,74%, 96,00%), dengan selisih kurang dari satu poin persentase. Analisis confusion matrix mengungkap misklasifikasi yang konsisten pada kelas minoritas dan serangan dengan karakteristik serupa, yang menjadi dasar kerangka optimasi simulasi serangan siber adaptif yang diusulkan.
Kata kunci: serangan siber; optimasi; machine learning; variabilitas lingkungan
Abstract:Abstract: Accurate bone age estimation is essential for monitoring pediatric growth, diagnosing endocrine disorders, and supporting clinical decision-making. Although deep learning has improved prediction accuracy, limited…
ed studies have systematically examined how increasing model depth affects performance and reliability. This study evaluates the effectiveness of progressively deeper convolutional neural networks, specifically EfficientNet variants B0 to B5, for bone age estimation from hand radiographs. Experiments were conducted using 12,611 hand X-ray images from the RSNA Pediatric Bone Age Challenge dataset on Kaggle. To ensure fair comparison, all models were trained using a unified and consistent training pipeline. Model performance was evaluated using Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Concordance Correlation Coefficient (CCC), and Pearson correlation coefficient. The results show a consistent improvement in prediction accuracy as model depth increases. Among the evaluated models, EfficientNet-B5 achieved the best performance, with an MAE of 21.5 months, MAPE of 6.23%, CCC of 0.9148, and Pearson’s r of 0.9203. These findings confirm that model scaling plays a critical role in enhancing prediction robustness and clinical reliability. Future work should emphasize external validation across diverse populations and incorporate interpretability techniques, such as Grad-CAM, to improve clinical transparency and trust.
Keywords: bone age prediction; deep learning; model evaluation; clinical validation
Abstrak: Estimasi usia tulang yang akurat sangat penting untuk memantau pertumbuhan anak, mendiagnosis gangguan endokrin, dan mendukung pengambilan keputusan klinis. Meskipun pembelajaran mendalam telah meningkatkan akurasi prediksi, studi yang secara sistematis meneliti bagaimana peningkatan kedalaman model memengaruhi kinerja dan keandalan masih terbatas. Studi ini mengevaluasi efektivitas jaringan saraf konvolusional yang semakin dalam, khususnya varian EfficientNet B0 hingga B5, untuk estimasi usia tulang dari radiografi tangan. Eksperimen dilakukan menggunakan 12.611 gambar sinar-X tangan dari dataset RSNA Pediatric Bone Age Challenge di Kaggle. Untuk memastikan perbandingan yang adil, semua model dilatih menggunakan alur pelatihan yang terpadu dan konsisten. Kinerja model dievaluasi menggunakan Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Concordance Correlation Coefficient (CCC), dan koefisien korelasi Pearson. Hasil menunjukkan peningkatan yang konsisten dalam akurasi prediksi seiring dengan peningkatan kedalaman model. Di antara model yang dievaluasi, EfficientNet-B5 mencapai kinerja terbaik, dengan MAE sebesar 21,5 bulan, MAPE sebesar 6,23%, CCC sebesar 0,9148, dan Pearson’s r sebesar 0,9203. Temuan ini menegaskan bahwa penskalaan model memainkan peran penting dalam meningkatkan optimasi prediksi dan keandalan klinis. Penelitian selanjutnya dapat menekankan validasi eksternal di berbagai populasi dan menggabungkan teknik interpretasi, seperti Grad-CAM, untuk meningkatkan transparansi dan kepercayaan klinis.
Kata kunci: prediksi usia tulang; deep learning; evaluasi model; validasi klinis
Abstract:Abstract: This study discusses the optimization of RAG for a FAQ system in the field of information technology product security certification at BSSN. Although LLM generate reliable responses, they often lack up-to-date…
and domain-specific knowledge, which can be addressed through the RAG approach. This research aims to optimize a domain-specific RAG system by improving embedding performance, enhancing prompt robustness, and increasing retrieval accuracy. The research methods consist of three stages. The first stage involves fine-tuning the bge-m3 embedding model and evaluating its performance using MRR, Recall, and AUC. The second stage applies prompt engineering techniques, namely the SRSM and Autodefense, to mitigate direct-injection and escape-character prompt injection attacks. The third stage evaluates the proposed RAG system using Precision, Recall, and F1-Score metrics against four baseline models. The results of research show that the fine-tuned embedding model achieves higher performance than the original model, with MRR@1 and Recall@1 values of 0.80 and an AUC@100 of 0.7023. In addition, the proposed prompt engineering techniques demonstrate robustness against prompt injection attacks, while the overall RAG system attains a perfect Precision, Recall, and F1-Score of 1.00. In conclusion, the proposed approach effectively enhances retrieval accuracy, embedding quality, and system security, resulting in a more reliable RAG-based FAQ system for information technology product security certification.
Keywords: embedding fine-tuning; large language model; prompt engineering; prompt injection mitigation; retrieval-augmented generation
Abstrak: Studi ini membahas optimasi RAG untuk sistem FAQ di bidang sertifikasi keamanan produk teknologi informasi di BSSN. Meskipun LLM menghasilkan respons yang andal, mereka seringkali kurang memiliki pengetahuan terkini dan spesifik domain, yang dapat diatasi melalui pendekatan RAG. Penelitian ini bertujuan untuk mengoptimalkan sistem RAG spesifik domain dengan meningkatkan kinerja embedding, meningkatkan ketahanan prompt dan meningkatkan akurasi pengambilan. Metode penelitian terdiri dari tiga tahap. Tahap pertama melibatkan fine-tuning model embedding bge-m3 dan mengevaluasi kinerjanya menggunakan Mean Reciprocal Rank (MRR), Recall, dan AUC. Tahap kedua menerapkan teknik rekayasa prompt, yaitu Self- SRSM dan Autodefense, untuk mengurangi serangan direct-injection dan escape-character prompt injection. Tahap ketiga mengevaluasi sistem RAG yang diusulkan menggunakan metrik Presisi, Recall, dan F1-Score terhadap empat model dasar. Hasil penelitian menunjukkan bahwa model embedding yang disempurnakan mencapai kinerja yang lebih tinggi daripada model asli, dengan nilai MRR@1 dan Recall@1 sebesar 0,80 dan AUC@100 sebesar 0,7023. Selain itu, teknik rekayasa prompt yang diusulkan menunjukkan ketahanan terhadap serangan injeksi prompt, sementara sistem RAG secara keseluruhan mencapai Presisi, Recall, dan F1-Score sempurna sebesar 1,00. Kesimpulannya, pendekatan yang diusulkan secara efektif meningkatkan akurasi pengambilan, kualitas embedding dan keamanan sistem, menghasilkan sistem FAQ berbasis RAG yang lebih andal untuk sertifikasi keamanan produk teknologi informasi.
Kata kunci: penyempurnaan embedding; model bahasa besar; rekayasa prompt; mitigasi injeksi prompt; retrieval-augmented generation
Abstract:Abstract: Obesity is an escalating global health concern, with unhealthy lifestyle patterns contributing significantly to its development. This study aims to evaluate and compare three clustering techniques for categorizing…
ing lifestyle patterns and obesity-related factors: K-Means, Agglomerative Clustering, and Gaussian Mixture Model (GMM). The data used in this study is sourced from the Food Nutrition dataset, which includes variables such as dietary habits, physical activity, and socio-economic status. The three clustering methods were assessed using evaluation metrics such as Silhouette Score, Davies-Bouldin Index (DBI), and Calinski-Harabasz Index (CHI). The findings revealed that K-Means exhibited the best performance in terms of cluster separation with a Silhouette Score of 0.5559, while GMM showed better flexibility in handling more complex data. Although Agglomerative Clustering produced acceptable results, it had a higher overlap between clusters compared to the other methods. This study offers valuable insights into selecting the most appropriate clustering technique based on the data characteristics.
Keywords: agglomerative; clustering; GMM; k-means; lifestyle patterns; obesity
Abstrak: Obesitas menjadi masalah kesehatan yang semakin meningkat di seluruh dunia, dengan pola hidup yang tidak sehat berperan besar dalam perkembangannya. Penelitian ini bertujuan untuk membandingkan tiga metode clustering dalam mengelompokkan pola gaya hidup dan faktor yang memengaruhi obesitas, yaitu K-Means, Agglomerative Clustering, dan Gaussian Mixture Model (GMM). Data yang digunakan diperoleh dari dataset Food Nutrition yang mencakup informasi terkait pola makan, aktivitas fisik, serta faktor sosial-ekonomi. Ketiga metode tersebut diuji dengan menggunakan beberapa metrik evaluasi, seperti Silhouette Score, Davies-Bouldin Index (DBI), dan Calinski-Harabasz Index (CHI). Hasil penelitian menunjukkan bahwa K-Means memiliki kinerja terbaik dalam hal pemisahan klaster, dengan nilai Silhouette Score sebesar 0.5559, sementara GMM lebih fleksibel dalam menangani data yang lebih kompleks. Meskipun Agglomerative Clustering memberikan hasil yang dapat diterima, tumpang tindih antar klaster lebih besar dibandingkan dengan kedua metode lainnya. Penelitian ini memberikan pemahaman yang lebih baik mengenai pemilihan metode clustering yang tepat berdasarkan karakteristik data yang digunakan.
Kata kunci: agglomerative; clustering; GMM; k-means; obesitas; pola gaya hidup
Abstract:Abstract: The policy to increase the Rural and Urban Land and Building Tax (PBB-P2) in Indonesia often elicits mixed reactions from the public. Some support it because they believe it can strengthen regional fiscal capacity,…
ity, while others reject it because they are concerned that it will increase the economic burden on the community. Understanding public sentiment towards this policy is important for evaluating the effectiveness of the policy and formulating appropriate communication strategies. This study aims to analyze public sentiment towards the PBB-P2 increase policy using data uploaded on Platform X (Twitter). The data were collected through crawling with the keyword “building tax,” then processed through several preprocessing stages before classifying tweets into positive and negative sentiments. Two models were used: Support Vector Machine (SVM) and Bidirectional Long Short-Term Memory (BiLSTM). Results show that SVM outperformed BiLSTM, achieving training accuracy of 99.4% and testing accuracy of 85.9%, with accuracy 0.8595, precision 0.8536, recall 0.8595, and F1-score 0.8449. Meanwhile, BiLSTM achieved training accuracy of 86.9% and testing accuracy of 82.9%, with accuracy 0.8294, precision 0.8150, recall 0.8294, and F1-score 0.8080. These findings suggest SVM is more effective in classifying public sentiment and can support better evaluation of regional tax policies.
Keywords: sentiment analysis; PBB-P2; BiLSTM; SVM; X platform
Abstrak: Kebijakan kenaikan tarif Pajak Bumi dan Bangunan Perdesaan dan Perkotaan (PBB-P2) di In-donesia sering memunculkan beragam reaksi dari masyarakat. Sebagian mendukung karena dianggap dapat memperkuat kapasitas fiskal daerah, sementara lainnya menolak karena kha-watir menambah beban ekonomi masyarakat. Pemahaman terhadap sentimen publik atas ke-bijakan tersebut penting untuk mengevaluasi efektivitas kebijakan dan merumuskan strategi komunikasi yang tepat. Penelitian ini bertujuan menganalisis sentimen masyarakat terhadap kebijakan kenaikan PBB-P2 menggunakan data unggahan di Platform X (Twitter). Data dik-umpulkan melalui proses crawling dengan kata kunci “pajak bangunan” kemudian diproses melalui beberapa tahap preprocessing sebelum diklasifikasikan menjadi sentimen positif dan negatif. Dua model digunakan dalam penelitian ini, yaitu Support Vector Machine (SVM) dan Bidirectional Long Short-Term Memory (BiLSTM). Hasil penelitian menunjukkan bahwa SVM memiliki kinerja lebih baik dibandingkan BiLSTM, dengan akurasi pelatihan 99,4% dan akurasi pengujian 85,9%. Nilai akurasi 0,8595, precision 0,8536, recall 0,8595, dan F1-score 0,8449. Sementara itu, BiLSTM memperoleh akurasi pelatihan 86,9% dan akurasi pengujian 82,9%, dengan akurasi 0,8294, precision 0,8150; recall 0,8294; dan F1-score 0,8080. Temuan ini menunjukkan bahwa SVM lebih efektif dalam mengklasifikasikan sentimen publik serta dapat mendukung evaluasi kebijakan pajak daerah dengan lebih baik.
Kata kunci: analisis sentimen; PBB-P2; BiLSTM; SVM; platform X