Abstract:Quality Village Bangau Putih in Parupuk Tabing subdistrict, Padang City, has a handicraft business made from coconut fibre. The problems faced by Kampung Berkualitas Bangau Putih in marketing its products include not utilising…
lising technology and the internet, not having an e-commerce website and not knowing about Search Engine Optimization (SEO) methods that can be implemented in digital marketing of handicraft products it produces. In addition, the bookkeeping of financial records still uses manual methods. Therefore, the PKM team held a service activity with a method consisting of several stages, namely conducting a survey to the partner's location to find out the partner's problems, then conducting training according to the partner's needs based on existing problems, then evaluating the results of training and mentoring if there are still obstacles. With this PKM programme, Kampung Berkualitas Bangau Putih understand the importance of technology and the internet in marketing their products and understand digital marketing using the SEO method.
Keywords: digital marketing, kampung berkualitas, search engine optimization, SEO
Abstrak: Kampung Berkualitas Bangau Putih yang berada di Kelurahan Parupuk Tabing, Kota Padang, memiliki usaha kerajinan tangan yang terbuat dari serabut kelapa. Beberapa masalah yang dihadapi oleh Kampung Berkualitas Bangau Putih dalam memasarkan produknya diantaranya adalah belum memanfaatkan teknologi dan internet, belum memiliki website e-commerce serta belum mengetahui tentang metode Search Engine Optimization (SEO) yang dapat diimplementasikan dalam pemasaran digital produk kerajinan tangan yang dihasilkannya. Selain itu, pembukuan catatan keuangannya masih menggunakan cara manual. Oleh karena itu, tim PKM mengadakan kegiatan pengabdian dengan metode yang terdiri atas beberapa tahapan, yaitu melakukan survey ke lokasi mitra untuk mengetahui permasalahan mitra, kemudian melakukan pelatihan sesuai dengan kebutuhan mitra berdasarkan permasalahan yang ada, selanjutnya melakukan evaluasi terhadap hasil pelatihan dan pendampingan jika masih terdapat kendala. Dengan adanya program PKM ini, masyarakat Kampung Berkualitas Bangau Putih menjadi paham tentang pentingnya teknologi dan internet dalam pemasaran produknya serta mengerti tentang pemasaran digital dengan metode SEO.
Kata kunci: kampung berkualitas; pemasaran digital; search engine optimization, SEO
Abstract:This research aims to examine the effectiveness of the Fingermathic method in forming students' independent learning character. This method is applied in mathematics learning in elementary schools with a focus on the use…
of fingers as a tool for visualizing arithmetic operations. The research involved students as test subjects who were assessed through an evaluation questionnaire on various aspects of the characteristics of independent learning. The results of the analysis show that the Fingermathic method can increase students' learning initiative and self-confidence, although more attention is still needed on the aspects of setting targets, overcoming difficulties, and evaluating learning outcomes. The conclusions of this research provide a basis for further development in designing learning strategies that support the formation of students' independent learning character at the elementary school level.
Keywords: student character; learning independence; fingermathic
Abstract:This article discusses the use of Fun Books as a measuring tool to increase students' creativity at elementary school level in mathematics and language learning. This service is carried out with a focus on measuring students'…
ents' creativity levels before and after implementing the Fun Book as well as evaluating how to stimulate students' creativity in both subjects. The target of the training is selected students, namely SD Negeri No. 010246 Banjar. The students selected were 16 Grade 2 students. The problem seen at this school is that students are still passive in learning, students are not yet creative and have difficulty answering questions asked by the teacher during each lesson in class, there are even 50% of students who are sleepy when taking part in class lessons. The impact of this training was that 13 students were able to use Fun Book media. Evaluation is carried out at the end of the training by distributing questionnaires to measure the participant's level of understanding. The questionnaire contains questions related to the respondent's identity; general questions related to mathematics and language learning and specific questions related to Fun Book media. The calculation of the questionnaire used the Guttman scale. The evaluation results showed that 89.84% had increased knowledge seen from the calculation of the questionnaire per individual and per question asked and the participation and enthusiasm of students during activities using the Fun Book.
Keywords: Fun Book; creativity; student
Abstract:PPM Shadr El-Islam Vocational School is in the Lake Sijabut District. Air Batu District. Asahan North Sumatra Province in evaluating teacher performance in learning supervision does not yet have a computerized system. This…
is is still done manually by filling in the instrument file. So the assessment results seem more subjective. So this community service activity aims to guide the use and exploitation of the features of the teacher performance evaluation application for teacher performance ratings in learning supervision. This aims to ensure that principals, teachers, and students at SMK PPM Shadr El-Islam can understand the objective teacher rating system, which in turn will facilitate effective decision-making. The methods applied in this activity are description and practice. The speaker will explain the features of the Teacher Performance Evaluation Application in Learning Supervision and then involve participants in direct practice. In this way, teachers and students can better understand how to use the teacher performance evaluation application, and understand the material and concepts presented, so that training objectives can be achieved better.
Keywords: Workshops, Applications, Teacher Performance, Decision Support Systems
Abstrak: SMK PPM Shadr El-Islam berada di Danau Sijabut Kec. Air Batu Kab. Asahan Provinsi Sumatera Utara dalam melakukan evaluasi kinerja guru pada supervisi pembelajaran belum memiliki sistem terkomputerisasi. Hal tersebut masih dilakukan secara manual dengan mengisi berkas instrument. Sehingga hasil penilaian terkesan lebih subjektif. Maka Kegiatan pengabdian kepada masyarakat ini bertujuan untuk memberikan panduan tentang penggunaan dan eksploitasi fitur-fitur dari aplikasi evaluasi kinerja guru atas peringkat kinerja guru pada supervisi pembelajaran. Hal ini bertujuan agar kepala sekolah, guru, dan siswa di SMK PPM Shadr El-Islam dapat memahami sistem peringkat guru yang objektif, yang pada gilirannya akan memudahkan pengambilan keputusan yang efektif. Metode yang diterapkan dalam kegiatan ini adalah deskripsi dan praktik. Pemateri akan memberikan penjelasan tentang fitur-fitur Aplikasi Evaluasi Kinerja Guru dalam Supervisi Pembelajaran, dan selanjutnya melibatkan peserta dalam praktik langsung. Dengan cara ini, para guru dan siswa dapat lebih paham menggunakan aplikasi evaluasi kinerja guru, paham atas materi dan konsep yang disampaikan, sehingga tujuan pelatihan dapat tercapai dengan lebih baik.
Kata kunci: Workshop, Aplikasi, Kinerja Guru, Sitem Pendukung Keputusan
Abstract:Abstract: Community service activities aimed at the government of Cipta Karya Village, Sungai Betung District, Bengkayang Regency aim to increase the interest and use of Information Technology in the Website field. Through…
gh a village institution managed by the community and village government, namely BUMdes, this greatly helps the community in improving the village economy which has the potential for information that can be used to convey information. Utilization of Information Technology in the creation of the assisted village web to display information related to the activities of the creation village. The service was carried out by studying the literature, implementing, and evaluating. Where the implementation is carried out in stages such as socialization, data management, creation of websites and domains as well as admin training, to the management of village websites. Through this website, the village government can provide information related to village activities such as potential tourism objects.
Keywords: BUMDES; management; website development; village
Abstrak: Kegiatan pengabdian pada masyarakat dengan sasaran pemerintah Desa Cipta Karya Kecamatan Sungai Betung Kabupaten Bengkayang bertujuan untuk meningkatkan minat dan pemanfaatan Teknologi Informasi pada bidang Website. Desa Cipta Karya belum memiliki wadah atau tempat untuk mempromosi potensi wisata desa. Pengelolaan Bumdes belum dimanfaatkan dengan baik dan benar dan belum ada tempat untuk menginformasi kegiatan atau informasi yang ada di Desa. Begitu pula peta lokasi wisata belum banyak diketahui oleh masyarakat luar. Melalui sebuah lembaga Desa yang dikelola oleh masyarakat dan pemerintah desa yaitu BUMdes, ini sangat membantu masyarakat dalam meningkatkan perekonomian desa yang memiliki potensi informasi yang bisa digunakan untuk menyampaikan suatu informasi. Pemanfaatan Teknologi Informasi dalam pembuatan web desa binaan untuk menampilkan informasi yang berkaitan dengan kegiatan desa cipta karya. Pengabdian ini dilakukan dengan metode studi literatur, pelaksanaan dan evaluasi. Dimana pada pelaksanaannya dilakukan tahap seperti sosialisasi, pengumpulan data, pembuatan website dan domain dan juga pelatihan admin, hingga pengelolaan website desa. Melalui website ini, pihak pemerintah desa dapat memberikan informasi terkait dengan kegiatan desa seperti potensi objek wisata.
Kata kunci: BUMdes; desa; pengelolaan; pengembangan website
Abstract:Abstract: The assessment of PKH employees in Batu Bara Regency still requires an objective and measurable evaluation process to support performance decisions. Manual assessment can cause subjectivity and take more time,…
especially when several criteria must be considered. This study aims to apply the Simple Additive Weighting (SAW) method to the PKH employee assessment system in Batu Bara Regency. The criteria used in this assessment are attendance, teamwork, responsibility, communication, and length of service. The SAW method is applied by determining criteria weights, converting employee values, normalizing the decision matrix, and calculating preference values to obtain the final ranking. The results show that alternative A1, Rahmi Rizkya, obtained the highest score of 0.9504 and ranked first, while alternative A5, Toni Syahpradanadaely, obtained the lowest score of 0.4831. Based on these results, the SAW method can help the employee assessment process become more objective, structured, and useful as a reference for evaluating PKH employee performance.
Keywords: decision support system; PKH employee; simple additive weighting
Abstrak: Penilaian pegawai PKH Kabupaten Batu Bara membutuhkan proses evaluasi yang objektif dan terukur untuk mendukung pengambilan keputusan terhadap kinerja pegawai. Penilaian yang masih dilakukan secara manual dapat menimbulkan subjektivitas dan membutuhkan waktu lebih lama, terutama jika penilaian melibatkan beberapa kriteria. Penelitian ini bertujuan untuk menerapkan metode Simple Additive Weighting (SAW) pada sistem penilaian pegawai PKH Kabupaten Batu Bara. Kriteria yang digunakan dalam penilaian meliputi kehadiran, kerja sama tim, tanggung jawab, komunikasi, dan masa kerja. Metode SAW diterapkan melalui penentuan bobot kriteria, konversi nilai pegawai, normalisasi matriks keputusan, serta perhitungan nilai preferensi untuk memperoleh hasil perankingan. Hasil penelitian menunjukkan bahwa alternatif A1 atas nama Rahmi Rizkya memperoleh nilai tertinggi sebesar 0,9504 dan menempati peringkat pertama, sedangkan alternatif A5 atas nama Toni Syahpradanadaely memperoleh nilai terendah sebesar 0,4831. Berdasarkan hasil tersebut, metode SAW dapat membantu proses penilaian pegawai menjadi lebih objektif, terstruktur, dan dapat dijadikan acuan dalam evaluasi kinerja pegawai PKH.
Kata kunci: pegawai PKH; simple additive weighting; sistem pendukung keputusan
Abstract:Abstract: The development of Artificial Intelligence (AI) in education provides significant opportunities for supporting the development of English teaching materials in elementary schools. However, the wide variety of available…
vailable AI tools makes it difficult for teachers to select the most appropriate tools for their instructional needs. This study aims to analyze and generate recommendations for AI utilization using a Decision Support System (DSS) based on the Analytical Hierarchy Process (AHP) and Simple Additive Weighting (SAW) methods. The AHP method is used to determine the weight of criteria based on their importance, while the SAW method is applied to rank alternative AI tools. This study involves teachers at SDN 15 Padang Genting in identifying criteria and evaluating alternatives. The results show that the proposed DSS model is capable of generating appropriate AI tool recommendations based on predefined criteria. This approach contributes to more objective and systematic decision-making in utilizing AI for developing English teaching materials in elementary education.
Keywords: analytical hierarchy proces; artificial intelligence; decision support system; simple additive weighting; teaching materials
Abstrak: Perkembangan Artificial Intelligence (AI) dalam pendidikan memberikan peluang dalam penyusunan bahan ajar Bahasa Inggris di sekolah dasar. Namun, banyaknya pilihan tools AI menyebabkan guru mengalami kesulitan dalam menentukan tools yang paling sesuai dengan kebutuhan pembelajaran. Penelitian ini bertujuan untuk menganalisis dan menghasilkan rekomendasi pemanfaatan AI menggunakan Sistem Pendukung Keputusan (SPK) berbasis metode Analytical Hierarchy Process (AHP) dan Simple Additive Weighting (SAW). Metode AHP digunakan untuk menentukan bobot kriteria berdasarkan tingkat kepentingannya, sedangkan metode SAW digunakan untuk melakukan perangkingan alternatif tools AI. Penelitian ini melibatkan guru di SDN 15 Padang Genting dalam proses identifikasi kriteria dan penilaian alternatif. Hasil penelitian menunjukkan bahwa model SPK mampu menghasilkan rekomendasi tools AI yang sesuai dengan kebutuhan pengguna berdasarkan kriteria yang telah ditentukan. Pendekatan ini memberikan kontribusi dalam mendukung pengambilan keputusan yang lebih objektif dan sistematis dalam pemanfaatan AI untuk penyusunan bahan ajar Bahasa Inggris di sekolah dasar.
Kata kunci: analisis proses hierarki; bahan ajar; kecerdasan buatan; sistem pendukung keputusan; simple additive weighting.
Abstract:Abstract: Understanding students’ emotional conditions is important for evaluating engagement and learning atmosphere in classroom environments. However, conventional evaluation methods are often subjective and difficult…
lt to apply in real time. Therefore, this study proposes a real-time multi-face emotion detection system designed for classroom learning environments. The system integrates a CNN-based Tiny Face Detector for multi-scale face localization with a convolutional neural network to classify seven facial emotions: angry, disgust, fear, happy, sad, surprise, and neutral. Experimental evaluation was conducted using classroom video data under varying lighting conditions, face orientations, partial occlusions, and different numbers of detected faces per frame. The proposed system achieves stable real-time performance with processing speeds ranging from 10–20 FPS, depending on face density. The results show higher recognition performance for expressive emotions, while subtle emotions remain more challenging. Overall classification accuracy reaches above 80% when emotion predictions are aggregated across multiple faces and time windows. These results indicate that the proposed system is suitable for objective analysis of emotional dynamics in classroom environments and supports the deployment of lightweight emotion-aware monitoring systems for educational applications.
Keywords: classroom monitoring; convolutional neural network; facial emotion recognition; multi-face detection; tiny face detector.
Abstrak: Pemahaman terhadap kondisi emosional mahasiswa penting untuk mengevaluasi keterlibatan dan suasana pembelajaran di kelas. Namun, metode evaluasi konvensional umumnya bersifat subjektif dan sulit diterapkan secara real-time. Oleh karena itu, penelitian ini mengusulkan sistem deteksi emosi multi-wajah secara real-time yang dirancang untuk lingkungan pembelajaran di kelas. Sistem mengintegrasikan Tiny Face Detector berbasis CNN untuk pelokalan wajah multi-skala dengan jaringan saraf konvolusional untuk mengklasifikasikan tujuh emosi wajah, yaitu marah, jijik, takut, senang, sedih, terkejut, dan netral. Evaluasi eksperimen dilakukan menggunakan data video kelas dengan variasi kondisi pencahayaan, orientasi wajah, oklusi parsial, serta jumlah wajah yang berbeda dalam satu frame. Sistem menunjukkan kinerja real-time yang stabil dengan kecepatan pemrosesan antara 10–20 FPS, bergantung pada kepadatan wajah. Hasil pengujian menunjukkan kinerja yang lebih baik pada emosi ekspresif, sementara emosi dengan ciri halus lebih menantang untuk dikenali. Akurasi klasifikasi keseluruhan mencapai di atas 80% ketika hasil emosi diagregasi berdasarkan banyak wajah dan interval waktu. Hasil ini menunjukkan bahwa sistem yang diusulkan berpotensi digunakan untuk analisis objektif dinamika emosi di kelas serta mendukung pemantauan lingkungan pembelajaran berbasis kecerdasan buatan.
Kata kunci: pengenalan emosi wajah; deteksi multi-wajah; Tiny Face Detector; jaringan saraf konvolusional; pemantauan kelas.
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: 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