Claim Missing Document
Check
Articles

Found 15 Documents
Search

Penilaian Esai Pendek Otomatis Berdasarkan Similaritas Semantik dengan SBERT Nurul Chamidah; Mayanda Mega Santoni; Helena Nurramdhani Irmanda; Ria Astriratma; Yulnelly Yulnelly
Techno.Com Vol 21, No 4 (2022): November 2022
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/tc.v21i4.6758

Abstract

Ujian dalam bentuk soal esai dianggap lebih baik dalam mengukur pemahaman dari pada soal berbentuk pilihan. Namun, jawaban esai memerlukan waktu dan tenaga lebih banyak untuk dievaluasi dan sering terjadi inkonsistensi. Maka dari itu, diperlukan suatu sistem penilaian esai otomatis yang dapat membantu evaluator dalam memberikan nilai dengan lebih cepat dan lebih konsisten. Penelitian ini bertujuan untuk mengevaluasi performa model penilaian esai otomatis dimana teks esai jawaban uji dan kunci jawaban dibandingkan secara semantik untuk mengetahui seberapa besar persamaan antara teks jawaban uji dan kunci jawaban. Semantik dari teks esai diperoleh dengan melakukan word embeddings dengan memanfaatkan model bahasa pretrained Siamese-BERT (SBERT) yang mentransformasi teks esai menjadi vektor sepanjang 512. Proses penilaian esai otomatis ini dimulai dengan praproses pada teks dengan menerapkan case folding, berikutnya word embeddings pada teks yang telah di praproses dengan SBERT. Vektor numerik dari kunci jawaban dan jawaban uji hasil word embeddings kemudian dibandingkan dengan Cosine Similarity untuk mendapatkan similaritas semantik sekaligus nilai esai yang merupakan output model. Evaluasi model penilaian esai otomatis ini dilakukan dengan membandingkan nilai dari model dengan nilai dari evaluator manusia. Pengukuran yang dipakai untuk mengukur performa penilaian esai otomatis ini adalah adalah dengan menghitung Mean Absolute Error (MAE) dan Pearson Correlation, dimana hasil penelitian ini menunjukan nilai rata-rata MAE sebesar 0.26 dan rata-rata korelasi sebesar 0.78.
Supporting Food Security Indicator by Village Production Results Data Management for Rajaiyang Village Apparatus with Inventory Application Training I Wayan Widi Pradnyana; Widya Cholil; Jayanta Jayanta; Ria Astriratma; Ika Nurlaili Isnainiyah; Agyei Fosu
SPEKTA (Jurnal Pengabdian Kepada Masyarakat : Teknologi dan Aplikasi) Vol. 4 No. 1 (2023)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/spekta.v4i1.6994

Abstract

Background: Rajaiyang Village is one of the villages in Indramayu Regency which has agricultural commodities in the form of rice production. In the current condition, even though it has a fertile area, welfare data of the community is not good enough from the management of these commodity products. The village government strategy requires support of information technology and knowledge development due to support regional food security and village sustainable development goals indicators. Contribution: Increased understanding and ability to manage the availability of commodity results using information technology to support food security strategies. Method: Inducting inventory training with an internet-based inventory application system for farmer groups and village apparatus. Results: The ability of residents and village apparatus to become better, more prepared with the system and product inventory management process, together with BUMDes support as a village owned enterprise. Conclusion: Implementation strategies and supporting facilities for village food security can be improved by using updated technology, as well as collaboration between village agencies for integrated decisions
SISTEM PAKAR UNTUK MENDIAGNOSIS HAMA PENYAKIT TANAMAN SEMANGKA MENGGUNAKAN METODE CERTAINTY FACTOR DAN METODE BAYES Luqman Imam; Henki Bayu Seta; Ria Astriratma
Jurnal Ilmiah Matrik Vol 24 No 2 (2022): Jurnal Ilmiah Matrik
Publisher : Direktorat Riset dan Pengabdian Pada Masyarakat (DRPM) Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33557/jurnalmatrik.v24i2.1764

Abstract

Watermelon is one of the most popular fruits by the general public. Apart from the benefits of watermelon, watermelon also has several diseases that are difficult for farmers to know, such as fruit rot (anthracnose), fruit scabies (bacterial fruit blotch), and others. Although watermelon disease is common, there are still many farmers who do not know about this problem. Therefore, an expert system for watermelon disease detection can be used using the certainty factor algorithm and the Bayes method. Based on the problems that occurred, this study raised the title "Expert System for Diagnosing Pests and Diseases of Watermelon Plants using the Certainty Factor Method and the Bayes Method" to overcome the ignorance of farmers in detecting watermelon disease by entering various characteristics listed in the system based on plant events, the system will provide insight based on existing characteristics using a certainty factor algorithm which will then compare the results with the Bayes method
Implementasi Algoritma K-Means untuk Clustering Project Health pada PT XYZ Ajeng Arifa Chantika Rindu; Ria Astriratma; Ati Zaidiah
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 7 No 5 (2023): October 2023
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v7i5.5181

Abstract

Indonesia has several companies that are involved in the telecommunications sector. Various projects run in parallel to support the success of telecommunications companies. The potential of a project can increase company revenue and productivity. On the other hand, there are some risks that need to be considered for every project when it is about to start. Project data is recorded from start to finish so that the project's progress and improvements can be monitored and analyzed. As the project runs, the project team at one of Indonesia's telecommunication companies, which is responsible for the processes leading to project success, requires a project health category. Therefore, this study is conducted to develop a clustering project health process, which is included in a type of unsupervised learning that runs on unlabeled data. One of the clustering algorithms is K-Means, which groups data based on similar criteria. Researchers also use dimensionality reduction with the principal component analysis (PCA) method to determine its impact on the clustering process with the K-Means algorithm. From this study, the researcher obtained three groups or project health categories, consisting of groups 0, 1, and 2. The evaluation results with the Calinski-Harabasz index showed that the K-Means model in the PCA dimensionality reduction data performed better than the standard K-Means model with a Calinski-Harabasz index value of 55633,12776405707, which is higher than 25914,578262576793.
Pelatihan Coding Sederhana Bagi Siswa Sekolah Dasar melalui Pembangunan Game Pada Scratch Tool Ati Zaidiah; Ika Nurlaili Isnainiyah; Ria Astriratma
INTEGRITAS : Jurnal Pengabdian Vol 8 No 1 (2024): JANUARI - JULI
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat - Universitas Abdurachman Saleh Situbondo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36841/integritas.v8i1.4084

Abstract

Keterampilan coding dalam bidang teknologi informasi merupakan keterampilan yang penting untuk diasah sejak usia dini. Namun, istilah coding masih belum banyak terdengar dalam dunia pendidikan pada umumnya, terutama tingkat pendidikan dasar. SD Kreatif Muhammadiyah 03 sudah berusaha dengan baik dalam memberikan pembelajaran kepada siswanya, namun dalam hal pemanfaatan teknologi informasi masih belum dioptimalkan. Media pembelajaran yang ada dirasa kurang memberikan motivasi kepada siswa dalam belajar dan terkesan monoton, khususnya pembelajaran terkait pengenalan TI. Program pengabdian kepada masyarakat ini telah dilaksanakan dengan memberikan pelatihan teknologi informasi kepada siswa untuk meningkatkan motivasi belajar siswa. Materi pelatihan yang disampaikan berisikan cara membangun permainan sederhana dalam rangka mengenal alur logika coding sederhana (pemula) melalui Scratch tool. Tingkat keberhasilan kegiatan menunjukkan penambahan pengetahuan mitra sebesar 61,5% berdasarkan perbandingan hasil pre-test dan post-test.