Instances classification with the small dataset for Quran ontology is the current research problem which appears in Quran ontology development. The existing classification approach used machine learning: Backpropagation Neural Network. However, this method has a drawback; if the training set amount is small, then the classifier accuracy could decline. Unfortunately, Holy Quran has a small corpus. Based on this problem, our study aims to formulate new instances classification framework for small training corpus applied to semantic question answering system. As a result, the instances classification framework consists of several essential components: pre-processing, morphology analysis, semantic analysis, feature extraction, instances classification with Radial Basis Function Networks algorithm, and the transformation module. This algorithm is chosen since it robustness to noisy data and has an excellent achievement to handle small dataset. Furthermore, document processing module on question answering system is used to access instances classification result in Quran ontology.

<p>Salah satu upaya pemerintah untuk mengatasi masalah kemiskinan di Indonesia yaitu membuat program beras sejahtera (RASTRA). RASTRA merupakan program dari pemerintah berupa bantuan beras bersubsidi untuk membantu masyarakat yang berpenghasilan rendah. Permasalahan yang terjadi yakni banyaknya kriteria penilaian yang digunakan dalam pedoman RASTRA dan penduduk miskin di suatu area/wilayah seringkali menyulitkan proses penentuan Keluarga Penerima Manfaat yang berhak menerima RASTRA pada Musyawarah desa/kecamatan. Tujuan penelitian ini adalah merancang dan mengembangkan sistem penunjang keputusan menggunakan model matematika <em>Simple Additive Weighting </em>(SAW) dan <em>Weighted Product</em> (WP) untuk memberikan rekomendasi penerima RASTRA. Terdapat empat tahapan penelitian yang digunakan untuk mencapai tujuan penelitian, yaitu analisis kebutuhan perangkat lunak, desain perangkat lunak, pengembangan, dan pengujian perangkat lunak. Berdasarkan hasil pengujian, hasil perhitungan nilai preferensi SAW<em> </em>memiliki performa yang lebih baik daripada WP karena SAW mampu meminimalisir nilai preferensi alternatif yang sama. Hal ini tampak dari perankingan alternatif berdasarkan hasil perhitungan SAW sejumlah 13 peringkat, dan WP sejumlah 10 peringkat.</p><p> </p><p class="Judul2"><strong><em>Abstract</em></strong></p><p class="Judul2">One of the government's efforts to overcome the poverty problem in Indonesia is to make the program "Beras Sejahtera" (RASTRA). RASTRA is a government program of subsidised rice to help low-income communities. The problems which occur are the number of assessment criteria used in the RASTRA guidelines and the poor in an area/region often complicate the process of determining the Beneficiary Family who are eligible to receive RASTRA at the village/sub-district deliberation. The purpose of this research is to design and develop decision support system using Simple Additive Weighting (SAW) and Weighted Product (WP) mathematical model to give the recommendation of RASTRA recipient. There are four research stages to achieve the research objectives, namely software requirements analysis, software design, development, and software testing. Based on the test results, the calculation of SAW preference values has better performance than WP because SAW can minimise the value of the same alternative preferences. This can be seen from the alternative ranking based on the calculation of SAW of 13 ranks, and WP 10 rank number.</p>

The current gap which appears in the Quran ontology population domain is stemming impact analysis on Indonesian Quran translation and their Tafsir to develop ontology instances. The existing studies of stemming effect analysis performed in various languages, dataset, stemming method, cases, and classifier. However, there is a lack of literature that studies about stemming influence on instances classification for Quran ontology with different dataset, classifier, Quran translation, and their Tafsir on Indonesian. Based on this problem, our study aims to investigate and analyze the stemming impact on instances classification results using Indonesian Quran translation and their Tafsir as datasets with multiple supervised classifiers. Our classification framework consists of text pre-processing, feature extraction, and text classification stage. Sastrawi stemmer was used to perform stemming operation in text pre-processing stage. Based on our experiment results, it was found that Support Vector Machine (SVM) with Term Frequency-Inverse Document Frequency (TF-IDF) and stemming operation owns the best classification performance, i.e., 70.75% for accuracy and 71.55% for precision in Indonesian Quran translation dataset on 20% test data size. While in 30% test data size, SVM and TF-IDF with stemming process own the best classification performance, i.e., 67.30% for accuracy and 68.10% for precision in Ministry of Religious Affairs Indonesia dataset. Furthermore, in this study, it was also discovered that the Backpropagation Neural Network has the most precision and accuracy reduction due to the negative impact of stemming operations.

<p class="Abstrak">Dalam studi ini, kami mengembangkan aplikasi <em>virtual</em><em> </em><em>reality</em> untuk mempelajari tata surya di tingkat sekolah dasar. Tujuan pembuatan aplikasi ini untuk menyediakan media pembelajaran berbasis multimedia bagi siswa agar dapat memahami konsep tata surya. <em>Multimedia Development Life Cycle</em><em> </em>(MDLC) adalah tahap pengembangan sistem yang digunakan untuk membangun aplikasi <em>virtual reality</em>. MDLC terdiri dari tahapan konsep manufaktur, desain, pengumpulan bahan, perakitan, pengujian, dan distribusi. Hasil tes penerimaan pengguna yang dilakukan oleh satu orang guru pengampu menunjukkan hasil 81,25%, sedangkan yang dilakukan oleh 26 siswa menunjukkan hasil 88,63%. Berdasarkan hasil tes penerimaan oleh guru diperoleh saran perbaikan aplikasi pada sisi interaktifitas pengguna. Evaluasi kepuasan pengguna terhadap aplikasi dilakukan dengan kuesioner berdasarkan empat elemen multimedia: teks, interaktivitas, animasi, dan gambar grafis. Hasil evaluasi penggunaan teks memiliki nilai 3,57, grafik bernilai 3,52, animasi bernilai 3,54, dan interaktivitas memiliki nilai 3,51. Berdasarkan hasil tes, dapat disimpulkan bahwa responden puas dengan penggunaan elemen multimedia pada aplikasi tersebut, dan aplikasi tersebut dapat membantu mereka untuk memahami topik pembelajaran lebih baik daripada metode pembelajaran dan pengajaran konvensional.</p><p class="Abstrak"> </p><p class="Abstrak"><em><strong>Abstract</strong></em></p><p class="Abstract"><em>In this study, we developed a virtual reality application for learning the solar system at the elementary school. The purpose of making this application is to provide multimedia-based learning media for students to be able to understand the concept of the solar system. Multimedia Development Life Cycle is a development stage of the system used to build virtual reality applications. MDLC consists of stages of the manufacturing concept, design, material collecting, assembly, testing, and distribution. Results of user acceptance test conducted by one teacher show the results of 81.25%, while that is done by 26 student shows the results of 88.63%. Based on the acceptance test results by the teacher, there are suggestions to improve the application on the user interactivity aspect. Evaluation of user satisfaction of the applications is done by a questionnaire based on the four elements of multimedia: text, interactivity, animation, and a graphical image. The result of the evaluation of the use of text has a value of 3.57, the graphic has a value of 3.52, animation has a value of 3.54, and interactivity has a value of 3.51. Based on the test results, it can be concluded that the respondents are satisfied with the use of multimedia elements on the application, and the application can help them to understand the learning topic better than conventional methods of learning dan teaching.</em><strong></strong></p><p class="Abstrak"><em><strong><br /></strong></em></p>

Question Answering System has the ability to present an answer based on a question submitted by the user in natural languages. This system consists of question processing, document retrieval, and answer extraction component. Challenge to optimize Question Answering’s system is to increase the performance of all components in the framework. The performance of all component which has not been optimized has caused to the lack of accurate answer from the systems. Based on this issue, the purpose of this research is to investigate the research gaps in the current state of existing Question Answering Systems on Holy Quran. The result of this study reveals potential research issues, namely morphology analysis, question classification, search techniques, and ontology resources.