Hasil Pencarian  ::  Simpan CSV :: Kembali

"Forum diskusi asinkron adalah salah satu media pembelajaran kolaboratif daring yang mampu mendorong pemikiran kritis, pertukaran gagasan, dan pembentukan pengetahuan. Analisis konten merupakan metode ilmiah yang dapat digunakan untuk mengidentifikasi keterampilan berpikir kritis dari transkrip pada forum diskusi asinkron. Metode analisis konten konvensional membutuhkan tahapan pengodean manual yang membutuhkan banyak waktu dan tenaga. Hal ini dapat mengakibatkan pengajar terlambat dalam memberikan intervensi instruksional karena informasi keterampilan berpikir kritis tidak dapat diperoleh secara cepat.Penelitian ini mengacu pada kerangka kerja Community of Inquiry (CoI) di mana keterampilan berpikir kritis dioperasionalisasikan melalui empat level dalam kehadiran kognitif yaitu pemantik diskusi, eksplorasi, integrasi, dan resolusi. Tujuan penelitian adalah mengembangkan model klasifikasi berbasis machine learning yang mampu menganalisis secara otomatis kehadiran kognitif pada transkrip diskusi berbahasa Indonesia. Desain penelitian menggunakan metode campuran kuantitatif dan kualitatif. Data eksperimen berjumlah 1.200 pesan diskusi dari mata kuliah Aljabar Linear di lingkungan pembelajaran bauran.Hasil penelitian menunjukkan bahwa kesiapan mahasiswa dalam mengelola pembelajaran dan lingkungan e-learning berpengaruh signifikan terhadap pengembangan kehadiran sosial dan kehadiran kognitif. Dataset level kehadiran kognitif pada transkrip diskusi asinkron dibangun dengan metode analisis konten yang reliabel kategori hampir sempurna (Cohen’s kappa = 0,88). Eksperimen pengembangan model analisis kehadiran kognitif menggunakan sepuluh basis algoritma yaitu XGBoost, Random Forest, Support Vector Machine, Logistic Regression, Naïve Bayes, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), IndoBERT-base, IndoBERT-large dan XLM-RoBERTa. Model berbasis IndoBERT-large memiliki performa terbaik dengan akurasi sebesar 0,825. Prototipe sistem Cognipresa (cognitive presence analytics) telah dikembangkan untuk memfasilitasi pengajar dengan menganalisis kehadiran kognitif mahasiswa dalam diskusi secara otomatis. Evaluasi sistem menunjukkan hasil yang menjanjikan dari sisi usability dengan nilai System Usability Scale (SUS) sebesar 80,83.

---

The asynchronous discussion forum serves as a collaborative online learning platform capable of stimulating critical thinking, exchanging ideas, and shaping knowledge. Content analysis is a scientific method that can be employed to identify critical thinking skills from transcripts in asynchronous discussion forums. Conventional content analysis methods entail manual encoding stages, which consume a significant amount of time and effort. This may lead to instructors being delayed in providing instructional interventions due to the inability to swiftly obtain information on critical thinking skills.

This study references the Community of Inquiry (CoI) framework, where critical thinking skills are operationalized through four levels of cognitive presence: triggering event, exploration, integration, and resolution. The research's objective is to develop a machine learning-based classification model capable of automatically analyzing cognitive presence in Indonesian-language discussion transcripts. The research design incorporates both quantitative and qualitative methods. The experimental data consists of 1,200 discussion messages from the Linear Algebra course in a blended learning environment.

The research findings indicate that students' preparedness in managing learning and e-learning environment significantly influences the development of social presence and cognitive presence. The dataset for cognitive presence at the transcript of asynchronous discussions was constructed using a content analysis method with a reliably almost perfect category (Cohen’s kappa = 0.88). An experimental development of the cognitive presence analysis model was conducted using ten algorithmic bases, namely XGBoost, Random Forest, Support Vector Machine, Logistic Regression, Naïve Bayes, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), IndoBERT-base, IndoBERT-large, and XLM- RoBERTa. The IndoBERT-large-based model demonstrated the best performance with an accuracy of 0.825. A prototype system called Cognipresa (cognitive presence analytics) has been developed to facilitate educators in automatically analyzing students' cognitive presence in discussions. The system evaluation indicates promising results in terms of usability, with a System Usability Scale (SUS) score of 80.83."

"Grammatical Error Correction (GEC) adalah salah satu task Natural Language Processing (NLP) yang mendeteksi dan mengoreksi kesalahan tata bahasa dalam sebuah teks. Task ini terus berkembang sampai saat ini dan telah diterapkan menggunakan berbagai metode, seperti rule-based, machine learning-based, dan sebagainya. Tugas akhir ini bertujuan membandingkan dua metode state-of-the-art Grammatical Error Correction yaitu metode T5 dan GECToR menggunakan dataset bahasa Inggris dan bahasa Indonesia. Untuk metode T5, akan dibandingkan model Flan-T5 dan mT5 dengan variasi ukuran base dan large. Adapun model yang dibandingkan untuk metode GECToR adalah model RoBERTa dan XLNet dengan variasi ukuran base dan large. Untuk dataset bahasa Inggris, akan digunakan dataset FCE untuk training dan dataset CoNLL-14 untuk testing. Sedangkan untuk dataset bahasa Indonesia, akan digunakan dataset Gramatika. Kemudian, untuk evaluasi digunakan metrik F0.5. Berdasarkan hasil uji coba, didapatkan bahwa untuk dataset bahasa Inggris FCE+CoNLL-14, metode T5 dengan varian model Flan-T5 unggul dari kedua varian metode GECToR dengan skor F0.5 sebesar 52,85%. Varian Flan-T5 ini unggul dengan margin sebesar 15,83% dari varian terbaik metode GECToR, yaitu RoBERTa. Sedangkan, metode GECToR dengan varian RoBERTa lebih unggul dengan margin 10,12% dari metode T5 dengan varian model mT5. Untuk dataset bahasa Indonesia Gramatika, kedua varian metode T5 lebih unggul dari metode GECToR. Varian terbaik metode T5 dengan skor F0.5 sebesar 45,38% dengan margin 31,05% dari varian terbaik metode GECToR, yaitu RoBERTa.

---

Grammatical Error Correction (GEC) is one of the Natural Language Processing (NLP) tasks that detect and correct grammatical errors in a text. This task continues to grow today and has been implemented using various methods, such as rule-based, machine learning-based, and so on. This final project aims to compare two state-of-the-art Grammatical Error Correction methods, namely the T5 and GECToR methods using English and Indonesian datasets. For the T5 method, Flan-T5 and mT5 models will be compared with base and large size variations. As for the GECToR method, RoBERTa and XLNet models will be compared with base and large size variations. For the English dataset, the FCE dataset will be used for training and the CoNLL-14 dataset for testing. As for the Indonesian dataset, the Grammatical dataset will be used. Then, the F0.5 metric is used for evaluation. Based on the experimental results, it is found that for the FCE+CoNLL-14 English dataset, the T5 method with the Flan-T5 model variant is superior to both variants of the GECToR method with an F0.5 score of 52.85%. The Flan-T5 variant is superior by a margin of 15.83% to the best variant of the GECToR method, RoBERTa. Meanwhile, the GECToR method with the RoBERTa variant is superior by a margin of 10.12% to the T5 method with the mT5 model variant. For the Indonesian Grammatical dataset, both variants of the T5 method are superior to the GECToR method. The best variant of the T5 method with an F0.5 score of 45.38% with a margin of 31.05% from the best variant of the GECToR method, which is RoBERTa."

"Materials informatics: a ?hot topic? area in materials science, aims to combine traditionally bio-led informatics with computational methodologies, supporting more efficient research by identifying strategies for time- and cost-effective analysis.The discovery and maturation of new materials has been outpaced by the thicket of data created by new combinatorial and high throughput analytical techniques. The elaboration of this "quantitative avalanche", and the resulting complex, multi-factor analyses required to understand it, means that interest, investment, and research are revisiting informatics approaches as a solution.This work, from Krishna Rajan, the leading expert of the informatics approach to materials, seeks to break down the barriers between data management, quality standards, data mining, exchange, and storage and analysis, as a means of accelerating scientific research in materials science."