No abstract

Online learning is the key to the implementation of learning in the Covid 19 pandemic and the New Normal era. The purpose of this study was to determine the effectiveness of the e-learning course on subjects ‘Learn and Learning’ with Moodle-based for prospective teachers in Indonesia. This research was conducted using the Berg and Gail development method. The development instruments were validated by experts, and further product development was carried out in an integrated and simultaneous manner by the Higher Education Research Consortium Team (KRUPT) from Padang State University, Malang State University, Jakarta State University, Medan State University and Surabaya State University. This product is declared valid by the Expert, both in content, design and IT. Tests were limited during the Covid 19 pandemic and data collection was carried out online. Data collected in the form of an online questionnaire to student respondents (n = 40). Based on respondent questionnaire data, this product was declared to be very suitable for online learning, reaching 3.967 which indicated the highly acceptance level. Based on this research, it was concluded that e-learning products for subjects with learning and learning subjects could be widely used in the Educational Personnel Education Institution in Indonesia.

Freedom of opinion through social media is frequently affect a negative impact that spreads hatred. This study aims to automatically detect Indonesian tweets that contain hate speech on Twitter social media. The data used amounted to 4,002 tweets related to politics, religion, ethnicity and race in Indonesia. The application model uses classification methods with machine learning algorithms such as Naïve Bayes, Multi Level Perceptron, AdaBoost Classifier, Decision Tree and Support Vector Machine. The study also compared the performance of the model using SMOTE to overcome imbalanced data. The results show that the Multinomial Naive Bayes algorithm produces the best model with the highest recall value of 93.2% which has an accuracy value of 71.2% for the classification of hate speech. Therefore, the Multinomial Naïve Bayes algorithm without SMOTE is recommended as the model to detect hate speech on social media.

No abstract