3 research outputs found
Transfer Learning Methods for Hate Speech Detection in Bahasa Indonesia
Get PDFCommunication is becoming more accessible with the growth and emergence of social media platforms. However, this can be misused, such as for spreading hate speech. Building an efficient hate speech detection model requires sufficient annotated data to train the model. However, this is difficult as it requires more data for low-resource languages like Bahasa Indonesia. To address this issue, we study whether the transfer learning method can yield improved results. This study performs extensive experiments to show that transfer learning methods are suitable for low-resource hate speech prediction. Our experimental results show that transferring knowledge using a multilingual pre-trained language model and translating hate speech datasets as additional data can improve the performance of detecting hate speech in Bahasa Indonesia. By using the XLM-RoBERTa-based hate speech model for transfer learning improved the F1-score for hate speech detection in Bahasa Indonesia by 78%. Meanwhile, translating the data from English as additional data for training and using the BERT model to detect hate speech in Bahasa Indonesia improved the F1-score from 60% to 69%. These results were statistically proven by the McNemar test and evaluated using the ROC-AUC score
Early Detection Application of Bipolar Disorders Using Backpropagation Algorithm
Get PDFMental health is an important aspect in realizing overall health and important to be considered as physical health. Mental disorders are classified as difficult to diagnose due to the similarity of symptoms that can occur. In addition, information about mental disorders is inadequate so that it can be difficult for experts to provide a diagnosis of the disorders experienced by patients. The difficulty of experts in diagnosing is usually caused by the similarity of symptoms in mental disorders, such as in schizophrenia and bipolar disorder. Based on these problems, this research would like to conduct an early detection study of bipolar disorder by using screening questionnaire data from 300 respondents and serve as a knowledge base to be processed using the backpropagation algorithm. Based on all the results of testing the backpropagation algorithm that has been done to find out the results obtained accuracy and the highest results of training, the highest results obtained with the total test data correct or suitable is 249 and the wrong data is 1 of 250 test data. If it is calculated by a formula, the resulting accuracy rate is 99.6%. And it can be concluded broadly that the greatest influence of the accuracy of the backpropagation algorithm is based on momentum. Because in testing momentum the highest accuracy can be produced compared to the results of other analyzes
