ABSTRACT
The Indonesian government provided various social assistance programs to local governments during Covid-19. One of the difficulties for the local governments in determining candidates for social aid is ensuring that the number of candidates is in balance with the available quota. Therefore, the local governments must select the most eligible candidates. This study proposes a priority model that can provide recommendations for candidates who meet the criteria for social assistance. The six parameters used in this study were: number of dependents, occupation, income, age, Covid status, and citizen status. The model operates in two stages, namely classification followed by ranking. The classification stage is conducted using a decision tree, while the ranking stage is performed conducted using the Analytical Hierarchy Process (AHP) algorithm. The decision tree separates two classes, namely, eligible and non-eligible. In addition, the classification process is also used to determine the dominant attributes and played a role in the modeling. The proposed model generates a list of the most eligible candidates based on our research. These are sorted by weight from greatest to most eligible using five dominant parameters: number of dependents, income, age, Covid status, and citizen status.
ABSTRACT
During the Corona Virus Disease (COVID-19) pandemic, many access to learning used the e-learning system through the Learning Management System (LMS) platform. One of the weaknesses of the learning process through e-learning is that it cannot detect student learning styles based on actual behavior patterns during online learning. Most of the methods used to study automatic detection techniques use classification methods. One of the weaknesses of the classification method is the determination of class labels, so a learning style detection model was developed using the concept of clustering before classification to produce class labels with a high level of validation. This study focuses on increasing the validity of the clustering method by comparing the performance of the modified K-Means and K-Mode algorithms. The proposed modification of the two algorithms is carried out at the initial centroid determination stage. The performance of the two modified algorithms was carried out by measuring the validation values of the Davies-Bouldin Index (DBI) and Silhouette Index (SI) using log file data from 88 students taking computer programming courses. The validation results of the DBI and SI values indicate that the proposed model has better performance when implemented in the K-Mode algorithm than the K-Means algorithm. © 2023 ICIC International.
ABSTRACT
The rise of the infodemic containing false news or hoaxes and rumors about Covid-19 in society can worsen the pandemic situation itself. In addition, the infodemic can also be fatal to cause loss of life. This phenomenon that often appears in the community, such as drinking a cup of hot tea that has been dripped with eucalyptus oil can cure Covid-19 positive patients, making people believe that they ignore the health protocol recommendations. Therefore, to find out the truth or discrepancy of information in tweets, we can create a hoax detection system to minimize the emergence of hoax news. This study compares the Naive Bayes algorithm and the Support Vector Machine with a case study of Covid-19 tweets in Indonesian. The dataset collected is 500 tweets by manual labeling. For testing using the confusion matrix, the Naive Bayes method gets 78% accuracy and the support vector machine method gets 80% accuracy. The results of these tests prove that it can detect the truth of information or tweet using the support vector machine method with the highest accuracy. © 2022 Institute of Advanced Engineering and Science (IAES).