Prediction of Evaluation Result of E-learning Success Based on Student Activity Logs With Selection of Neural Network Attributes Base on PSO

Evaluation of learning systems based on e-learning is very important to determine learning success. The purpose of this study is to obtain predictive results from evaluating students who follow e-learning based learning systems. The data used is the result of logs of student learning activities taken from the LMS. The data used in this study were 641 user logs of student activity. In predicting the evaluation results based on the learning system on e-learning we use a neural network method based on swarm particle optimization. Neural Network has a problem in optimizing very large data so using swarm particle optimization can solve this problem. From the data testing we have done, the results obtained by the Neural Network method get an accuracy value of 95.47%, and the results of the AUC value of 97.90%. The observation of variables C, ∊ and population of Neural Network and particle swarm optimization use the K-Fold Cross Validation method. Then the researchers tested several choices on the attributes used. By using the Neural Network method based on the swarm particle optimization attribute, there are 9 predictor variables so that as many as 6 attributes are used, namely sports, chat, discussion, messages, Quiz exercises and total logs. The results show an accuracy rate higher than 97.50%, and an AUC value of 98.20%. So the accuracy value increased by 2.03% and the AUC increased by 0.3%. With accuracy and AUC values, the Artificial Neural Network algorithm based on particle optimization is very well categorized.