No abstract

Cyber-bullying includes repeated acts with the aim of scaring, angering, or embarrassing those who are targeted Cyber-bullying is happening along with the rapid development of technology and social media in society. The media and users need to filter out bully comments because they can indirectly affect the mental psychology that reads them especially directly aimed at that person. By utilizing information mining, the system is expected to be able to classify information circulating in the community. One of the classification techniques that can be applied to text-based classification is Naïve Bayes. The algorithm is good at performing the classification process. In this research, the precision of the algorithm's has been carried out on 1000 comment datasets. The data is grouped manually first into the labels "bully" and "not bully" then the data is divided into training data and test data. To test the system's ability, the classified data is analyzed using the confusion matrix method. The results showed that the Naïve Bayes Algorithm got the level of precision at 87%. and the level of  area under the curve (AUC) at 88%. In terms of speed of completing the system, the Naïve Bayes Algorithm has a very good rate of speed with completion time of 0.033 seconds.

Cyberbullying is the same as bullying but it is done through media technology. Bullying has often occurred along with the development of social media technology in society. Some technique are needed to filter out bully comments because it will indirectly affect the psychological condition of the reader, morover it is aimed at the person concerned. By using data mining techniques, the system is expected to be able to classify information circulating in the community. This research uses the Support Vector Machine (SVM) classification because the algorithm is good at performing the classification process. Research using about 1000 dataset comments. Data are grouped manually first into the labels "bully" and "not bully" then the data divide into training data and test data. To test the system capability, data is analyzed using confusion matrix. The results showed that the SVM Algorithm was able to classify with an level of accuracy 87.75%, 89% precision and 91% Recal. The SVM algorithm is able to formulate training data with level of accuracy 98.3%

In general, image classification is more like to classify objects with large categories, where these objects have a low level of similarity that is relatively rare. Birds image classification is a tough image dataset annotated with many bird species. It may be a challenging issue as numerous of the species of birds have degree of visual closeness. Bird species recognition can be challenging for people, let alone computer vision calculations. To analyze the image, this paper resizes the image into 224224 pixels. We use the Convolutional Neural network (CNN) approach and add the structure of MobileNetV2, EfficientNetB0, EfficientNetB3 and the weight of the network that has previously trained using ImageNet. This paper attempts to analyze the comparative results from using MobileNetV2, EfficientNetB0 and EfficientNetB3 architecture. The F1 weighted average score MobileNetV2 is 75%, EfficientNet B0 is 81% and EfficientNet B3 is 81%. This result shows that some models are completely unable to predict some classes of birds, but other models can recognize them. This can happen because of differences of the operation in each CNN architecture parameter. These models complement each other.