Visualizing Relation Between (De)Motivating Topics and Public Stance toward COVID-19 Vaccine

While social media plays a vital role in communication nowadays, misinformation and trolls can easily take over the conversation and steer public opinion on these platforms. We saw the effect of misinformation during the COVID-19 pandemic when public health officials faced significant push-back while trying to motivate the public to vaccinate. To tackle the current and any future threats in emergencies and motivate the public towards a common goal, it is essential to understand how public motivation shifts and which topics resonate among the general population. In this study, we proposed an interactive visualization tool to inspect and analyze the topics that resonated among Twitter-sphere during the COVID-19 pandemic and understand the key factors that shifted public stance for vaccination. This tool can easily be generalized for any scenario for visual analysis and to increase the transparency of social media data for researchers and the general population alike.

Applying Data Augmentation to Handwritten Arabic Numeral Recognition Using Deep Learning Neural Networks

Handwritten character recognition has been the center of research and a benchmark problem in the sector of pattern recognition and artificial intelligence, and it continues to be a challenging research topic. Due to its enormous application many works have been done in this field focusing on different languages. Arabic, being a diversified language has a huge scope of research with potential challenges. A convolutional neural network model for recognizing handwritten numerals in Arabic language is proposed in this paper, where the dataset is subject to various augmentation in order to add robustness needed for deep learning approach. The proposed method is empowered by the presence of dropout regularization to do away with the problem of data overfitting. Moreover, suitable change is introduced in activation function to overcome the problem of vanishing gradient. With these modifications, the proposed system achieves an accuracy of 99.4\% which performs better than every previous work on the dataset.