David C. Wyld: CSITY, NWCOM, SIGPRO, ASOFT, AIFZ, BDIoT, ITCCMA, CLSB, DTMN, MLNLP - 2021 pp. 295-304, 2021. CS & IT - CSCP 2021 DOI: 10.5121/csit.2021.111424 PREDICTION OF VACCINATION SIDE-EFFECTS USING DEEP LEARNING Farhan Uz Zaman, Tanvinur Rahman Siam and Zulker Nayen Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh ABSTRACT Deep learning has been very successful in the field of research which includes predictions. In this paper, one such prediction is discussed which can help to implement safe vaccination. Vaccination is very important in order to fight viral diseases such as covid-19. However, people at times have to go through unwanted side effects of the vaccinations which might often cause serious illness. Therefore, modern techniques are to be utilised for safe implementations of vaccines. In this research, Gated Recurrent Unit, GRU, which is a form of Recurrent Neural Network is used to predict whether a particular vaccine will have any side effect on a particular patient. The extracted predictions might be used before deciding whether a vaccine should be injected to a particular person or not. KEYWORDS Deep Learning, Gated Recurrent Unit, Recurrent Neural Network. 1. INTRODUCTION Viral diseases have taken millions of lives over the years. Spanish Flu and Covid-19 have proven to be the darkest enemies of humanity. Not only the loss of lives, these viruses have also caused huge economic losses. Hence, the people who survived the pandemic had to face economic hardships and even famine. Vaccination is very important especially for fighting against pandemics such a covid-19. A national public health institute in the United States of America, Centers for Disease Control and Prevention (CDC), have reported that 23.3 million people have been saved worldwide since 2011 by vaccines [1]. However, the entire process of vaccination is very delicate since human life is more fragile than we think. Therefore, a single mistake might be very costly in terms of life as we have seen in the Cutter Incident back in 1955 which ended with the death of 10 children [2]. To prevent such accidents from occurring several measures have been taken. Since many delicate problems have been solved with the help of modern technologies, turning to deep learning for the prevention of such mishaps would be very ideal. Deep learning methods such as recurrent neural networks have proved to be very efficient in terms of deriving the correct result within the shortest period of time. In most cases, they are used for the purpose of prediction. Hence, in this paper, a model is developed using a gated recurrent unit (GRU), which is a very popular form of recurrent neural network. This model is used to predict whether a certain vaccine will have any side effect on a person. This model is necessary since administering vaccines safely is a very important issue. Despite the fact that GRU is reputed to have very high accuracy while solving problems, our topic was very challenging since gathering the news of side effects are often buried by the vaccine producers to prevent the