Emotion and Sentiment Recognition using Natural Language Processing and Machine Learning Techniques during Disaster Situation

ABSTRACT

Detecting emotions of the residents during disaster scenario is important for the government agencies to properly take care of its constituents. COVID-19 is a global disaster scenario that has caused unprecedented shutdowns, unemployment, death, and isolation. The behavioral and emotional health impact of COVID-19 is investigated in this study through the use of sentiment analysis and emotion recognition. The dataset is formed by collecting tweets from the seven months before COVID-19 became prevalent in March 2020 and the following seven months after. VADER sentiment analysis method was used to determine if a tweet was positive, negative, or neutral. For emotion recognition, several machine learning algorithms were evaluated and Convolutional Neural Network (CNN) Long-Short Term Memory (LSTM) performed better than the other models. Hence, CNN-LSTM was used to classify the emotion of each tweet as either anger, fear, joy, or sadness. Each tweet has a longitude and latitude stored with it that was geocoded to give the exact location, which was used to compare the states within the USA, and finally compare the USA as a whole with Canada, and Mexico. Sentiment analysis shows that all countries have experienced an increase in negative tweets. Emotion recognition shows that compared to Canada and Mexico, USA has experienced a steep drop in emotional health. © 2022 IEEE.