Aspect oriented Sentiment classification of COVID-19 twitter data; an enhanced LDA based text analytic approach

Social media has become one of the most important sources of information dissemination during crisis and pandemics. The unknown nature of these disasters makes it hard to analyze the comprehensive situational awareness through different aspects and sentiments to support authorities. Current aspect detection and sentiment analysis system largely relies on labelled data and also categorize the aspects manually. So, in this research, we proposed a hybrid text analytical framework to do aspect level public sentiments analysis. Our approach consists of three layers, first we extracted and clustered the aspects from the data by utilizing the widely used Latent dirichlet allocation (LDA) topic modelling, then we extracted the sentiments and label the dataset by using the linguistic inquiry and word count (LIWC) lexicon, then in third layer of our framework we mapped the aspects into sentiments and sentiments are then classified with well-known machine learning classifiers. Experiments with real dataset gives us promising results as compared to existing aspect oriented sentiment analysis approaches and our method with different variant of classifiers outperforms existing methods with highest F1 scores of 91 %.