Root cause analysis of COVID-19 cases by enhanced text mining process

<p>The main focus of this research is to find the reasons behind fresh cases COVID-19 from public’s perception for data specific India. The analysis done using machine learning approaches and validating inferences with medical professionals. processing accomplished in three steps. First, dimensionality vector space model (VSM) reduced improvised feature engineering (FE) process by a weighted term frequency-inverse document frequency (TF-IDF) forward scan trigrams (FST) followed removal weak features hashing technique. In second step, an enhanced K-means clustering algorithm used grouping, based on public posts Twitter®. last latent dirichlet allocation (LDA) applied discovering trigram topics relevant increase cases. improved Dunn index value 18.11% when compared traditional method. By incorporating two-step FE process, LDA 14% terms coherence score 19% 15% semantic (LSA) hierarchical (HDP) respectively thereby resulting 14 root causes spike disease.</p>