Twitter based Data Analysis in Natural Language Processing using a Novel Catboost Recurrent Neural Framework

In recent years, the sentiment analysis using Twitter data is the most prevalent theme in Natural Language Processing (NLP). However, the existing sentiment analysis approaches are having lower performance and accuracy for classification due to the inadequate labeled data and failure to analyze the complex sentences. So, this research develops the novel hybrid machine learning model as Catboost Recurrent Neural Framework (CRNF) with an error pruning mechanism to analyze the Twitter data based on user opinion. Initially, the twitter-based dataset is collected that tweets based on the coronavirus COVID-19 vaccine, which are pre-processed and trained to the system. Furthermore, the proposed CRNF model classifies the sentiments as positive, negative, or neutral. Moreover, the process of sentiment analysis is done through Python and the parameters are calculated. Finally, the attained results in the performance parameters like precision, recall, accuracy and error rate are validated with existing methods.