Using Hybrid Gated Recurrent Networks to Analyze Twitter Sentiment and Unveil Sentiments

The most popular and active area of data mining study is sentiment analysis. Twitter is an important instrument for gathering and disseminating people's thoughts, feelings, views, and attitudes regarding specific entities. There are several social media platforms available today. Due to this Natural Language Processing is applied for sentiment analysis field gave rise to fascinating. While numerous methods for sentiment analysis have been devised, there is always room for improvement in system efficiency and accuracy. The suggested framework combines sentiment analysis based on deep learning with efficient optimization-driven feature selection to tackle these requirements. On a dataset of 140 sentiment-labelled texts, we assessed the efficiency of the proposed (GRN) architecture named gated recurrent network. We first cleaned and filtered the dataset to remove any errors or inconsistencies. Then, we used accuracy, precision, to measure and same time we also calculated performance metrics to estimate recall, and F-measure towards the GRN. The results which we have found and shows that on the dataset, the GRN performed at the cutting edge. These results suggest that the GRN is a promising new architecture for sentiment analysis.