Optimizing sentiment analysis of Nigerian 2023 presidential election using two-stage residual long short term memory

Abstract

Sentiment analysis is the process of recognizing positive or negative attitudes in text. This technique makes use of computational linguistics, text analysis, and natural language processing. The 2023 presidential election in Nigeria is a significant event for the country, as it will determine the leader of the nation for the next four years. As such, it is important to understand the sentiment of the public towards the different candidates. In this research, we aimed to understand the sentiment of the public towards the three main candidates in the 2023 presidential election in Nigeria, Atiku, Tinubu, and Obi, by conducting a sentiment analysis on tweets related to the candidates. We used the long short-term memory (LSTM), peephole long short term memory (PLSTM), and two-stage residual long short-term memory (TSRLSTM) models to classify tweets as positive, neutral, or negative. Our dataset consisted of a large number of tweets that were preprocessed to remove noise and irrelevant information. Results showed that TSRLSTM performed excellently well in classifying the tweets and in identifying the sentiment towards each candidate individually. Our findings provide valuable insights into the public's opinion on the candidates and their campaign strategies, which can be useful for researchers, political analysts, and decision-makers. Our study highlights the importance of sentiment analysis in understanding public opinion and its potential applications in the field of political science.