Sentiment analysis and prediction of polarity vaccines based on Twitter data using deep NLP techniques

Abstract

The global impact of COVID-19 has been significant and several vaccines have been developed to combat this virus. However, these vaccines have varying levels of efficacy and effectiveness in preventing illness and providing immunity. As the world continues to grapple with the ongoing pandemic, the development and distribution of effective vaccines remains a top priority, making monitoring prevention strategies mandatory and necessary to mitigate the spread of the disease. These vaccines have raised a huge debate on social networks and in the media about their effectiveness and secondary effects. This has generated big data, requiring intelligent tools capable of analyzing these data in depth and extracting the underlying knowledge and feelings. There is a scarcity of works that analyze feelings and the prediction of these feelings based on their estimated polarities at the same time. In this work, first, we use big data and Natural Language Processing (NLP) tools to extract the entities expressed in tweets about AstraZeneca and Pfizer and estimate their polarities; second, we use a Long Short-Term Memory (LSTM) neural network to predict the polarities of these two vaccines in the future. To ensure parallel data treatment for large-scale processing via clustered systems, we use the Apache Spark Framework (ASF) which enables the treatment of massive amounts of data in a distributed way. Results showed that the Pfizer vaccine is more popular and trustworthy than AstraZeneca. Additionally, according to the predictions generated by Long Short-Term Memory (LSTM) model, it is likely that Pfizer will continue to maintain its strong market position in the foreseeable future. These predictive analytics, which uses advanced machine learning techniques, have proven to be accurate in forecasting trends and identifying patterns in data. As such, we have confidence in the LSTM's prediction of Pfizer's ongoing dominance in the industry.

Use of AI Applications to Learn the Sentiment Polarity of Public Perceptions: A Case Study of the COVID-19 Vaccinations in the UAE

“…An unsupervised neural language model is used to train word embedding and is trained by an unsupervised group of tweets. The conventional neural network is used to refine the embedding on the supervised corpus [10]. The components used in the proposed work are activations, sentence matrix pooling, SoftMax and convolutional layer [11].…”

Clustering Algorithms in Sentiment Analysis Techniques in Social Media – A Rapid Literature Review

“…Topic modeling is essential to comprehend the tweets and group them into manage-able categories. As traditional methodologies are unable to effectively handle noise, high volume, dimensionality, and short text sparseness, some authors [10] rely on topic modelling approaches to cluster the tweets (or short text messages) to groups. Their original solution uses a hierarchical two-stage clustering technique and can address the problem of data sparsity in short text.…”

“…However, because tweets are limited to 280 characters, individuals tend to use casual language, which makes it difficult to understand the true mood behind tweets [8]. Also, due to the high number of total registered users (650 million) and instant notifications [9], [10] over a broad range of mobile equipment's, Twitter provide useful datasets for research to help better understand public behaviors, opinions, and sentiments [11]. This review is built on Social Media (SM) datasets where Twitter/X was found to be the most prominent for many reasons, such as: high data volume, public data availability, hashtags (relevant for clustering analysis), text-based posts, real-time analysis and abundant recent publications which are conducive to performing a comprehensive investigation.…”

Paragraph-oriented methods for determining the coherence and thematic unity of scientific and technical texts

“…The NLP methods provide a wide variety of possibilities for data extraction from natural language texts. A good example is paper [2], which describes the application of NLP prognostic analytics aimed at the extraction of certain text entities from twits regarding the evaluation of comments polarity on vaccine quality. This study utilizes the Apache Spark Framework app., which gives the possibility to process significant amounts of data using the distribution method.…”