ABSTRACT
The spread of data on the web has increased in the last twenty years. One of the reasons is the appearance of social media. The data on social sites describe many real-life events in our daily lives. In the period of the COVID-19 pandemic, a lot of people and media organizations were writing and documenting their health status and the latest news about the coronavirus on social media. Using these tweets (sentiments) about the coronavirus and analyzing them in a computational model can help decision makers in measuring public opinion and yielding remarkable findings. In this research article, we introduce a deep learning sentiment analysis model based on Universal Sentence Encoder. The dataset used in this research was collected from Twitter, and it was classified as positive, neutral, and negative. The sentence embedding model determines the meaning of word sequences instead of individual words. The model divides the dataset into training and testing and depends on the sentence similarity in detecting sentiment class. The obtained accuracy results reached 78.062%, and this result outperforms many traditional ML classifiers based on TF-IDF applied on the same dataset and another model based on the CNN classifier.
Subject(s)
COVID-19 , Social Media , Humans , Pandemics , Semantics , Sentiment AnalysisABSTRACT
The spread of data on the web has increased in the last twenty years. One of the reasons is the appearance of social media. The data on social sites describe many real-life events in our daily lives. In the period of the COVID-19 pandemic, a lot of people and media organizations were writing and documenting their health status and the latest news about the coronavirus on social media. Using these tweets (sentiments) about the coronavirus and analyzing them in a computational model can help decision makers in measuring public opinion and yielding remarkable findings. In this research article, we introduce a deep learning sentiment analysis model based on Universal Sentence Encoder. The dataset used in this research was collected from Twitter, and it was classified as positive, neutral, and negative. The sentence embedding model determines the meaning of word sequences instead of individual words. The model divides the dataset into training and testing and depends on the sentence similarity in detecting sentiment class. The obtained accuracy results reached 78.062%, and this result outperforms many traditional ML classifiers based on TF-IDF applied on the same dataset and another model based on the CNN classifier.