Information Extraction and Named Entity Recognition Supported Social Media Sentiment Analysis during the COVID-19 Pandemic

Abstract

Social media platforms are increasingly being used to communicate information, something which has only intensified during the pandemic. News portals and governments are also increasing attention to digital communications, announcements and response or reaction monitoring. Twitter, as one of the largest social networking sites, which has become even more important in the communication of information during the pandemic, provides space for a lot of different opinions and news, with many discussions as well. In this paper, we look at the sentiments of people and we use tweets to determine how people have related to COVID-19 over a given period of time. These sentiment analyses are augmented with information extraction and named entity recognition to get an even more comprehensive picture. The sentiment analysis is based on the ’Bidirectional encoder representations from transformers’ (BERT) model, which is the basic measurement model for the comparisons. We consider BERT as the baseline and compare the results with the RNN, NLTK and TextBlob sentiment analyses. The RNN results are significantly closer to the benchmark results given by BERT, both models are able to categorize all tweets without a single tweet fall into the neutral category. Then, via a deeper analysis of these results, we can get an even more concise picture of people’s emotional state in the given period of time. The data from these analyses further support the emotional categories, and provide a deeper understanding that can provide a solid starting point for other disciplines as well, such as linguistics or psychology. Thus, the sentiment analysis, supplemented with information extraction and named entity recognition analyses, can provide a supported and deeply explored picture of specific sentiment categories and user attitudes.

Sentiment analysis of epidemiological surveillance reports on COVID-19 in Greece using machine learning models

“…People were interested in the virus early in the COVID-19 pandemic. Afterwards, public opinion focused on government measures, hygiene, and social and financial terms ( 27 ). The communication strategy of EODY and social media activity on Facebook are also criticized, while transparency issues emerged ( 58 , 59 ).…”

“…Furthermore, the justification of sentiment analysis using data from SNS is also manifested in another proposed research. The outcome emphasized that emotional state and sentiment polarity information during the pandemic can support communication strategies and public guidance ( 27 ).…”

Risk Identification of Internet Public Opinion on Social Media in Public Crisis Events Based on the Five-stage Perception State - A Brief Analysis on the Impact of Emotional Characteristics on the Risk Identification of Online Public Opinion

“…Classification and clustering processing uses natural language processing and similar text aggregation analysis for topic identification and tracking, and uses natural language processing, machine learning, and in-depth learning for emotional tendency analysis. For example, Nemes L et al [7] analyzed the negative sentiment tweet and, sorted based on entity type and mention frequency, which could highlight the main dissatisfaction of the people during the epidemic; Cai Yang [8] conducted research based on building a model based on the attention mechanism, and improved the structure of Transformer to solve the problem sentence-level and aspect-level text review sentiment analysis problems, and for fine-grained aspect-level sentiment analysis problems. The Light-Transformer-ALSC model was proposed to better evaluate the impact of aspect words on the overall text sentiment polarity; Wang Gang [9] , based on the transfer learning method, proposed a relationship-based emotional knowledge learning and transfer model R-EKLT, who combined the self-attention mechanism to realize the visualization of emotional knowledge, thereby enable himself to perform trainings on emotional classifiers more easily in new areas without rich labels；Yadav et al [10] proposed a locationless embedding model based on attention mechanism for aspect level sentiment classification Analyze and conduct experiments on datasets Restaurant 14, Laptop 14, Restaurant 15, and Restaurant 16,The accuracy rates reached 81.37%, 75.39%, 80.88%, and 89.30%, respectively.…”

Computational linguistics based text emotion analysis using enhanced beetle antenna search with deep learning during COVID-19 pandemic

“…The complete procedure comprises sentiment analysis, data collection, word embedding, classification, and preprocessing. In Nemes & Kiss (2021) , the author looks at the sentiments of individuals and utilizes tweets to determine how people have connected to coronavirus disease for a given period. Such SA was amplified by extracting information and named entity detection to receive a more inclusive picture.…”