Deep Learning Model for COVID-19 Sentiment Analysis on Twitter

Hernández, Salvador Contreras; Cruz, María Patricia Tzili; Sánchez, José Martín; Tzili, Angélica Pérez

doi:10.1007/s00354-023-00209-2

Cited by 10 publications

(12 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given that research tends to use an automatic labeling process. Like the work by Contreras mentioned above [35]. Therefore, we present a corpus with a manual labeling process and an annotation guideline.…”

Section: Related Workmentioning

confidence: 99%

“…Researchers have also analyzed the performance of language models for sentiment analysis in Spanish. Specifically, for the COVID-19 tweet polarity, Contreras et al [35] found that pretrained BERT models in Spanish (BETO), with domain-adjusted, have achieved a high accuracy of 97% in training and 81% in testing. Such performance was the best compared to multilingual BERT models and other classification methods such as Decision Trees, Support Vector Machines, Naive Bayes, and Logistic Regression.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning and Deep Learning Sentiment Analysis Models: Case Study on the SENT-COVID Corpus of Tweets in Mexican Spanish

Gomez-Adorno,

Bel-Enguix,

Sierra

et al. 2024

Informatics

View full text Add to dashboard Cite

This article presents a comprehensive evaluation of traditional machine learning and deep learning models in analyzing sentiment trends within the SENT-COVID Twitter corpus, curated during the COVID-19 pandemic. The corpus, filtered by COVID-19 related keywords and manually annotated for polarity, is a pivotal resource for conducting sentiment analysis experiments. Our study investigates various approaches, including classic vector-based systems such as word2vec, doc2vec, and diverse phrase modeling techniques, alongside Spanish pre-trained BERT models. We assess the performance of readily available sentiment analysis libraries for Python users, including TextBlob, VADER, and Pysentimiento. Additionally, we implement and evaluate traditional classification algorithms such as Logistic Regression, Naive Bayes, Support Vector Machines, and simple neural networks like Multilayer Perceptron. Throughout the research, we explore different dimensionality reduction techniques. This methodology enables a precise comparison among classification methods, with BETO-uncased achieving the highest accuracy of 0.73 on the test set. Our findings underscore the efficacy and applicability of traditional machine learning and deep learning models in analyzing sentiment trends within the context of low-resource Spanish language scenarios and emerging topics like COVID-19.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Machine Learning and Deep Learning Sentiment Analysis Models: Case Study on the SENT-COVID Corpus of Tweets in Mexican Spanish

Gomez-Adorno,

Bel-Enguix,

Sierra

et al. 2024

Informatics

View full text Add to dashboard Cite

show abstract

“…Natural language processing (NLP) techniques are commonly used to preprocess the text data, including tasks such as tokenization, stemming, and removing stop words [14]. Machine learning models, such as support vector machines (SVM) or deep learning-based models like long short-term memory (LSTM) recurrent neural networks, can be employed for sentiment classification [8] [15]. These models analyze the linguistic indicators present in the text and classify the sentiment expressed in the posts [1].…”

Section: IImentioning

confidence: 99%

“…This information can be used to gain insights into the emotional well-being of post-COVID patients, identify areas where support and intervention may be needed, and inform public health strategies for addressing the mental health challenges associated with the pandemic [3]. India has been significantly impacted by the COVID-19 pandemic, with a high number of cases and fatalities [8]. The country has faced numerous challenges in managing the spread of the virus and…”

Section: Introductionmentioning

confidence: 99%

“…By analyzing the emotions expressed in these posts, researchers can gain insights into the prevalent emotional states of post-COVID patients, such as anxiety, fear, resilience, or hope [12]. This information can be utilized to develop targeted interventions and support systems to address the emotional needs of post-COVID patients in India [13]. Additionally, it can contribute to a better understanding of the long-term effects of COVID-19 on mental health and inform future research and policy decisions.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Sentiment Analysis of Post-Covid Patients on Social Media by Predictive Modeling

S. Roja

2023

IJRITCC

View full text Add to dashboard Cite

Social media has become a powerful platform for individuals to express their thoughts, experiences, and emotions. With the advent of the COVID-19 pandemic, social media has witnessed a surge in posts related to the virus and its aftermath. In India, a country severely hit by the pandemic, there is a prevalence of post-COVID patients sharing their experiences on social media. These posts provide valuable insights into the physical and emotional challenges faced by individuals after recovering from COVID-19. This paper aims to explore the prevalence of post-COVID patients on social media in India, the signs and symptoms experienced by these individuals, the correlations between post-COVID sentiment and patient characteristics, and the development of a predictive model for sentiment analysis. The prevalence of post-COVID patients on social media in India is evident through the increased number of posts related to COVID-19 and its aftermath. The surge in COVID-19 tweets was followed by an increased number of posts expressing personal experiences with the virus, indicating a significant presence of post-COVID patients on social media. These posts provide a valuable resource for understanding the challenges faced by individuals after recovering from COVID-19. Post-COVID patients often experience a range of signs and symptoms that can have a significant impact on their physical and mental well-being. Fatigue, shortness of breath, brain fog, chest pain, headache, and other symptoms have been reported as potential long-term effects of COVID-19. Additionally, patients with post-COVID-19 depressive symptoms share psychopathological symptoms, indicating the presence of mental health challenges. These signs and symptoms highlight the need for a comprehensive understanding of the post-COVID experience and the emotional toll it can take on individuals. Predictive modeling plays a crucial role in analyzing sentiment expressed by post-COVID patients on social media. Predictive modeling is a mathematical process that aims to predict future events or outcomes by analyzing relevant historical data. By developing a predictive model for sentiment analysis, researchers can gain valuable insights into the emotional experiences of post-COVID patients and potentially identify patterns or trends. This modeling approach allows for a systematic analysis of the vast amount of data available on social media platforms.

show abstract

Context-Based Persuasion Analysis of Sentiment Polarity Disambiguation in Social Media Text Streams

singh,

Kumari,

Gupta

2023

New Gener. Comput.

View full text Add to dashboard Cite

Deep Learning Model for COVID-19 Sentiment Analysis on Twitter

Cited by 10 publications

References 46 publications

Machine Learning and Deep Learning Sentiment Analysis Models: Case Study on the SENT-COVID Corpus of Tweets in Mexican Spanish

Machine Learning and Deep Learning Sentiment Analysis Models: Case Study on the SENT-COVID Corpus of Tweets in Mexican Spanish

Sentiment Analysis of Post-Covid Patients on Social Media by Predictive Modeling

Context-Based Persuasion Analysis of Sentiment Polarity Disambiguation in Social Media Text Streams

Contact Info

Product

Resources

About