Twitter Sentiment Analysis on Coronavirus: Machine Learning Approach

Machuca, Cristian R.; Gallardo, Cristian; Toasa, Renato M.

doi:10.1088/1742-6596/1828/1/012104

Cited by 41 publications

(22 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Across individuals, the sentiment over the course of the COVID-19 pandemic was generally negative. Other studies performing sentiment analyses on social media with overlapping time ranges during the pandemic have found overall negativity [63,64], overall positivity [59,65,66], or mixed results [67]. This variability is likely a result of type of language assessed, location of the participants, time period, and sentiment analysis algorithm.…”

Section: Discussionmentioning

confidence: 97%

“Is there anything else you would like to tell us?”: An analysis of language features in text responses to a study on mental health during the COVID-19 pandemic

Weger¹,

Lossio-Ventura²,

Rose-McCandlish³

et al. 2022

Preprint

View full text Add to dashboard Cite

The COVID-19 pandemic and associated restrictions have been a major stressor and exacerbated mental health worldwide. Qualitative data play a unique role in documenting mental state, via both language features and content. Within a longitudinal study on mental health during the COVID-19 pandemic, we analyzed free responses to the question: “Is there anything else you would like to tell us that might be important that we did not ask about?” We applied text analysis methods to ask whether individuals who responded to the item differed from non- responders, whether there were associations between language use and psychological status, and to characterize the content of responses and how responses changed over time. 3,655 individuals provided biweekly measures of mental health and responses to the COVID-19 pandemic for 6 months. Of these, 2,497 participants provided at least one free response (9,741 total responses). Response likelihood was influenced by demographic factors and health status: Participants who were male, Asian, Black, or Hispanic were less likely to respond, and odds of responding increased with age and education as well as with a history of physical health conditions. Although mental illness history did not influence an individual’s overall likelihood of responding, it was associated with more negative sentiment, negative word use, and higher usage of first-person singular pronouns. Responses were dynamically influenced by psychological status, such that distress and loneliness were positively associated with an individuals’ likelihood to respond at a given timepoint, and predicted more negativity. Finally, responses were negative in valence overall, exhibited fluctuations linked with external events, and covered a variety of topics, with the most common being mental health and emotion. Our results identify trends in language use during the first year of the pandemic, and suggest that the both the content of responses and overall sentiment are linked to mental health.

show abstract

Section: Discussionmentioning

confidence: 97%

“Is there anything else you would like to tell us?”: An analysis of language features in text responses to a study on mental health during the COVID-19 pandemic

Weger¹,

Lossio-Ventura²,

Rose-McCandlish³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Finally, we use these features to train a SVM model to make a prediction. LR: We implement the algorithm proposed in [ 41 ], which uses Logistic Regression algorithm to classify each tweet as positive or negative. The tweets are encoded by TF-IDF, and all the tweets’ embedding vectors are averaged as the user/author’s historical tweets.…”

Section: Methodsmentioning

confidence: 99%

FEBDNN: fusion embedding-based deep neural network for user retweeting behavior prediction on social networks

Wang

Zhang

Yuan

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

Due to the fast growing amount of user generated content (UGC) on social networks, the prediction of retweeting behavior is attracting significant attention in recent years. However, the existing studies tend to ignore the influence of implicit social influence and group retweeting factor factors. Also, it is still challenging to consider all related factors into a unified framework. To solve the above disadvantages, we propose a novel deep neural network fusion embedding-based deep neural network (FEBDNN) through the perspective of user embedding and tweets embedding for the author and the user’s historical tweets. Firstly, we propose dual auto-encoder (DAE) network for user embedding by integrating user’s basic features, explicit and implicit social influence and group retweeting factor. Then, we utilize the attention-based F_BLSTM_CNN(A_F_BLSTM_CNN) model for historical tweets’ representative embedding based on the combination of convolutional neural network (CNN) and bidirectional long short-term memory (BLSTM). Finally, we concatenate these embedding features into a vector and design a hidden layer and a fully connected softmax layer to predict the retweeting label. The experimental results demonstrate that the FEBDNN model compares favorably performance against the state-of-the-art methods.

show abstract

“…During the COVID-19 pandemic from Twitter in 2020, English tweets were classified as positive or negative by applying the LR algorithm to them, using this method they achieved a classification accuracy of 78.5% [9].…”

Section: Related Workmentioning

confidence: 99%

Sentiment analysis with ensemble and machine learning methods in multi-domain datasets

Başarslan

Kayaalp

2023

Turkish Journal of Engineering

View full text Add to dashboard Cite

The first place to get ideas on all the activities considered to occur in everyday life was the comments on the websites. This is an area that deals with these interpretations in the natural language processing, which is a sub-branch of artificial intelligence. Sentiment analysis studies, which is a task of natural language processing are carried out to give people an idea and even guide them with such comments. In this study, sentiment analysis was implemented on public user feedback on websites in two different areas. TripAdvisor dataset includes positive or negative user comments about hotels. And Rotten Tomatoes dataset includes positive (fresh) or negative (rotten) user comments about films. Sentiments analysis on datasets have been carried out by using Word2Vec word embedding model, which learns the vector representations of each word containing the positive or negative meaning of the sentences, and the Term Frequency Inverse Document Frequency text representation model with four machine learning methods (Naïve Bayes-NB, Support Vector Machines-SVM, Logistic Regression-LR, K-Nearest Neighbour-kNN) and two ensemble learning methods (Stacking, Majority Voting-MV). Accuracy and F-measure is used as a performance metric experiments. According to the results, Ensemble learning methods have shown better results than single machine learning algorithms. Among the overall approaches, MV outperformed Stacking.

show abstract

Twitter Sentiment Analysis on Coronavirus: Machine Learning Approach

Cited by 41 publications

References 6 publications

“Is there anything else you would like to tell us?”: An analysis of language features in text responses to a study on mental health during the COVID-19 pandemic

“Is there anything else you would like to tell us?”: An analysis of language features in text responses to a study on mental health during the COVID-19 pandemic

FEBDNN: fusion embedding-based deep neural network for user retweeting behavior prediction on social networks

Sentiment analysis with ensemble and machine learning methods in multi-domain datasets

Contact Info

Product

Resources

About