Detecting Emotions in English and Arabic Tweets

Ahmad, Tariq; Ramsay, Allan; Ahmed, Hanady

doi:10.3390/info10030098

Cited by 12 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Labeling: In order to annotate the data set, we followed guidelines by Bandi and Fellah [4] and labeled each tweet as positive, negative, or neutral. The TextBlob tool 3 was used for the purpose of labeling the emotional sentiment into positive, negative, and neutral. According to Bandi and Fellah [4], TextBlob can indicate a sentence's attitude by calculating the score as a polarity [-1 to 1].…”

Section: A Covidsenti Data Collection and Labelingmentioning

confidence: 99%

COVIDSenti: A Large-Scale Benchmark Twitter Data Set for COVID-19 Sentiment Analysis

Naseem

Razzak

Khushi

et al. 2021

IEEE Trans. Comput. Soc. Syst.

276

128

View full text Add to dashboard Cite

Social media (and the world at large) have been awash with news of the COVID-19 pandemic. With the passage of time, news and awareness about COVID-19 spread like the pandemic itself, with an explosion of messages, updates, videos, and posts. Mass hysteria manifest as another concern in addition to the health risk that COVID-19 presented. Predictably, public panic soon followed, mostly due to misconceptions, a lack of information, or sometimes outright misinformation about COVID-19 and its impacts. It is thus timely and important to conduct an ex post facto assessment of the early information flows during the pandemic on social media, as well as a case study of evolving public opinion on social media which is of general interest. This study aims to inform policy that can be applied to social media platforms; for example, determining what degree of moderation is necessary to curtail misinformation on social media. This study also analyzes views concerning COVID-19 by focusing on people who interact and share social media on Twitter. As a platform for our experiments, we present a new large-scale sentiment data set COVIDSENTI, which consists of 90 000 COVID-19-related tweets collected in the early stages of the pandemic, from February to March 2020. The tweets have been labeled into positive, negative, and neutral sentiment classes. We analyzed the collected tweets for sentiment classification using different sets of features and classifiers. Negative opinion played an important role in conditioning public sentiment, for instance, we observed that people favored lockdown earlier in the pandemic; however, as expected, sentiment shifted by mid-March. Our study supports the view that there is a need to develop a proactive and agile public health presence to combat the spread of negative sentiment on social media following a pandemic.

show abstract

Section: A Covidsenti Data Collection and Labelingmentioning

confidence: 99%

COVIDSenti: A Large-Scale Benchmark Twitter Data Set for COVID-19 Sentiment Analysis

Naseem

Razzak

Khushi

et al. 2021

IEEE Trans. Comput. Soc. Syst.

276

128

View full text Add to dashboard Cite

show abstract

“…A diverse array of methods and tools were used for textual analytics, subject to the nature of the textual data, research objectives, size of dataset and context. Twitter data has been used widely for textual and emotions analysis [18][19][20]. In another instance, a study analyzing customer feedback for a French Energy Company using more than 70,000 tweets published over a year [21], used a Latent Dirichlet Allocation algorithm to retrieve interesting insights about the energy company, hidden due to data volume, by frequency-based filtering techniques.…”

Section: Textual Analyticsmentioning

confidence: 99%

“…To minimize the loss function stated in (20), we use gradient descent method. The objective is to find the minimum weight of the loss function.…”

Section: Optimization Algorithmmentioning

confidence: 99%

COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification

et al. 2020

View full text Add to dashboard Cite

Along with the Coronavirus pandemic, another crisis has manifested itself in the form of mass fear and panic phenomena, fueled by incomplete and often inaccurate information. There is therefore a tremendous need to address and better understand COVID-19’s informational crisis and gauge public sentiment, so that appropriate messaging and policy decisions can be implemented. In this research article, we identify public sentiment associated with the pandemic using Coronavirus specific Tweets and R statistical software, along with its sentiment analysis packages. We demonstrate insights into the progress of fear-sentiment over time as COVID-19 approached peak levels in the United States, using descriptive textual analytics supported by necessary textual data visualizations. Furthermore, we provide a methodological overview of two essential machine learning (ML) classification methods, in the context of textual analytics, and compare their effectiveness in classifying Coronavirus Tweets of varying lengths. We observe a strong classification accuracy of 91% for short Tweets, with the Naïve Bayes method. We also observe that the logistic regression classification method provides a reasonable accuracy of 74% with shorter Tweets, and both methods showed relatively weaker performance for longer Tweets. This research provides insights into Coronavirus fear sentiment progression, and outlines associated methods, implications, limitations and opportunities.

show abstract

“…A diverse array of methods and tools have been used for textual analytics, subject to the nature of the textual data, research objectives, size of dataset and context. Twitter data has been used widely for textual and emotions analysis [20][21][22]. In another instance, a study analyzing customer feedback for a French Energy Company using more than 70000 tweets published over a year [23], used a Latent Dirichlet Allocation algorithm to retrieve interesting insights about the energy company, hidden due to data volume, by frequency-based filtering techniques.…”

Section: Textual Analyticsmentioning

confidence: 99%

“…where the gradient in (24) represents the difference betweenŷ and y multiplied by the corresponding input x j . Note that in (22), we need to do the partial derivatives for all the values of x j where 1 ≤ j ≤ n. As described in section 3.4, the purpose is to demonstrate application of exploratory sentiment classification, to compare the effectiveness of Naïve Bayes and logistic regression, and to examine accuracy under varying lengths of Coronavirus Tweets. As with classification of Tweets using Naïve Bayes, positive sentiment Tweets were assigned a value of 1, and negative sentiment Tweets were denoted by 0, allowing for a simple binary classification using logistic regression methodology.…”

Section: Optimization Algorithmmentioning

confidence: 99%

COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification

Samuel

Ali

Rahman

et al. 2020

Preprint

View full text Add to dashboard Cite

Along with the Coronavirus pandemic, another crisis has manifested itself in the form of mass fear and panic phenomena, fueled by incomplete and often inaccurate information. There is therefore a tremendous need to address and better understand COVID-19's informational crisis and gauge public sentiment, so that appropriate messaging and policy decisions can be implemented. In this research article, we identify public sentiment associated with the pandemic using Coronavirus specific Tweets and R statistical software, along with its sentiment analysis packages. We demonstrate insights into the progress of fear-sentiment over time as COVID-19 approached peak levels in the United States, using descriptive textual analytics supported by necessary textual data visualizations. Furthermore, we provide a methodological overview of two essential machine learning (ML) classification methods, in the context of textual analytics, and compare their effectiveness in classifying Coronavirus Tweets of varying lengths. We observe a strong classification accuracy of 91\% for short Tweets, with the Na\"ive Bayes method. We also observe that the logistic regression classification method provides a reasonable accuracy of 74\% with shorter Tweets, and both methods showed relatively weaker performance for longer Tweets. This research provides insights into Coronavirus fear sentiment progression, and outlines associated methods, implications, limitations and opportunities.

show abstract

Detecting Emotions in English and Arabic Tweets

Cited by 12 publications

References 25 publications

COVIDSenti: A Large-Scale Benchmark Twitter Data Set for COVID-19 Sentiment Analysis

COVIDSenti: A Large-Scale Benchmark Twitter Data Set for COVID-19 Sentiment Analysis

COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification

COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification

Contact Info

Product

Resources

About