Identification of affective valence of Twitter generated sentiments during the COVID-19 outbreak

Mittal, Ruchi; Mittal, Amit; Aggarwal, Ishan

doi:10.1007/s13278-021-00828-x

Cited by 17 publications

(9 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study aligns with previous studies that during this period of the COVID-19 lockdown, help-seeking posts were loaded with high-arousal emotions [ 4 ], especially negative emotions being the dominant ones [ 7 , 12 , 33 , 34 ]. During this special situation, people who sought help were more likely to have negative emotions (e.g., anger, fear, and sadness) rather than positive emotions (e.g., encouragement and hope) [ 13 ].…”

Section: Discussionsupporting

confidence: 91%

“Help Us!”: a content analysis of COVID-19 help-seeking posts on Weibo during the first lockdown

et al. 2023

View full text Add to dashboard Cite

Background Social media is playing an increasingly important role in public emergencies for help-seekers, especially during the global COVID-19 pandemic. Wuhan, China, firstly official reported COVID-19 cases and implemented lockdown measures to prevent the spread of the virus. People during the first lockdown were restricted from seeking help face-to-face. Social media is more prominent as an online tool for people seeking help, especially for patients, than in other stages of the COVID-19 pandemic. Objective This study aimed to explore the urgent needs presented in help-seeking posts in Wuhan during the first COVID-19 lockdown, the content features of these posts, and how they influenced online user engagement. Methods This study collected posts from Weibo posted with specific help tags during the first COVID-19 lockdown in Wuhan: from 23 January 2020 to 24 March 2020, and eventually received 2055 data, including textual content, comments, retweets, and publishing location. Content analysis was conducted, and manual coding was performed on help-seeking typology, narrative mode, narrative subject, and emotional valence. Results The result showed that help-seeking posts primarily were seeking medical (97.7%). Features of these posts were mainly adopting a mixed narrative mode (46.4%), released by relatives of patients (61.7%), and expressing negative emotions (93.2%). Chi-square tests suggested that help-seeking posts with mixed narrative modes released by relatives express more frequent negative emotions. Results of negative binomial regression indicated posts of seeking information (B = 0.52, p < .001, e0.52 = 1.68), with mixed narrative mode (B = 0.63, p < .001, e0.63 = 1.86), released by themselves (as referential groups) and with neutral emotions increased comments. Posts of seeking medical (B = 0.57, p < .01, e0.57 = 1.77), with mixed narrative mode (B = 1.88, p < .001, e1.88 = 6.53), released by people of unrelated patients (B = 0.47, p < .001, e0.47 = 1.60) and with neutral emotions increased retweets. Conclusions This study provides evidence of what actual public demands are to be considered and addressed by governments and public administrators before implementing closure and lockdown policies to limit the spread of the virus. Meanwhile, our findings offer strategies for people help-seeking on social media in similar public health emergencies.

show abstract

Section: Discussionsupporting

confidence: 91%

“Help Us!”: a content analysis of COVID-19 help-seeking posts on Weibo during the first lockdown

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Moreover, Chourdrie et al [84] conducted a study analyzing emotions during various points in time in different countries. Besides, sentiment analysis can be used to predict the number of infections, recoveries, and the death toll, as shown by a study by Mittal and Aggarwal [85]. Likewise, Sing et al [86] found a correlation between negative tweets and, respectively, the number of global cumulative infections, global cumulative deaths, and cumulative recoveries (in China).…”

Section: ) Threat Perceptionmentioning

confidence: 97%

“…Hence, Zhou et al [118] studied the sentiment in tweets in the Australian region of New South Wales during the pandemic. Mittal et al [85] analyzed the correlation between public sentiment and factors such as global infections, global deaths or recoveries, and Surano et al [110] used sentiment polarity as a predictor for other socioeconomic factors.…”

Section: ) Overview Of Classification Techniquesmentioning

confidence: 99%

Machine Learning Techniques for Sentiment Analysis of COVID-19-Related Twitter Data

et al. 2023

View full text Add to dashboard Cite

On Twitter, COVID-19 is a highly discussed topic. People worldwide have used Twitter to express their viewpoints and feelings during the pandemic. Previous research has focused on particular topics such as the public's sentiment during the lockdown, their opinion on governmental measures, or their stance towards COVID-19 vaccines. However, until today, there is no comprehensive overview that presents possible areas of application for sentiment analysis of COVID-19 Twitter data. Therefore, this study reveals how sentiment analysis can provide relevant insights for managing the pandemic by applying a behavioral and social science lens. In this context, our systematic literature review focuses on machine learning-based sentiment analysis techniques and compares the best-performing classification algorithms for COVID-19related Twitter data. We performed a search in five databases, which are: IEEE Xplore DL, ScienceDirect, SpringerLink, ACM DL, and AIS Electronic Library. This search resulted in 40 papers published between October 2019 and January 2022 that used sentiment analysis to evaluate the public opinion on COVID-19-related topics, which we further investigated. Our research indicates that the best performing models in terms of accuracy are ensemble models that comprise various machine learning classifiers. Especially BERT and RoBERTa models provide the most promising results when fine-tuned on Twitter data. Our study aims to combine machine learning-based sentiment analysis and insights from social and behavioral science to provide decision-makers and public health experts with guidance on the application of sentiment analysis in the fight against the spread of COVID-19.

show abstract

“…In late 2019, the world witnessed the spread of the coronavirus (COVID-19), which infected many industries and companies globally, including the social, health, economic, and educational sectors ( Shambour & Abu-Hashem, 2021 ; Singh, Jakhar & Pandey, 2021 ). The epidemic forced many countries to implement restrictions to combat the transmission of infection and put preventive measures to push the public into social distancing, which in turn had a substantial influence on many aspects and activities of life that people are familiar with ( Mittal, Mittal & Aggarwal, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

“…Recently, studies have shown a growing interest in knowing the feelings of users of different social media platforms through machine learning (ML) and lexicon-based algorithms that analyze and categorize what users think across social media platforms, such as Facebook, Twitter, and YouTube. The analysis of such data helps in understanding the thoughts of individuals and society in response to specific events and predicting future trends, such as those related to the COVID-19 pandemic ( Mittal, Mittal & Aggarwal, 2021 ), tourism ( Chaabani, Toujani & Akaichi, 2018 ), disasters ( Zaki et al, 2018 ), and economy ( Urlam, 2021 ). Despite many publications describing several subjects related to tracking and sentiment analytics in the literature, the Arabic literature on sentiment analysis (SA) topics has been comparatively weak compared with that in English ( Abu Farha & Magdy, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Analyzing perceptions of a global event using CNN-LSTM deep learning approach: the case of Hajj 1442 (2021)

Shambour¹

2022

PeerJ Computer Science

View full text Add to dashboard Cite

Hajj (pilgrimage) is a unique social and religious event in which many Muslims worldwide come to perform Hajj. More than two million people travel to Makkah, Saudi Arabia annually to perform various Hajj rituals for four to five days. However, given the recent outbreak of the coronavirus (COVID-19) and its variants, Hajj in the last 2 years 2020–2021 has been different because pilgrims were limited down to a few thousand to control and prevent the spread of COVID-19. This study employs a deep learning approach to investigate the impressions of pilgrims and others from within and outside the Makkah community during the 1442 AH Hajj season. Approximately 4,300 Hajj-related posts and interactions were collected from social media channels, such as Twitter and YouTube, during the Hajj season Dhul-Hijjah 1–13, 1442 (July 11–23, 2021). Convolutional neural networks (CNNs) and long short-term memory (LSTM) deep learning methods were utilized to investigate people’s impressions from the collected data. The CNN-LSTM approach showed superior performance results compared with other widely used classification models in terms of F-score and accuracy. Findings revealed significantly positive sentiment rates for tweets collected from Mina and Arafa holy sites, with ratios exceeding 4 out of 5. Furthermore, the sentiment analysis (SA) rates for tweets about Hajj and pilgrims varied during the days of Hajj. Some were classified as positive tweets, such as describing joy at receiving the days of Hajj, and some were negative tweets, such as expressing the impression about the hot weather and the level of satisfaction for some services. Moreover, the SA of comments on several YouTube videos revealed positive classified comments, including praise and supplications, and negative classified comments, such as expressing regret that the Hajj was limited to a small number of pilgrims.

show abstract

Identification of affective valence of Twitter generated sentiments during the COVID-19 outbreak

Cited by 17 publications

References 82 publications

“Help Us!”: a content analysis of COVID-19 help-seeking posts on Weibo during the first lockdown

“Help Us!”: a content analysis of COVID-19 help-seeking posts on Weibo during the first lockdown

Machine Learning Techniques for Sentiment Analysis of COVID-19-Related Twitter Data

Analyzing perceptions of a global event using CNN-LSTM deep learning approach: the case of Hajj 1442 (2021)

Contact Info

Product

Resources

About