An analysis of emotions and the prominence of positivity in #BlackLivesMatter tweets

Field, Anjalie; Park, Chan Young; Theóphilo, Antônio; Watson-Daniels, Jamelle; Tsvetkov, Yulia

doi:10.1073/pnas.2205767119

Cited by 13 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It encourages participation in any movements and sustained involvement within them. A study conducted by Field et al [20], adopted natural language processing techniques to analyze emotions conveyed in tweets about the 2020 black lives matter protests. In their study, a few-shot domain adaptation approach was used to measure the different emotions expressed in the tweets following the death of George Floyd in May 2020.…”

Section: Literature Reviewmentioning

confidence: 99%

Text Mining and Emotion Classification on Monkeypox Twitter Dataset: A Deep Learning-Natural Language Processing (NLP) Approach

Olusegun,

Oladunni,

Audu

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Emotion classification has become a valuable tool in analyzing text and emotions people express in response to events or crises, particularly on social media and other online platforms. The recent news about monkeypox highlighted various emotions individuals felt during the outbreak. People's opinions and concerns have been very different based on their awareness and understanding of the disease. Although there have been studies on monkeypox, emotion classification related to this virus has not been considered. As a result, this study aims to analyze the emotions individual expressed on social media posts related to the monkeypox disease. Our goal is to provide real-time information and identify critical concerns about the disease. To conduct our analysis, first, we extract and preprocess 800,000 datasets and then use NRCLexicon, a Python library, to predict and measure the emotional significance of each text. Secondly, we develop deep learning models based on Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Bi-directional LSTM (BiLSTM), and the combination of Convolutional Neural Networks and Long Short-Term Memory (CLSTM) for emotion classification. We use SMOTE (Synthetic Minority Oversampling Technique) and Random Undersampling techniques to address the class imbalance in our training dataset. The results of our study revealed that the CNN model achieved the highest performance with an accuracy of 96%. Overall, emotion classification on the monkeypox dataset can be a powerful tool for improving our understanding of the disease. The findings of this study will help develop effective interventions and improve public health.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Text Mining and Emotion Classification on Monkeypox Twitter Dataset: A Deep Learning-Natural Language Processing (NLP) Approach

Olusegun,

Oladunni,

Audu

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Thus, the explosive growth of a movement dedicated to racial equality, which, by some accounts, was possibly the largest protest movement in American history (Buchanan, Bui and Patel, 2020), likely posed a perceived threat to and induced fear and anxiety in many white Americans (Rose, 2020;Smith and King, 2021;Field et al, 2022). Second, the unexpected outbreak of large-scale protests created substantial spatial and temporal variation in the incidence of BLM protests, and therefore a source of variation in perceived racial threats.…”

Section: Introductionmentioning

confidence: 99%

Perceived Racial Threats Increase Demand for Conservative Media: Evidence from Black Lives Matter Protests and Fox News Ratings

Jensen¹,

Karell²

2023

Preprint

View full text Add to dashboard Cite

With the growing evidence that the content on Fox News Channel (FNC) influences its viewers' attitudes and behaviors, it is important that we better understand the real-world factors driving demand for FNC, especially among those who are not already frequent viewers. Yet, our ability to identify these factors is plagued by difficult methodological issues, most notably, the selection problem of inferring the determinants of demand from content. This study overcomes these challenges by exploiting the substantial spatial and temporal variation in the Black Lives Matter (BLM) protests during 2020, the year of George Floyd's murder and other prominent police killings of Black Americans, to examine whether perceived racial threats increased FNC viewership. We construct a census block group-week panel of BLM protests and FNC ratings during 2020. With this spatial panel, we test whether the local occurrence of a BLM protest increased the portion of the local population watching FNC in the subsequent period. We find that the number of FNC viewers rose by approximately 2% following a BLM protest. At the same time, we find evidence that viewership of CNN, a moderate news channel, was unaffected and possibly declined. Our results, which survive robustness checks, tests of the modeling assumptions, and replication at the census tract level, can be interpreted as causal under reasonable assumptions. The findings provide real-world evidence that perceived racial threats increase demand for conservative media.

show abstract

“…Research that has examined geographic state and city-level correlations between BLM tweets and protest activity in 2020 further supports the predictions of the present research. That is, such research has found that BLM tweets are associated with negative emotions like anger yet also positive emotions like hope and optimism ( 13 ). Thus, the present research builds on such findings in several ways.…”

Section: Introductionmentioning

confidence: 99%

Racism hurts, can antiracism heal?: Positive mental health correlates of antiracist engagement

Brannon

2023

PNAS Nexus

View full text Add to dashboard Cite

Racism can hurt by negatively impacting mental health. For instance, large-scale events tied to racism like the May 2020 police-involved murder of George Floyd have been linked to poor mental health indicators (e.g., depression, anxiety). Notably, racism can spark anti-racist engagement— support for addressing systemic racism. For example, Floyd’s murder sparked unprecedented anti-racist engagement including heightened Black Lives Matter (BLM) support and protest participation. The present research explored the potential that anti-racist engagement can heal: be positively associated with well-being. First, Study 1 found that state-level BLM engagement (i.e., protest numbers, anti-racism information-seeking on Google/YouTube) during an 8-week period following Floyd’s death was associated with positive mental health indicators (i.e., lower depression and anxiety, higher self-rated health). It found these effects among racial/ethnic minorities (e.g., Black/African Americans, Hispanics, N=161,359) and Whites (N=516,002). Then, Study 2 examined social media data (i.e., tweets) and emotional well-being. It used a measure of happiness indexed across 144,649,285,571 tweets from 2019 through 2021. It found a positive correlation between the volume of tweets with anti-racist engagement content (e.g., referenced efforts to address systemic racism) and the happiness measure. Finally, Study 3 examined anti-racism protest data/information-seeking and a sample of BLM tweets (N=100,321) posted between April and July 2020. Conceptually replicating Studies 1-2, Study 3 found that anti-racist engagement was associated with greater positive emotion/sentiment (e.g., happiness) relative to negative emotion/sentiment (e.g., anxiety). Relevant to theory and policy, the observed results suggest that anti-racist engagement can be associated with benefits for well-being across racial/ethnic groups.

show abstract

An analysis of emotions and the prominence of positivity in #BlackLivesMatter tweets

Cited by 13 publications

References 53 publications

Text Mining and Emotion Classification on Monkeypox Twitter Dataset: A Deep Learning-Natural Language Processing (NLP) Approach

Text Mining and Emotion Classification on Monkeypox Twitter Dataset: A Deep Learning-Natural Language Processing (NLP) Approach

Perceived Racial Threats Increase Demand for Conservative Media: Evidence from Black Lives Matter Protests and Fox News Ratings

Racism hurts, can antiracism heal?: Positive mental health correlates of antiracist engagement

Contact Info

Product

Resources

About