Using Twitter to track immigration sentiment during early stages of the COVID-19 pandemic

Rowe, Francisco; Mahony, Michael; Graells-Garrido, Eduardo; Rango, Marzia; Sievers, Niklas

doi:10.1017/dap.2021.38

Cited by 30 publications

(22 citation statements)

References 60 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We approximated these movements analysing changes in local populations. While this is not a serious constrain, it resonates with calls made elsewhere to triangulate digital trace data with other sources of information as we have done in this paper (Rowe et al 2021;Rowe et al 2022) .…”

Section: Discussionmentioning

confidence: 56%

Sensing Population Displacement from Ukraine Using Facebook Data: Potential Impacts and Settlement Areas

Rowe¹,

Neville²,

González‐Leonardo³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The escalation of conflict in Ukraine has triggered the largest refugee crisis in Europe since WWII. As of 17 August 2022, over 6.6 million people have fled Ukraine. Large-scale efforts have been made to collect data and measure the scale of forced population displacements, and identify the major receiving countries of these population flows. Current evidence has thus focused on providing a country level representation of the unfolding refugee crisis. Less is known about the subnational patterns of population displacement within Ukraine, and potential subnational settlement areas of the continuous flow of Ukrainian refugees in major receiving countries. Highly granular geographical data in real time are critical to these ends to ensure the appropriate delivery of humanitarian assistance where it is most needed. Drawing on digital trace data from Meta-Facebook, this paper aims to identify and assess the potential settlement areas and impacts of population displacements on the demographic and economic structures of sub-national communities within and outside Ukraine. We reveal large population losses in eastern, southern and northern Ukraine, particularly Khersonska (59%), Kharkivska (55%) and Kyiv (45%), and gains in western areas, specially in Livivska (16%). We also find reductions in female and young populations across the country, and increases in male and older populations in central and western regions. We identify likely settlement areas in some countries (Poland, Czechia, Slovakia, Hungary, Italy, Germany and Spain), noting that Ukrainian refugees are less likely to remain in countries which have recorded large refugee influxes but lack of local social networks, such as Romania and Turkey. We also reveal the potential impact of refugees moving to areas with old population structures and low unemployment. Yet, these impacts appear to differ across countries.

show abstract

Section: Discussionmentioning

confidence: 56%

Sensing Population Displacement from Ukraine Using Facebook Data: Potential Impacts and Settlement Areas

Rowe¹,

Neville²,

González‐Leonardo³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…They were also not perceived as "scapegoats" that were to be blamed given their status in society (39). This was in a way surprising given that other studies have shown that ostracism or other forms of discriminatory practises would be expected in a pandemic (40)(41)(42).…”

Section: Discussionmentioning

confidence: 91%

A qualitative study on health stigma and discrimination in the first year of the COVID-19 pandemic: Lessons learnt from a public health perspective

Tang²,

Low³

et al. 2023

Front. Public Health

View full text Add to dashboard Cite

BackgroundStigmatisation, misinformation and discrimination have been magnified globally due to the COVID-19 pandemic. The healthcare sector was not spared from this. We conducted a transnational study, using the Health Stigma and Discrimination framework (HSDF) to explore public perception and reactions to the COVID-19 pandemic in a multicultural context. Findings from the Asian arm of the study, sited in Singapore, are reported in this paper.MethodsThis phenomenological research deployed semi-structured informant interviews using non-probability sampling approaches to recruit members of the public. Interviews were coded independently by two researchers and thematic analysis was used to analyse the responses.ResultsTwenty-nine members of the public (23–80 years old) were interviewed between Oct 2020 to Feb 2021. Five major themes were identified: (i) perception of stigma amongst respondents, (ii) experiences of stigma amongst respondents, (iii) views on what drove stigma and misinformation, (iv) facilitators in preventing and reducing stigma and misinformation, and (v) ageist attitudes towards older adults. Overall, construction workers living in dormitories, healthcare workers, and to some extent tourists from China, were perceived to have been stigmatised and shunned by the public. Place-based stigmatisation was common; participants responded by avoiding places that had confirmed cases of COVID-19. Perceived stigma was temporary and not enduring, driven at the outset by fear of being infected. This study also identified the role played by trust in reducing stigmatisation. The relative absence of politicising of issues and high-quality information readily disseminated to the public were reported as factors that could have reduced and prevented stigma and misinformation on the various groups. Ageist attitudes were observed in some participants with older adults being labelled as vulnerable, susceptible to misinformation and being less able to cope during the pandemic.ConclusionThrough the lens of the HSDF, this study provided an exploratory account of the nature of stigma that resulted from the COVID-19 pandemic in an Asian context. It also shed light on facilitators in preventing and reducing stigma during an outbreak especially the role of trust and communications during a public health crisis.

show abstract

“…They also have designed an algorithm to find the top-involved users at various times using the user's involvement score. Similarly, Rowe et al [25] have analyzed the tweets using topic modeling and Valence Aware Dictionary and sEntiment Reasoner (VADER) with respect to immigrants. They have observed that there is a steady increase of negative attitudes towards the immigrants during the pandemic era.…”

Section: Related Workmentioning

confidence: 99%

Sentiment Drift Detection and Analysis in Real Time Twitter Data Streams

Susi¹,

Shanthi²

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Handling sentiment drifts in real time twitter data streams are a challenging task while performing sentiment classifications, because of the changes that occur in the sentiments of twitter users, with respect to time. The growing volume of tweets with sentiment drifts has led to the need for devising an adaptive approach to detect and handle this drift in real time. This work proposes an adaptive learning algorithm-based framework, Twitter Sentiment Drift Analysis-Bidirectional Encoder Representations from Transformers (TSDA-BERT), which introduces a sentiment drift measure to detect drifts and a domain impact score to adaptively retrain the classification model with domain relevant data in real time. The framework also works on static data by converting them to data streams using the Kafka tool. The experiments conducted on real time and simulated tweets of sports, health care and financial topics show that the proposed system is able to detect sentiment drifts and maintain the performance of the classification model, with accuracies of 91%, 87% and 90%, respectively. Though the results have been provided only for a few topics, as a proof of concept, this framework can be applied to detect sentiment drifts and perform sentiment classification on real time data streams of any topic.

show abstract

Using Twitter to track immigration sentiment during early stages of the COVID-19 pandemic

Cited by 30 publications

References 60 publications

Sensing Population Displacement from Ukraine Using Facebook Data: Potential Impacts and Settlement Areas

Sensing Population Displacement from Ukraine Using Facebook Data: Potential Impacts and Settlement Areas

A qualitative study on health stigma and discrimination in the first year of the COVID-19 pandemic: Lessons learnt from a public health perspective

Sentiment Drift Detection and Analysis in Real Time Twitter Data Streams

Contact Info

Product

Resources

About