Content uploaded by Adina Nerghes
Author content
All content in this area was uploaded by Adina Nerghes on May 30, 2018
Content may be subject to copyright.
A preview of the PDF is not available
The Refugee/Migrant Crisis Dichotomy on Twitter: A Network and Sentiment Perspective
Abstract and Figures
Media reports, political statements, and social media debates on the refugee/migrant crisis shape the ways in which people and societies respond to those displaced people arriving at their borders world wide. These current events are framed and experienced as a crisis, entering the media, capturing worldwide political attention, and producing diverse and contradictory discourses and responses. The labels "migrant'' and "refugee'' are frequently distinguished and conflated in traditional as well as social media when describing the same groups of people. In this paper, we focus on the simultaneous struggle over meaning, legitimization, and power in representations of the refugee crisis, through the specific lens of Twitter. The 369,485 tweets analyzed in this paper cover two days after a picture of Alan Kurdi -- a three-year-old Syrian boy who drowned in the Mediterranean Sea while trying to reach Europe with his family -- made global headlines and sparked wide media engagement. More specifically, we investigate the existence of the dichotomy between the "deserving'' refugee versus the "undeserving'' migrant, as well as the relationship between sentiment expressed in tweets, their influence, and the popularity of Twitter users involved in this dichotomous characterization of the crisis. Our results show that the Twitter debate was predominantly focused on refugee related hashtags and that those tweets containing such hashtags were more positive in tone. Furthermore, we find that popular Twitter users as well as popular tweets are characterized by less emotional intensity and slightly less positivity in the debate, contrary to prior expectations. Co-occurrence networks expose the structure underlying hashtag usage and reveal a refugee-centric core of meaning, yet divergent goals of some prominent users. As social media become increasingly prominent venues for debate over a crisis, how and why people express their opinions offer valuable insights into the nature and direction of these debates.
Figures - uploaded by Adina Nerghes
Author content
All figure content in this area was uploaded by Adina Nerghes
Content may be subject to copyright.
... Migration-related issues were probed in the context of France (Siapera et al. 2018), Germany (Riyadi and Widhiasti 2020;Siapera et al. 2018), Italy (Capozzi et al. 2020;Kim et al. 2020b), Korea (Kim et al. 2020a), Netherlands (Udwan, Leurs, and Alencar 2020), Spain (Calderón, de la Vega, and Herrero 2020; Vázquez and Pérez 2019), Syria (Dekker et al. 2018;Rettberg and Gajjala 2016;Reel et al. 2018;Öztürk and Ayvaz 2018;Udwan, Leurs, and Alencar 2020), Turkey (Bozdag and Smets 2017;Özerim and Tolay 2020), the UK (Coletto et al. 2016), and the USA (Zagheni et al. 2018). Information science researchers mostly analyzed online contents, such as Facebook (Capozzi et al. 2020;Hrdina 2016;Zagheni et al. 2018), Instagram (Guidry et al. 2018), Pinterest (Guidry et al. 2018), YouTube , Twitter (Alcántara-Plá and Ruiz-Sánchez 2018; Aswad and Menezes 2018;Calderón, de la Vega, and Herrero 2020;Gualda and Rebollo 2016;Kim et al. 2020;Nerghes and Lee 2018;Pope and Griffith 2016;Vázquez and Pérez 2019) as well as mainstream media (Nerghes and Lee 2019). ...
... These studies have employed various NLP tools such as topic modeling (Calderón, de la Vega, and Herrero 2020;Guidry et al. 2018), sentiment analysis Öztürk and Ayvaz 2018;Pope and Griffith 2016), hashtag analysis (Özerim and Tolay 2020;Kreis 2017;Riyadi and Widhiasti 2020), and network analysis (Himelboim et al. 2017;Nerghes and Lee 2018;2019). ...
We draw insights from the social psychology literature to identify two facets of Twitter deliberations about migrants, i.e., perceptions about migrants and behaviors towards migrants. Our theoretical anchoring helped us in identifying two prevailing perceptions (i.e., sympathy and antipathy) and two dominant behaviors (i.e., solidarity and animosity) of social media users towards migrants. We have employed unsupervised and supervised approaches to identify these perceptions and behaviors. In the domain of applied NLP, our study offers a nuanced understanding of migrant-related Twitter deliberations. Our proposed transformer-based model, i.e., BERT + CNN, has reported an F1-score of 0.76 and outperformed other models. Additionally, we argue that tweets conveying antipathy or animosity can be broadly considered hate speech towards migrants, but they are not the same. Thus, our approach has fine-tuned the binary hate speech detection task by highlighting the granular differences between perceptual and behavioral aspects of hate speeches.
... Migration-related issues were probed in the context of France (Siapera et al. 2018), Germany (Riyadi and Widhiasti 2020;Siapera et al. 2018), Italy (Capozzi et al. 2020;Kim et al. 2020b), Korea (Kim et al. 2020a), Netherlands (Udwan, Leurs, and Alencar 2020), Spain (Calderón, de la Vega, and Herrero 2020;Vázquez and Pérez 2019), Syria (Dekker et al. 2018;Rettberg and Gajjala 2016;Reel et al. 2018;Öztürk and Ayvaz 2018;Udwan, Leurs, and Alencar 2020), Turkey (Bozdag and Smets 2017;Özerim and Tolay 2020), the UK (Coletto et al. 2016), and the USA (Zagheni et al. 2018). Information science researchers mostly analyzed online contents, such as Facebook (Capozzi et al. 2020;Hrdina 2016;Zagheni et al. 2018), Instagram (Guidry et al. 2018), Pinterest (Guidry et al. 2018), YouTube , Twitter (Alcántara-Plá and Ruiz-Sánchez 2018; Aswad and Menezes 2018; Calderón, de la Vega, and Herrero 2020; Gualda and Rebollo 2016;Kim et al. 2020;Nerghes and Lee 2018;Pope and Griffith 2016;Vázquez and Pérez 2019) as well as mainstream media (Nerghes and Lee 2019). ...
... These studies have employed various NLP tools such as topic modeling (Calderón, de la Vega, and Herrero 2020;Guidry et al. 2018), sentiment analysis Öztürk and Ayvaz 2018;Pope and Griffith 2016), hashtag analysis (Özerim and Tolay 2020;Kreis 2017;Riyadi and Widhiasti 2020), and network analysis (Himelboim et al. 2017;Nerghes and Lee 2018;2019). ...
We draw insights from the social psychology literature to identify two facets of Twitter deliberations about migrants, i.e., perceptions about migrants and behaviors towards mi-grants. Our theoretical anchoring helped us in identifying two prevailing perceptions (i.e., sympathy and antipathy) and two dominant behaviors (i.e., solidarity and animosity) of social media users towards migrants. We have employed unsuper-vised and supervised approaches to identify these perceptions and behaviors. In the domain of applied NLP, our study of-fers a nuanced understanding of migrant-related Twitter de-liberations. Our proposed transformer-based model, i.e., BERT + CNN, has reported an F1-score of 0.76 and outper-formed other models. Additionally, we argue that tweets con-veying antipathy or animosity can be broadly considered hate speech towards migrants, but they are not the same. Thus, our approach has fine-tuned the binary hate speech detection task by highlighting the granular differences between perceptual and behavioral aspects of hate speeches.
... Societal perceptions about migrants also get reflected in usergenerated social media content. A handful of studies noted bipolar opinions such as deserving vis-à-vis undeserving migrants, securityrelated concerns vis-à-vis humanitarian concerns, or critical visà-vis positive opinions [24,26,29,43]. Broadly, social media data reveals two diametrically opposite views: humanitarian concerns (because migrants face discrimination in terms of societal acceptance or employment opportunities or the lack of access to basic health or education facilities) and threat perceptions (because migrants can be a cultural as well as security threats, or they can be the economic burden for the host country) [29,33,56]. ...
... The selected language is crucial, as it influences the perceived legitimacy of claims to international protection and justifies policies of exclusion and containment [14,47]. This framing of the discussion based on the migrant/refugee dichotomy has also been observed in social media debates [51]. The International Centre for Migration Policy Development (ICMPD) identifies the displacement of populations due to (civil) wars and conflicts as one of the main drivers of migration flow [22]. ...
... The selected language is crucial, as it influences the perceived legitimacy of claims to international protection and justifies policies of exclusion and containment [14,47]. This framing of the discussion based on the migrant/refugee dichotomy has also been observed in social media debates [51]. The International Centre for Migration Policy Development (ICMPD) identifies the displacement of populations due to (civil) wars and conflicts as one of the main drivers of migration flow [22]. ...
The war in Ukraine seems to have positively changed the attitude toward the critical societal topic of migration in Europe -- at least towards refugees from Ukraine. We investigate whether this impression is substantiated by how the topic is reflected in online news and social media, thus linking the representation of the issue on the Web to its perception in society. For this purpose, we combine and adapt leading-edge automatic text processing for a novel multilingual stance detection approach. Starting from 5.5M Twitter posts published by 565 European news outlets in one year, beginning September 2021, plus replies, we perform a multilingual analysis of migration-related media coverage and associated social media interaction for Europe and selected European countries. The results of our analysis show that there is actually a reframing of the discussion illustrated by the terminology change, e.g., from "migrant" to "refugee", often even accentuated with phrases such as "real refugees". However, concerning a stance shift in public perception, the picture is more diverse than expected. All analyzed cases show a noticeable temporal stance shift around the start of the war in Ukraine. Still, there are apparent national differences in the size and stability of this shift.
... Seven participants (P1-4, P7-9) state that, as more researchers joined the field and more funding and data became available, more prolonged studies have been pursued, which made it possible to dive deeper and examine different study areas, such as family dynamics and mental health, as evident by Figure 6 where there is a steady increase in the psychological dimension of mobility. In terms of studied technologies, 34 papers focus solely on mobile/smartphones (e.g., [25,34]) and 31 papers on social media platforms (especially Facebook and Twitter, e.g., [95,115]). This is due to the rapid mobile device and social media penetration throughout the world, particularly in migrant-emitting countries. ...
This article presents a thorough discussion of the trajectories of international migration research in HCI. We begin by reporting our survey findings of 282 HCI-related publications about migration from nine digital libraries between 2010-2019, summarizing how this research stream has evolved, the geographies and populations it encompasses, and the methodologies it utilizes. We then augment these findings with data from interviews with 11 skilled researchers who reflect on their working experience in this area. Our analysis reveals how the domain has evolved from the European migrant crisis to a more global agenda of migration and points towards a shifting focus from addressing immediate needs to acknowledging more complex political and emotional aspects of mobility. We also uncover the critical role of academic, local, and international politics in migration research in HCI. We discuss these findings to explore future opportunities in this area and advance HCI research discourse with the marginalized populace.
The paper investigates changing levels of online concern about the Kashmiri Pandit migration of the 1990s on Twitter.
Although decades old, this movement of people is an ongoing issue in India, with no current resolution. Analysing changing reactions to it on social media may shed light on trends in public attitudes to the event. Tweets were downloaded
from Twitter using the academic version of its application programming interface (API) with the aid of the free social media analytics software Mozdeh. A set of 1000 tweets was selected for content analysis with a random number generator
in Mozdeh. The results show that the number of tweets about the issue has increased over time, mainly from India, and
predominantly driven by the release of films like Shikara and The Kashmir Files. The tweets show apparent universal support for the Pandits but often express strong emotions or criticize the actions of politicians, showing that the migration is
an ongoing source of anguish and frustration that needs resolution. The results also show that social media analysis can
give insights even into primarily offline political issues that predate the popularity of the web, and can easily incorporate
international perspectives necessary to understand complex migration issues.
International students have been historically valued by universities for their contributions to their host countries. Yet, representations of international students in the general public have become increasingly mixed, an issue likely exacerbated by COVID-19, which has shown increased hostility towards international students. Given the increased reports of discrimination during this period, there is ongoing need to understand how international students have been represented in this specific time of crisis. Our study analysed public representations of international students through Twitter data and qualitative analysis of 6,501 posts made during the immediate COVID-19 crisis (January-April 2020). Our findings confirm competing public representations of international students that changed over time: initially through stereotyping and depictions as assumed disease carriers, shifting to empathy and support after university campus closures. We also outline themes of racism and discrimination, which are of importance for the global higher education sector as we move into a post-COVID world.
This work examines how the outbreak of the COVID-19 pandemic reshaped the migration debate on Twitter. Through co-hashtag network analysis, time-frequency and content analysis, it shows that the pandemic was related with positive (humanitarian) and negative (threat) stances about migration. The positive side focused on the need to protect refugees stranded at camps in Greece from COVID-19. The negative focused on the Greek-Turkish land-border crisis (Evros crisis), using COVID-19 to reinforce migrants as racialized others. These findings fit the problematization of positive and negative migrant representations in the Global north as Eurocentric. In the case of camps, refugees fit well within the victim/helpless frame, justifying humanitarianism, this time on health grounds. Regarding the border crisis, refugees also fit the Eurocentric frame of vio-lent/male/inferior other who could spread a deadly virus. Overall, COVID-19 intertwined with migration in Twitter debates, reinforcing the racialized, Eurocentric representational field on migrants from the Global south.
Social media data provide increasing opportunities for the automated analysis of large sets of textual documents. So far, automated tools have been developed either to account for the social networks among participants in the debates, or to analyze the content of these debates. Less attention has been paid to mapping co‐occurrences of actors (participants) and topics (content) in online debates that can be considered as socio‐semantic networks. We propose a new, automated approach that uses the whole matrix of co‐addressed topics and actors for understanding and visualizing online debates. We show the advantages of the new approach with the analysis of two data sets: first, a large set of English‐language Twitter messages at the Rio + 20 meeting, in June 2012 (72,077 tweets), and second, a smaller data set of Dutch‐language Twitter messages on bird flu related to poultry farming in 2015–2017 (2,139 tweets). We discuss the theoretical, methodological, and substantive implications of our approach, also for the analysis of other social media data.
The immense growth of the social Web, which has made a large amount of user data easily and publicly available, has opened a whole new spectrum for research in social behavioral sciences. However, as the volume of social media content increases at a very fast rate, it becomes extremely difficult to systematically obtain high-level information from this data. As a consequence, tasks related to the analysis of historical news events based on social media data have not been explored, which limits any type of comparative historical research, causality analysis, and discovery of knowledge from patterns extracted from aggregated social media event information. In this work, we target this issue by proposing a compact high-level representation of news events using social media information. This representation explicitly includes temporal information about the event and information about locations, in particular of geopolitical entities. We call this a spatio-temporal context-aware event representation. Our hypothesis is that by including social, temporal, and spatial information in the event representation, we are enabling the analysis of historical world news from a social and geopolitical perspective. This facilitates, new information retrieval tasks related to historical event information extraction and international relations analysis. We support our claims by presenting two applications of this idea: the first, a visual tool, named Galean, for retrieval and exploration of historical news events within their geopolitical and temporal context. The second, a quantitative analysis of a 2-year Twitter dataset of news events reported by U.S. and U.K. media, which we explore using data mining techniques on our event representations. We present two case studies of event exploration using Galean and user evaluation of this tool, as well as details of our data mining empirical results.
By focusing on the recent events in the Middle East, that have pushed many to flee and seek refuge in neighboring countries or in Europe, we investigate dynamics of label use in social media, the emergent patterns of labeling that can cause further disaffection and tension, and the sentiments associated with the different labels. To achieve this, we examine key labels pertaining to the refugee/migrant crisis and their usage in the user comment thread of a highly viewed and informational video of the crisis on YouTube. The use of labels indicate that migration issues are being framed not only through labels characterizing the crisis but also by their describing the individuals themselves. The sentiments associated with these labels depart from what one would normally expect; in particular, negative sentiment is attached to labels that would otherwise be deemed neutral or positive. Interestingly, both positive and negative labels exhibit increased negativity across time. Using topic modeling and sentiment analysis jointly, we discover that the latent topics of the most positive comments show more overlap than those topics of the most negative comments, which are more focused and partitioned. In terms of sentiment, we find that labels indicating some degree of perceived agency or opportunity, such as 'migrant' or 'immigrant', are embedded in less sympathetic comments than those labels indicating a need to escape war-torn regions or persecution (e.g., asylum seeker or refugee). Our study offers valuable insights into the direction of public sentiment and the nature of discussions surrounding this significant societal event, as well as the nature of online opinion sharing.
Adopting a socio-semantic perspective, this study aims to verify the relation between social influence and discourse similarity networks in workgroups and explore its modification over time. Data consist of video transcripts of 45 3-h group meetings and weekly sociometric questionnaires. Relation between tie strength, actor centrality within the influence network, and shared elements of discourse between group members are examined over time. Observed correlations support the hypothesis of a relation between social influence and discourse similarity. Changes over time suggest a similarity threshold above which the relation between similarity and influence is reversed.
In present research, the authors examined how social media influencers affect the overall sentiment of a topic. To this end, they utilized supervised machine learning approach to develop SentiRobo for measuring the sentiment score of social media content. In the next stage, they studied social media datasets with 375,141 records in the education domain to investigate the correlation between social media topics and top authors' sentiment. The Pearson correlation test results revealed that top one percent of social media authors are enough to significantly influence the whole sentiment of each topic.
This paper explores the relations between social ties and cultural constructs in small groups. The analysis uses cross-sectional data comprising both social networks within three art groups and semantic networks based on verbal expressions of their members. We examine how positions of actors in the intragroup social networks associate with the properties of cultural constructs they create jointly with other group members accounting for different roles actors play in collective culture constructing. We find that social popularity rather hinders sharing of cultural concepts, while those individuals who socially bridge their groups come to share many concepts with others. Moreover, focusing and, especially, integration of cultural constructs, rather than mere ‘thickness’ of those, accompany intense interactions between the leaders and the followers.
Emotions are important in communication to effectively convey messages and to understand reactions to messages. Large scale studies of communication need methods to detect sentiment in order to investigate or model the processes involved. This chapter describes the sentiment strength detection program SentiStrength that was developed during the CyberEmotions project to detect the strength of sentiments expressed in social web texts. SentiStrength uses a lexical approach that exploits a list of sentiment-related terms and has rules to deal with standard linguistic and social web methods to express sentiment, such as emoticons, exaggerated punctuation and deliberate misspellings. This chapter also describes how SentiStrength can be refined for particular topics and contexts and how variants can be created for different languages. The chapter also briefly describes some studies that have applied SentiStrength to analyse trends in Twitter and You Tube comments.