We apply moral foundations theory (MFT) to explore how the public conceptualizes the first eight months of the conflict between Ukraine and the Russian Federation (Russia). Our analysis includes over 1.1 million English tweets related to the conflict over the first 36 weeks. We used linguistic inquiry word count (LIWC) and a moral foundations dictionary to identify tweets’ moral components (care, fairness, loyalty, authority, and sanctity) from the United States, pre- and post-Cold War NATO countries, Ukraine, and Russia. Following an initial spike at the beginning of the conflict, tweet volume declined and stabilized by week 10. The level of moral content varied significantly across the five regions and the five moral components. Tweets from the different regions included significantly different moral foundations to conceptualize the conflict. Across all regions, tweets were dominated by loyalty content, while fairness content was infrequent. Moral content over time was relatively stable, and variations were linked to reported conflict events.

What drives changes in the thematic focus of state-linked manipulated media? We study this question in relation to a long-running Iranian state-linked manipulated media campaign that was uncovered by Twitter in 2021. Using a variety of machine learning methods, we uncover and analyze how this manipulation campaign’s topical themes changed in relation to rising Covid-19 cases in Iran. By using the topics of the tweets in a novel way, we find that increases in domestic Covid-19 cases engendered a shift in Iran’s manipulated media focus away from Covid-19 themes and toward international finance- and investment-focused themes. These findings underscore (i) the potential for state-linked manipulated media campaigns to be used for diversionary purposes and (ii) the promise of machine learning methods for detecting such behaviors.

This article explores the language of social media by analyzing a selection of linguistic features in four corpora of Swedish social media available at Språkbanken Text: Blog mix, Familjeliv, Flashback, and Twitter. Previous research describes the language of these corpora as informal, spoken-like, unedited, non-standard, and innovative. Our corpus analysis confirms the informal and spoken-like nature of social media, while also showing that these traits are unevenly distributed across the various social media corpora and that they are also present in other traditional written corpora, such as novels. Our findings also reveal that the social media corpora show traits of involved and interactional language.

While prior studies have barely explored social interaction for COVID-19 across Asia, this study highlights how people interact with each other for the COVID-19 pandemic among India, Japan, and South Korea based on social network analysis by employing NodeXL for Twitter between July 27 and July 28, 2020. This study finds that the Ministry of Health and Prime Minister of India, news media of Japan, and the president of South Korea play the most essential role in social networks in their country, respectively. Second, governmental key players play the most crucial role in South Korea, whereas they play the least role in India. Third, the Indian are interested in COVID-19 deaths, the Japanese care about the information of COVID-19 patients, and the South Korean focus on COVID-19 vaccines. Therefore, governments and disease experts should explore their social interaction based on the characteristics of social networks to release important news and information in a timely manner.

This study highlights key players for COVID-19 in Brazil, Peru, Colombia, Chile, Argentina, and Ecuador by employing social network analysis for Twitter. This study finds that key players in Latin America play various roles in COVID-19 social networks, differing from country to country. For example, Brazil has no Latin key players, whereas Colombia and Ecuador have 8 Latin key players in the top 10 key players. Secondly, the role of governmental key players also varies across different countries. For instance, Peru, Chile, Argentina, and Ecuador have the governmental key player as the top key player, whereas Brazil and Colombia have the news media key player as the first. Thirdly, each country shows different social networks according to groups. For instance, Colombia exhibits the most open social networks among groups, whereas Brazil shows the most closed social networks among the 6 Latin countries. Fourthly, several top tweeters are common across the 6 Latin American countries. For example, Peru and Colombia have caraotadigital (Venezuelan news media), and Chile and Argentina have extravzla (Venezuelan news media) as the top tweeter.

We analyze a cache of tweets from partisan users concerning the confirmation hearings of Justices Brett Kavanaugh, Amy Coney Barrett, and Ketanji Brown Jackson. Using these original data, we investigate how Twitter users with partisan leanings interact with judicial nominations and confirmations. We find that these users tend to exhibit behavior consistent with offline partisan dynamics. Our analysis reveals that Democrats and Republicans express distinct emotional responses based on the alignment of nominees with their respective parties. Additionally, our study highlights the active participation of partisans in promoting politically charged topics throughout the confirmation process, starting from the vacancy stage.

Judges are not the first political officials that come to mind when one considers the role of social media in modern politics. Following in the wake of some prominent judicial personalities adopting Twitter, however, a growing number of state high court judges have adopted and established more public personas on the platform. Judges use Twitter in substantively different ways than traditional elected officials (Curry and Fix 2019); however, little is understood about how the use of such social media platforms affects broader judicial networks. Recognizing that judges, like typical social media users, may aspire to expand their networks to build and appeal to broader audiences, we contend that active participation in judicial Twitterverse could yield personal and professional advantages. Here, we address a currently unexplored question: To what extent have judges formed a distinctive “judicial network,” on Twitter, and what discernible patterns present in these networks? Leveraging the unique structure of social media, we collect comprehensive network data on judging using Twitter and analyze what institutional and social factors impact greater power within the judicial network. We find that early adoption, electoral concerns, and connective links between judges all impact the strength of the judicial network, highlighting the complex motivations driving judicial Twitter engagement, and the significance of network building in judges’ social media strategies and its potential impact on career advancement.

The proliferation of social networks has caused an increase in the amount of textual content generated by users. The voluminous nature of such content poses a challenge to users, necessitating the development of technological solutions for automatic summarisation. This paper presents a two-stage framework for generating abstractive summaries from a collection of Twitter texts. In the first stage of the framework, event detection is carried out through clustering, followed by event summarisation in the second stage. Our approach involves generating contextualised vector representations of tweets and applying various clustering techniques to the vectors. The quality of the resulting clusters is evaluated, and the best clusters are selected for the summarisation task based on this evaluation. In contrast to previous studies, we experimented with various clustering techniques as a preprocessing step to obtain better event representations. For the summarisation task, we utilised pre-trained models of three state-of-the-art deep neural network architectures and evaluated their performance on abstractive summarisation of the event clusters. Summaries are generated from clusters that contain (a) unranked tweets, (b) all ranked tweets, and (c) the top 10 ranked tweets. Of these three sets of clusters, we obtained the best ROUGE scores from the top 10 ranked tweets. From the summaries generated from the clusters containing the top ten tweets, we obtained ROUGE-1 F score of 48%, ROUGE-2 F score of 37%, ROUGE-L F score of 44%, and ROUGE-SU F score of 33% which suggests that if relevant tweets are at the top of a cluster, and then better summaries are generated.

Polarizing rhetoric and negative tone are thought to generate more attention on social media. We seek to describe and analyze how presidential candidates in Colombia’s 2022 election deployed (de)polarizing rhetoric and tone, around what topics, and with what effects. We analyze the tweets (and corresponding engagement) of the four leading candidates during the campaign. Tone behaves as expected. Negatively worded tweets receive overall more likes and retweets, though the strength of their effect varies by candidate. Polarizing rhetoric behaves differently. Using polarizing and depolarizing rhetoric proved better than neutral messages, but using depolarizing rhetoric, generated greater engagement than its polarizing counterpart. This study suggests that the visibility of a candidate does not necessarily correspond to their greater use of Twitter, an increased deployment of polarizing rhetoric, or an emphasis on negative emotions. This article provides a glimmer of hope regarding the potential usefulness of positive uniting messages on Twitter (now X).

Used by politicians, journalists, and citizens, Twitter has been the most important social media platform to investigate political phenomena such as hate speech, polarization, or terrorism for over a decade. A high proportion of Twitter studies of emotionally charged or controversial content limit their ability to replicate findings due to incomplete Twitter-related replication data and the inability to recrawl their datasets entirely. This paper shows that these Twitter studies and their findings are considerably affected by nonrandom tweet mortality and data access restrictions imposed by the platform. While sensitive datasets suffer a notably higher removal rate than nonsensitive datasets, attempting to replicate key findings of Kim’s (2023, Political Science Research and Methods 11, 673–695) influential study on the content of violent tweets leads to significantly different results. The results highlight that access to complete replication data is particularly important in light of dynamically changing social media research conditions. Thus, the study raises concerns and potential solutions about the broader implications of nonrandom tweet mortality for future social media research on Twitter and similar platforms.

This article analyzes tweets in the Turkish language from November 2020 to May 2021 in which Kurds are explicitly mentioned that feature negative animalization directed toward Kurds and pro-Kurdish organizations. It systematically compares ways of animalization attribution, to what entities the animalization is attributed mostly, and the attributors (actors) of animalization. First, it argues that animalizing dehumanization directed at Kurds in the data set principally occurs for attributing the lack of four human traits: agency, civility, morality, and rationality. Second, it shows in what different ways the lack of these traits is attributed to Kurdish people in general and to major pro-Kurdish groups such as HDP (the largest pro-Kurdish legal political party) and PKK (the largest pro-Kurdish armed group). Finally, it discloses three main political networks among Twitter users within the data set and characterizes how negative animal references to Kurds, pro-Kurdish groups, and each other were used by these actors. Thus, this research seeks to establish a framework to study other ethnic conflicts from the perspective of animalization and invites further research on whether the trends that were found imply a general tendency around the world.

In this article, we document the gender of the noun “COVID-19” in a database of more than 76,000 tweets and in traditional media (approximately 500,000 articles) in French as spoken in Africa, (North) America and Europe. We find that North American media comply near-categorically with the recommendations of the feminine by the World Health Organization and local linguistic authorities in March 2020. The majority of North American tweets follow suit soon after. The African data show an increase of articles and tweets adopting the feminine after the Académie française's recommendation in May 2020. Finally, the feminine is negligible in the European data. We argue that among the factors at play are dialect-specific differences in French gender and loanword adaptation; the complex relationship among linguistic authorities, the public, and local media; and the relative delay in the Académie française's recommendation of the feminine.