Twitter Discourse Research Articles

Gender disparities and mental health manifestations in Twitter discourse on student loan debts

ABSTRACT We sought to demonstrate social media’s efficacy as a unique data source to gain insights into people’s perceptions and beliefs. Leveraging Twitter data, we built a model for identifying language markers of mental illness, including depression, anxiety and stress. We explored associations between student loans, gender, and mental health, and investigated gender-specific differences in emotions and sentiments to understand the emotional toll of these disparities. Findings suggest the need for targeted interventions for those experiencing the coexisting burden of student loan and mental illness. This study highlights social media’s potential for studying human emotions and informing social work practices.

‘So Much for Literary Democracy’

Abstract This study examines the effect and impact of literary prizes, focusing on the Not the Booker Prize (NTBP) and its reception on social media platforms. The NTBP, organized by The Guardian, served as a counter to the prestigious Man Booker Prize, offering a more democratic alternative in which the audience is allowed a central role in nominating and voting for books. This article examines the impact of the 2012 scandal surrounding the NTBP, in which allegations of vote-rigging and author canvassing led to significant controversy. By analysing the Twitter discourse, the study explores how scandal influences the perception and value of literary awards. The findings highlight the tension between professional and lay criticism, the role of social media in literary evaluation, and the transformation of literary prizes in the digital age. Finally, the article emphasizes that cultural gatekeeping is undergoing significant change, while pointing out contradictions and frictions besetting the democratization of the literary field.

Exploring Twitter discourse with BERTopic: topic modeling of tweets related to the major German parties during the 2021 German federal election

AbstractWe present a study in the context of computational social science that explores the topics debated in the context of the 2021 German Federal Election by using the topic modeling technique BERTopic. The corpus consists of German language tweets posted by political party accounts of the major German parties, as well as tweets by the general public mentioning the party accounts. We examined the textual content of the tweets but also included the text in images that were posted into the analysis by extracting the text using optical character recognition (OCR). Our results show that the most frequently discussed topics are party-oriented policies (including call-to-action content), climate policy and financial policy, with these topics being discussed in tweets by both, the political party accounts and tweets by accounts mentioning them. In addition, we observed that some topics were discussed consistently throughout the year, such as the COVID-19 pandemic, climate policy or digitization, while other topics, such as the return to power of the Taliban in Afghanistan or Israel were debated to a greater extent at limited time frames during the election year.

“What Flipping Right Does a Teacher Have to Say Being [LGBTQ+] is Okay?”: Understanding Twitter Discourse Around U.S. Anti-LGBTQIA+ Legislation

Amidst an explosion in anti-LGBTQIA+ legislation and hate crimes in the United States, this study examines public discourses around legislation that suppress LGBTQIA+ rights. We conducted a computer-assisted content analysis of 25,711 posts on Twitter (now called X) collected during the time when bans on youths’ access to gender-affirming care were beginning to proliferate across the country. We identified five topics: education, legislation, medical, Disney dispute, anti-LGBTQIA+ attacks, and assessed the sentiments and toxicity levels of each topic. Findings reveal a fractured virtual public sphere in which discussions about LGBTQIA+ rights are contentious and toxic. We found that education was the most salient topic—whether children should be taught about sexual orientation and gender identity in schools—and tweets on this topic were also the most toxic. Overwhelmingly, the tone of the tweets was negative, although this varied by the topic of the tweets. We discuss the implications of our findings for a healthy online public sphere.

“All Eyes on McMinn:” Book Banning Discourse in the Age of Social Media

ABSTRACTThis project explores the intersection of local and online discourse around book bannings using the McMinn County School Board's decision in 2022 to remove Art Spiegelman's graphic memoir, Maus, from their school curriculum as a case study. Through interviews with McMinn County residents and data collected from Twitter, I argue that social media has altered book banning discourse. I interviewed 10 residents and asked them to discuss their experiences when Maus was removed by the school board and to reflect on how the local community responded amidst worldwide scrutiny online. Discourse on Twitter involved collecting over 2000 tweets mentioning the @McMinnCountySch account and tweets discussing Maus to understand online responses to the board's decision. I use Danielle Allen's discourse flow model as the theoretical framework for this project. In my initial findings, discourse began at the local level before traveling online and then back into the local space. Ongoing data analysis has shown that locally, residents were concerned with the board's decision along with the perception of their community once news of the banning spread. This is supported by Twitter discourse, where many tweets cast the McMinn County community in a negative light based on the school board's actions.

ChatGPT in the public eye: Ethical principles and generative concerns in social media discussions

With ChatGPT’s rapid adoption, concerns regarding generative artificial intelligence (AI) have shifted from theoretical to practical. Drawing upon the “algorithmic imaginary” framework from critical algorithm studies and the anthropological concept of “ordinary ethics,” we analyzed Twitter discourse during ChatGPT’s initial deployment, examining 368,359 tweets. Our analysis identified five topics reflecting functional and critical aspects of ChatGPT. We specifically point to two topics with a critical perspective: “Ethics” and “Concerns.” The first aligns with scholarly discussions in AI ethics on fairness and transparency, while the second focuses on ChatGPT’s generative capabilities. This highlights an emerging trend: While the academic discussion on AI ethics has gained popularity, especially in scrutinizing ChatGPT, the conversation is now expanding to more nuanced ethical deliberations. We analyzed the posts’ engagement and sentiment over time, demonstrating the AI ethics community’s influence in addressing the potential and harms of generative AI systems.

Exploring the Correlation between Emojis and Mood Expression in Thai Twitter Discourse

Mood, a long-lasting affective state detached from specific stimuli, plays an important role in behavior. Although sentiment analysis and emotion classification have garnered attention, research on mood classification remains in its early stages. This study adopts a two-dimensional structure of affect, comprising ”pleasantness” and ”activation,” to classify mood patterns. Emojis, graphic symbols representing emotions and concepts, are widely used in computer-mediated communication. Unlike previous studies that consider emojis as direct labels for emotion or sentiment, this work uses a pre-trained large language model which integrates both text and emojis to develop a mood classification model. Our contributions are three-fold. First, we annotate 10,000 Thai tweets with mood to train the models and release the dataset to the public. Second, we show that emojis contribute to determining mood to a lesser extent than text, far from mapping directly to mood. Third, through the application of the trained model, we observe the correlation of moods during the Thai political turmoil of 2019-2020 on Thai Twitter and find a significant correlation. These moods closely reflect the news events and reveal one side of Thai public opinion during the turmoil.

Multi-scale analysis of the community structure of the Twitter discourse around the Italian general elections of September 2022

We perform a multi-scale analysis of the geometric structure of the network of X (Twitter at the time of data collection) interactions surrounding the Italian snap general elections of September 25th 2022. We identify within it the communities related to the major Italian political parties and after it we analyse both the large-scale structure of interactions between different parties, showing that it resembles the coalitions formed in the run-up to the elections and the internal structure of each community. We observe that some parties have a very centralised communication with the major leaders clearly occupying the central role, while others have a more horizontal communication strategy, with many accounts playing an important role. We observe that this can be characterized by checking whether the network in the community has a strongly connected giant component or not.

AI approach on identifying change in public sentiment for major events: Dubai Expo 2020

Existing research in identifying changes in public sentiment for major events faces limitations in capturing the intricacies of temporal changes, especially with large-scale data and diverse linguistic nuances. This study addresses this problem, with a particular focus on the globally acclaimed Dubai Expo 2020. The methodology employed in this research introduces a groundbreaking approach by leveraging advanced data engineering techniques on a massive corpus of 118,025 Tweets obtained from diverse users across 60 languages, covering the period from April 2021 to March 2023. The study pioneers the application of artificial intelligence (AI), natural language processing (NLP), and Large Language Models (LLMs) for sentiment analysis and topic modeling on Twitter discourse. Through the meticulous data engineering process, including language detection, dynamic translation, and sentiment analysis, the research identifies subtle yet statistically significant changes in public sentiment, as evidenced by ANOVA testing (p=0.018 in average positive sentiment, p=0.004 in average neutral sentiment, and p=0.005 in average negative sentiments). Additionally, the study innovatively extracts and analyzes support-related Tweets, revealing distinct phases in temporal domains (pre-Expo, Expo, Post-Expo1, and Post-Expo2) and yielding 11,116 support-related tweets. The application of NLP techniques further uncovers 19 topics from UAE-related Tweets, providing a comprehensive understanding of the dynamic landscape of public sentiment over a two-year period. This research contributes significantly to the field by offering a novel and comprehensive framework for analyzing public sentiment, particularly in the context of major events, and sheds light on its broader implications for event management and public perception analysis.

Impoliteness in Twitter Discourse: a Case Study of Replies to Donald Trump and Greta Thunberg

Twitter (X) is a popular social media platform that allows users to express their opinions and interact on various topics, including politics. However, Twitter can provide a space for impolite and aggressive language use, especially when the issues are controversial or polarizing. This study analyzes the replies to two controversial and similar tweets, namely Donald Trump’s tweet to Greta Thunberg and Greta Thunberg’s tweet to Donald Trump. Ninety-seven tweets that impolitely took issue with the original tweets were collected and coded for their moral order themes and pragmatic functions. Culpeper’s (2011) impoliteness framework was consulted as a threshold to include or exclude reply tweets in the data analysis. The results show that the replies invoked moral order expectations in three overarching categories in the responses to both parties: age-appropriate behavior, respect and manners, and concern for the common good. As far as the pragmatic functions were concerned, criticism of personal characteristics, criticism of supporters, criticism of relatives (to Trump only), praise of the opposing party, directing, mockery, and ideology denial (to Thunberg only) were performed. The study discusses how users took offense through language in a highly polarized political context.

Exploring food poverty experiences in the German Twitter-Sphere

BackgroundThis study investigates the subjective perceptions of food poverty in Germany by analysing Twitter discourse using the German-language hashtag #IchBinArmutsbetroffen (#IamPovertyAffected) and examines the extent to which various dimensions of a multidimensional theoretical model of food poverty are represented in the discourse.MethodsEmploying a combination of computational social science and qualitative social research methods, the research identifies, and analyses tweets related to nutrition by applying a hierarchical dictionary search and qualitative content analysis. By examining the narratives and statements of individuals affected by food poverty, the study also investigates the interplay among different subdimensions of this phenomenon.ResultsThe analysis of 1,112 tweets revealed that 57.96% focused on the material dimension and 42.04% on the social dimension of food poverty, suggesting a relatively balanced emphasis on material and social aspects of food poverty in the narratives of those affected. The findings reveal that tweets on material food poverty underscore economic challenges and resource scarcity for food. Social food poverty tweets demonstrate widespread deprivation in social participation, leading to isolation, exclusion, and social network loss. Overall, the results elucidate intricate interconnections among subdimensions and multidimensional manifestations of food poverty.ConclusionsThis study contributes methodologically by presenting an approach for extracting food-related textual social media data and empirically by providing novel insights into the perceptions and multifaceted manifestations of food poverty in Germany. The results can aid in a better understanding of the phenomenon of food poverty as it currently manifests in Germany, and in developing targeted social, health-promoting, and political measures that address more effectively the empirically evident multidimensionality of the phenomenon.

“The ChatGPT bot is causing panic now – but it’ll soon be as mundane a tool as Excel”: analysing topics, sentiment and emotions relating to ChatGPT on Twitter

AbstractChatGPT, a sophisticated chatbot system by OpenAI, gained significant attention and adoption in 2022 and 2023. By generating human-like conversations, it attracted over 100 million monthly users; however, there are concerns about the social impact of ChatGPT, including panic, misinformation and ethics. Twitter has become a platform for expressing views on ChatGPT and popular NLP approaches like topic modelling, sentiment analysis and emotion detection are commonly used to study public discourses on Twitter. While these approaches have limitations, an analytical process of existing best practices captures the evolving nature of these views. Previous studies have examined early reactions and topics associated with ChatGPT on Twitter but have not fully explored the combination of topics, sentiment and emotions, nor have they explicitly followed existing best practices. This study provides an overview of the views expressed on Twitter about ChatGPT by analysing 88,058 tweets from November 2022 to March 2023 to see if panic and concern were replicated in Twitter discourses. The topics covered human-like text generation, chatbot development, writing assistance, data training, efficiency, impact on business and cryptocurrency. Overall, the sentiment was predominantly positive, indicating that concerns surrounding ChatGPT were not widely replicated. However, sentiment fluctuated, with a decline observed around the launch of ChatGPT Plus. The discourse saw consistent patterns of trust and fear, with trust maintaining a steady presence until a decline potentially influenced by concerns about biases and misinformation. We discuss how our findings build upon existing research regarding ChatGPT by providing trajectories of topics, sentiment and emotions.

She Speaks for Millions: The Emergence of Female Diplomatic Voices in the Russo-Ukrainian War

This research critically investigates the public diplomacy strategies deployed by a cohort of influential female European leaders on Twitter during the Russo-Ukrainian War of 2022-2023. The study comprises eight leaders - Kallas (Estonia), Marin (Finland), von der Leyen (President of the European Commission), Metsola (President of the European Parliament), Sandu (Moldova), Simonyte (Lithuania), Zourabichvili (Georgia), and Meloni (Italy) - representing millions of constituents. By mirroring the analytical attention given to Ukraine's President, Volodymyr Zelenskyy, this study scrutinizes the distinct approaches and differences in emotional, cognitive, and structural language use between these influential female figures and President Zelenskyy in their respective Twitter discourse during the crisis. By employing the Linguistic Inquiry and Word Count (LIWC)-22 dictionary, this research intends to uncover unique patterns and nuances in the language use of these leaders, thereby offering fresh insights into the gendered communication and diplomacy employed by the female cohort during conflicts. Keywords: Public diplomacy, Female leadership, Russo-Ukrainian War, Twitter communications, Linguistic Inquiry and Word Count (LIWC), Diplomacy, gendered communication

Language, identity, and resistance to English hegemony: unpacking language ideologies in Twitter discourses on Twi usage among the ‘Kumasiano Guys’ in Ghana

Language, identity, and resistance to English hegemony: unpacking language ideologies in Twitter discourses on Twi usage among the ‘Kumasiano Guys’ in Ghana

“Radicals” and “Racists”: Morality and Identity in U.S. Elite Political Communication

This study examines how elite political and media actors strategically leverage moral claims for partisan ends, transforming political identities, issues, and campaigns into zero-sum moral contests against their opposition. Here, I develop a framework for and approach to the study of morality as a strategic and identity-based tool in political communication, in the process developing a way of studying powerful and pervasive forms of political discourse often overlooked by scholarship. I show how partisan actors have identity-based motivations for employing particular forms of moral political communication, including religious, social, and civic morality. I then apply this framework to the case of the U.S. 2020 election, conducting context-sensitive computational and qualitative content analyses of elite political communication across political talk shows, op-eds, and campaign Twitter discourse. Results reveal the pervasive nature of moral political communication in these spaces. This work shows how, as U.S. political parties increasingly represent divergent and less cross-cutting groups of people, elite actors draw upon moral claims to attract and perform for particular ideological, religious, racial, and ethnic identity coalitions—often drawing from the same moral vocabulary to articulate opposing visions of democracy and civic life.

Narrative Characteristics in Refugee Discourse: An Analysis of American Public Opinion on the Afghan Refugee Crisis After the Taliban Takeover

The United States (U.S.) military withdrawal from Afghanistan in August 2021 was met with turmoil as the Taliban regained control of most of the country, including Kabul. These events have affected many and were widely discussed on social media, especially in the U.S. In this work, we focus on Twitter discourse regarding these events, especially potential opinion shifts over time and the effect social media posts by established U.S. legislators might have had on online public reception. To this end, we investigate two datasets on the war in Afghanistan, consisting of Twitter posts by self-identified U.S. accounts and conversation threads initiated by U.S. politicians. We find that Twitter users' discussions revolve around the Kabul airport event, President Biden's handling of the situation, and people affected by the U.S. withdrawal. Microframe analysis indicates that discourse centers the humanitarianism underlying these occurrences and politically leans liberal, focusing on care and fairness. Lastly, network analysis shows that Republicans are far more active on Twitter compared to Democrats and there is more positive sentiment than negative in their conversations.

Sentiment Analysis of Twitter Discourse on the 2023 Nigerian General Elections

Sentiment analysis entails discerning whether text conveys positive, neutral, or negative sentiments to ascertain the mood of the public concerning a given entity. This method relies on natural language processing, computational linguistics, and text analysis to identify, extract, and methodically analyze affective and subjective data. The 2023 Nigerian presidential election holds immense significance for the nation, determining its leadership for the subsequent four years. Consequently, comprehending public sentiment regarding the electoral process becomes paramount. This study sought to gauge public sentiment concerning the 2023 Nigerian General Elections by analyzing tweets related to candidates and their political parties. Leveraging three machine learning (ML) techniques—SVM, RF, and XGBoost—we aimed to categorize tweets as negative, positive, or neutral. Our dataset comprised a substantial volume of tweets, meticulously pre-processed to eliminate irrelevant content and noise. Results showcased the outstanding performance of RF and XGBoost in tweets classification and sentiment identification about the electoral process with the highest accuracy (93%) and precision (96%), occurring on neutral opinions. These results findings offer crucial insights into public opinion regarding candidates, their political parties, and the electoral procedure, benefiting researchers, political analysts and decision-makers alike. It suggests that 43% of the electorate expressed neutral sentiments about the elections, while 33% expressed positive sentiments, such as optimism about the electoral process, support for specific candidates, satisfaction with the results of the election, or excitement for taking part in democracy. Meanwhile, 24% of the electorate expressed negative sentiments, such as dissatisfaction with political candidates, criticism of the electoral processes, worries about fairness, or skepticism about the outcome. This research underscores the significance of sentiment analysis in comprehending public opinion and its potential contributions to political discourse.

Breaking Agenda Setting Boundaries: A Multi-Dimensional Approach to Understanding Salience of Gun Control in the Polarized Public Sphere

ABSTRACT We reexamine agenda setting by analyzing the salience of gun control within diverse U.S. audience groups. Utilizing data spanning from 2015 to 2022, we investigate the impact of traditional media, partisan media coverage, discourse on Twitter (now X), real-world gun-related events, and Google Trends search behavior on the perceived importance of gun control. Our findings indicate that while traditional media and Twitter discourse do not significantly sway the salience of gun control, partisan media coverage and specific information-seeking search behaviors do. Notably, media opposing an audience’s political ideology and searches for gun-related information are influential. The effect of real-world shooting events on issue salience is complex, with shootings influencing liberals, but with conservatives showing an initial decrease in perceived importance. Our approach explains issue salience for all ideological groups quite well and offers the most comprehensive understanding of the interplay between personal experiences, search behaviors, and a polarized media environment in shaping public salience on gun control to date.

Political Discourse on Twitter: The Case of Election Fraud in South Korea

The fake news that circulated on social media in 2020 and 2022 affected the voters of the South Korean general and presidential elections, respectively. The political controversy, centered on the election fraud that occurred in both the elections, received significant attention from the society. This study emphasizes the Twitter discourse and compares the formation and distribution of election fraud. We conduct semantic social network analysis and structural topic modeling (STM) to represent topics and relationships among the emerging themes using Twitter texts related to both elections. Results demonstrate that discourses on the same political issue exhibited unique contents and structures, as information is formed and distributed differently depending on the type of election in South Korea. Furthermore, this study illustrates the process and analysis of large-scale text data collected from Twitter. It also includes new methods, such as political ideology, for considering an analytical dimension.

Semantic Networks of Election Fraud: Comparing the Twitter Discourses of the U.S. and Korean Presidential Elections

Traditional news outlets, such as newspapers and television, are no longer major sources of news. These media channels have been replaced by social platforms, which have increased in value as information distributors. This change in communication is an underlying reason for the election fraud controversies that occurred in the United States and South Korea, which hold high standards of democracy, during similar periods. This study investigates a model for sharing political disputes over social networks, especially Twitter, and illustrates the influence of political polarization. This study examines Twitter content around the presidential elections in the United States and South Korea in 2020 and 2022, respectively. It applies semantic network analysis and structural topic modeling to describe and compare the dynamics of online discourse on the issue of election fraud. The results show that online spaces such as Twitter serve as public spheres for discussion among active political participants. Social networks are key settings for forming and spreading election fraud controversies in the United States and South Korea, with differences in content. In addition, the study applies large-volume text data and new analytical methods such as the structural topic model to examine the in-depth relationships among political issues in cyberspace.