Youssef Al Hariri

We present TwiXplorer, an interactive tool to explore and understand static Twitter (X) datasets. While obtaining new data from X has become more challenging for academics, there are still rich datasets available that have largely been untapped, for example, from the "The Twitter Stream Grab” project at the Internet Archive. Accessing and exploring this historical Twitter data is crucial for researchers interested in studying the history of social media. Our system is more advanced and easy to use than existing options and demonstrates how AI can help and be integrated into a process to make sense of large datasets. The tool is accessed through a web-based dashboard and designed with interaction in mind: the analyst can iteratively explore the data instead of being presented with static reports. We make the tool fully open source.

There is a long history of investment in solidaristic stories in the face of social upheaval, threat or conflict, and this was especially evident in relation to Covid-19. This article examines the way that one such narrative – the idea of kindness – was drawn on by Twitter users during the pandemic. Setting it in the context of a wider cultural preoccupation with kindness that both predates and continues beyond the pandemic, we draw on empirical research to develop the concept of the ‘good story’: a compelling collective narrative about goodness that carries with it anxieties about authenticity and dupery. We argue that ambivalences are inherent in the good story but are especially prominent in an age of social upheaval, polarisation, digital interaction and uncertainty. Such ambivalences cannot be wished away but need to be worked with, theoretically and practically. The good story is one tool for beginning to do this.

The recent growth in Middle Eastern stock markets has intensified the demand for specialized financial Arabic NLP models to serve this sector. This article presents the participation of Team SMASH of The University of Edinburgh in the Multi-dialect Intent Detection task (Subtask 1) of the Arabic Financial NLP (AraFinNLP) Shared Task 2024. The dataset used in the shared task is the ArBanking77 (Jarrar et al., 2023). We tackled this task as a classification problem and utilized several BERT and BART-based models to classify the queries efficiently. Our solution is based on implementing a two-step hierarchical classification model based on MARBERTv2. We fine-tuned the model by using the original queries. Our team, SMASH, was ranked 9th with a macro F1 score of 0.7866, indicating areas for further refinement and potential enhancement of the model’s performance.

This paper presents our submission for the Stance Detection in Arabic Language (StanceEval) 2024 shared task conducted by Team SMASH of the University of Edinburgh. We evaluated the performance of various BERT-based and large language models (LLMs). MARBERT demonstrates superior performance among the BERT-based models, achieving F1 and macro-F1 scores of 0.570 and 0.770, respectively. In contrast, Command R model outperforms all models with the highest overall F1 score of 0.661 and macro F1 score of 0.820.

Most previous research on online discussions of atheism has focused on atheism within a Christian context. In contrast, discussions about atheism in the Arab world and from Islamic background are relatively poorly studied. An added complication is that open atheism is against the law in some Arab countries, which may further restrict atheist activity on social media. In this work, we explore atheistic discussion in the Arab Twittersphere. We identify four relevant categories of Twitter users according to the content they post: atheistic, theistic, tanweeri (religious renewal), and other. We characterise the typical content posted by these four sets of users and their social networks, paying particular attention to the topics discussed and the interaction among them. Our findings have implication for the study of religious and spiritual discourse on social media and provide a better cross-cultural understanding of relevant aspects.

In this study, we investigate the extent of polarisation among theist versus atheist groups on Arab Twitter and their networks. We find four main self-identified groups of Arab users that can be distinguished by different attitudes to religion. In addition to Atheists and Theists, there are Rationalists, who promote rational thinking regardless of religious affiliation, and Tanweeri, who promote religious reforms. Through a keyword search of Twitter account handles and biographies, we identified 2,673 active, public Twitter accounts that clearly state whether they are Atheists, Theists, Tanweeri or Rationalists and analysed the interactions among themselves and the accounts that are followed, retweeted, or mentioned the most in their networks. Depending on the network analysed, we found between four and seven sub-communities that highlight the rich socio-cultural context in which discussions of religion, non-religion, and religious reform unfold. While there was clear online polarisation between atheists and theists, Rationalist and Tanweeri accounts are spread among the two polarised sides, acting as natural bridges. We also found a clear separation between Arab atheists who engage with Arab accounts promoting atheism and those who primarily engage with Western accounts promoting atheism. We discuss implications for the study of religious debate and religious polarisation on social media.

Purpose: With the recent conclusion of the United Nations Conference of the Parties (COP) 28 in the United Arab Emirates, this study aims to investigate the tweeting behaviour of firms surrounding COP events. The authors analyse the environmental, social and governance (ESG) tweets from the COP 26 and COP 27 events, aiming to deepen the understanding of the complex relationships between social media communication, industry characteristics and financial performance. This timely analysis is critical for assessing how the latest global discussions on climate change are influencing corporate communication strategies on sustainability, offering fresh insights into the evolving dynamics of ESG engagement in the context of these pivotal international meetings. Design/methodology/approach: In this study, the authors embrace a grounded theory approach to gain insights into the ESG and sustainability initiatives presented by companies on social media, with an intensified focus on climate change discourse. Leveraging advanced social media analytics, this study expands its scope by conducting a thorough examination of ESG-related tweets from Standard and Poor’s (S&P) 500 companies. In addition, the authors explore the relationships between such communication efforts and financial performance, applying an advanced cumulative abnormal returns (CARs) model. This methodological enhancement enables a more sophisticated understanding of how ESG communication on Twitter correlates with, and potentially influences, a firm’s market valuation and financial health, offering invaluable insights into the strategic importance of digital sustainability discourse. Findings: The research findings introduce four novel distinct groups – Unengaged, Catalysts, Cautious and Shapers – based on firms’ proactive or reactive sustainability communication patterns. The results explore the potential impact of COP event locations on tweeting behaviour, proposing that conferences held in different regions, such as Asia versus Europe, may elicit varied reactions from S&P 500 firms. Despite no significant inter-industry differences in tweeting habits, the authors discover a significant link between firms’ financial metrics, specifically CARs, and their categorised communication styles. The results challenge the simplistic view that higher social media engagement leads to positive financial outcomes, suggesting instead that lower financial performance may drive firms to adopt more extreme communication patterns, possibly as a strategic move to enhance corporate legitimacy.