Björn Ross

University of Edinburgh | UoE · School of Informatics

Since an ever-increasing part of the population makes use of social media in their day-today lives, social media data is being analysed in many different disciplines. The social media analytics process involves four distinct steps, data discovery, collection, preparation, and analysis. While there is a great deal of literature on the challenges and...

Information systems such as social media strongly influence public opinion formation. Additionally, communication on the internet is shaped by individuals and organisations with various aims. This environment has given rise to phenomena such as manipulated content, fake news, and social bots. To examine the influence of manipulated opinions, we dra...

Social media have become forums of discussions on political and societal debates in which individual users may forward information or influence others. While prior studies either employed network analyses or surveys to identify opinion leaders and their characteristics, the present investigation combines these two approaches to address the relation...

To proactively offer social media users a safe online experience, there is a need for systems that can detect harmful posts and promptly alert platform moderators. In order to guarantee the enforcement of a consistent policy, moderators are provided with detailed guidelines. In contrast, most state-of-the-art models learn what abuse is from labeled...

In this paper, we introduce and discuss the pervasive issue of bias in the large language models that are currently at the core of mainstream approaches to Natural Language Processing (NLP). We first introduce data selection bias, that is, the bias caused by the choice of texts that make up a training corpus. Then, we survey the different types of...

Content moderators play a key role in keeping the conversation on social media healthy. While the high volume of content they need to judge represents a bottleneck to the moderation pipeline, no studies have explored how models could support them to make faster decisions. There is, by now, a vast body of research into detecting hate speech, sometim...

Counterspeech has been proposed as a solution to the proliferation of online hate. Research has shown that natural language processing (NLP) approaches could generate such counterspeech automatically, but there are competing ideas for how NLP models might be used for this task and a variety of evaluation metrics whose relationship to one another is...

Introduction For most patients, cancer therapy with radiation is a new experience coming with many unknown challenges. This can be stressful, particularly for children and adolescents. With the aim of reducing this stress and anxiety, a virtual-reality (VR) game, which can be used by patients prior to treatment, was developed and evaluated in a pro...

Individuals engage in arguments on an everyday basis as they seek to obtain information about current affairs and engage with social media. While fact-checkers are available to help dispel misinformation, it is almost impossible for users to verify every single claim they encounter. This means that oftentimes, it is left to the user to decide wheth...

Cutting-edge image generation has been praised for producing high-quality images, suggesting a ubiquitous future in a variety of applications. However, initial studies have pointed to the potential for harm due to predictive bias, reflecting and potentially reinforcing cultural stereotypes. In this work, we are the first to investigate how multimod...

Sentiment analysis (SA) systems are widely deployed in many of the world's languages, and there is well-documented evidence of demographic bias in these systems. In languages beyond English, scarcer training data is often supplemented with transfer learning using pre-trained models, including multilingual models trained on other languages. In some...

Automated sentiment analysis can help efficiently detect trends in patients’ moods, consumer preferences, political attitudes and more. Unfortunately, like many natural language processing techniques, sentiment analysis can show bias against marginalised groups. We illustrate this point by showing how six popular sentiment analysis tools respond to...

The Stereotype Content model (SCM) states that we tend to perceive minority groups as cold, incompetent or both. In this paper we adapt existing work to demonstrate that the Stereotype Content model holds for contextualised word embeddings, then use these results to evaluate a fine-tuning process designed to drive a language model away from stereot...

The ArgMining 2022 Shared Task is concerned with predicting the validity and novelty of an inference for a given premise and conclusion pair. We propose two feed-forward network based models (KEViN 1 and KEViN 2), which combine features generated from several pre-trained transformers and the WikiData knowledge graph. The transformers are used to pr...

To proactively offer social media users a safe online experience, there is a need for systems that can detect harmful posts and promptly alert platform moderators. In order to guarantee the enforcement of a consistent policy, moderators are provided with detailed guidelines. In contrast, most state-of-the-art models learn what abuse is from labelle...

Social media plays a major role in public communication in many countries. Therefore, it has a large impact on societies and their cohesion. This thematic issue explores the impact social media has on social cohesion on a local or national level. The nine articles in this issue focus on both the potential of social media usage to foster social cohe...

Widespread mis- and disinformation during the COVID-19 social media “infodemic” challenge the effective response of Emergency Management Agencies (EMAs). Conversational Agents (CAs) have the potential to amplify and distribute trustworthy information from EMAs to the general public in times of uncertainty. However, the structure and responsibilitie...

In the last decade, Social Media platforms such as Twitter have gained importance in the various marketing strategies of companies. This work aims to examine the presence of influential content on a textual level, by investigating characteristics of tweets in the context of social impact theory, and its dimension immediacy. To this end, we analysed...

In many instances, misinformation among the population manifests itself in the form of conspiracy theories. Services such as YouTube, which allow the publication of audiovisual material in juxtaposition with peer responses (e.g., comments), function as ideal forums to disseminate such conspiracy theories and reach a massive audience. While previous...

Social media has become important in shaping the public discourse on controversial topics. Many businesses therefore monitor different social media channels and try to react adequately to a potentially harmful opinion climate. Still, little is known about how opinions form in an increasingly connected world. The spiral of silence theory provides a...

Artificial intelligence (AI) has moved beyond the planning phase in many organisations and it is often accompanied by uncertainties and fears of job loss among employees. It is crucial to manage employees' attitudes towards the deployment of an AI-based technology effectively and counteract possible resistance behaviour. We present lessons learned...

During the coronavirus disease 2019 (COVID-19) pandemic, the video-sharing platform YouTube has been serving as an essential instrument to widely distribute news related to the global public health crisis and to allow users to discuss the news with each other in the comment sections. Along with these enhanced opportunities of technology-based commu...

In this work we introduce Adversarial Attacks against Abuse (AAA), a new evaluation strategy and associated metric that better captures a model's performance on certain classes of hard-to-classify microposts, and for example penalises systems which are biased on low-level lexical features. It does so by adversarially modifying the model developer's...

Computational social science uses computational and statistical methods in order to evaluate social interaction. The public availability of data sets is thus a necessary precondition for reliable and replicable research. These data allow researchers to benchmark the computational methods they develop, test the generalizability of their findings, an...

Within the anamnesis, medical information is frequently withheld, incomplete, or incorrect, potentially causing negative consequences for the patient. The use of conversational agents (CAs), computer-based systems using natural language to interact with humans, may mitigate this problem. The present research examines whether CAs differ from physici...

Organizations are collecting large amounts of data that are generated by internet-connected devices in people’s homes. This raises questions regarding online privacy and data security. A common concern is that online advertisements are personalized based on conversations that have unknowingly been recorded by people’s smart devices. The present art...

Organizations introduce virtual assistants (VAs) to support employees with work-related tasks. VAs can increase the success of teamwork and thus become an integral part of the daily work life. However, the effect of VAs on virtual teams remains unclear. While social identity theory describes the identification of employees with team members and the...

In the last decade, Social Media platforms such as Twitter have gained importance in the various marketing strategies of companies. This work aims to examine the presence of influential content on a textual level, by investigating characteristics of tweets in the context of social impact theory, and its dimension immediacy. To this end, we analysed...

Information systems (IS) have been introduced in enterprises for decades to generate business value. Historically systems that are deeply integrated into business processes and not replaced remain vital assets, and thus become legacy IS (LISs). To secure the future success, enterprises invest in innovative technologies such as artificial intelligen...

Research data management (RDM) is an important prerequisite for a substantial and sustainable contribution to knowledge. There is a pressing need to examine why researchers hesitate to store, annotate, share and manage their research data. To model underlying psychological factors influencing researchers’ refusal to conduct RDM, the social exchange...

Academic research generates increasing amounts of data that needs to be shared between collaborators, made publicly accessible and/or archived for the long term, all while respecting applicable regulations on topics such as data protection. Good research data management (RDM) is challenging, and despite the growing number of available technical sol...

As false information may spread rapidly on social media, a profound understanding of how it can be debunked is required. This study offers empirical insights into the development of rumors after they are debunked, the various user groups who are involved in the process, and their network structures. As crisis situations are highly sensitive to the...

When attempting to solve a problem, humans call upon cognitive resources. These resources are limited, and the degree of their utilisation is described as cognitive load. While the number of parameters to be taken into account and to be processed by modern-day knowledge workers increases, their cognitive resources do not. Research shows that too hi...

In the context of events that involve public voting, such as televised competitions or elections, it has increasingly been recognized that communication data from social media is related to the outcome. Existing studies mainly analyse the number of messages and their sentiment, yet the role of different data collection periods has not been examined...

In recent years, mainstream E-commerce platforms have changed the way consumer goods are merchandized online. While such platforms increasingly discover social elements to drive sales, social media start implementing E-commerce features themselves. This emerging intersection also provides space for bot activity in a Social Commerce (SC) context, wh...

When addressing public concerns such as the existence of politically like-minded communication spaces in social media, analyses of complex political discourses are met with increasing methodological challenges to process communication data properly. To address the extent of political like-mindedness in online communication, we argue that it is nece...

Information systems (IS) are widely used in organisations to improve business performance. The steady progression in improving technologies like artificial intelligence (AI) and the need of securing future success of organisations lead to new requirements for IS. This research in progress firstly introduces the term AI-based services (AIBS) describ...

Information systems (IS) are widely used in organisations to improve business performance. The steady progression in improving technologies like artificial intelligence (AI) and the need of securing future success of organisations lead to new requirements for IS. This research in progress firstly introduces the term AI-based services (AIBS) describ...

When addressing public concerns such as the existence of politically like-minded communication spaces in social media, analyses of complex political discourses are met with increasing methodological challenges to process communication data properly. To address the extent of political like-mindedness in online communication, we argue that it is nece...

Zusammenfassung Im Kontext des IT-Service-Managements stellt ein wesentlicher Faktor zur möglichst effizienten und effektiven Entstörung gemeldeter Probleme das Incident Management dar. Aufgenommene Störungen werden dabei identifiziert, protokolliert und kategorisiert, so dass nachgelagerte Strukturen, wie Second- und Third-Level-Support, Beeinträc...

Like many other industries, the media industry has been profoundly affected by social media. The public discuss the news on services such as Twitter, and some celebrity tweets are picked up by journalists and become news stories themselves. Information systems research into information diffusion has largely neglected these cross-platform diffusion...

Warning messages are being discussed as a possible mechanism to contain the circulation of false information on social media. Their effectiveness for this purpose, however, is unclear. This article describes a survey experiment carried out to test two designs of warning messages: a simple one identical to the one used by Facebook, and a more comple...

Learning and understanding what happened before, during, and after a crisis is extremely important for the improvement of the response process. For this purpose, social media has become an important communication medium used by both the affected persons and the emergency management services (EMSs). However, in different crises, different informatio...

When Donald Trump won the Republican nomination and subsequently beat Hillary Clinton in the presidential elections, his success came as a surprise to most observers. This research contributes to understanding the dynamics of this unusual campaign, in which social media played a prominent role. We collected 6,099 tweets by both nominees during the...

Sharing platforms for creative content are often closely connected to general purpose social media platforms like Twitter. This also means that coordinated and automated mechanisms for promoting such content are likely to span both sites: spammers and bots operate across both plat-forms. This work-in-progress paper presents first results from an ef...

Wikipedia is an important source of information in today's world. Yet, the lack of gender diversity in its community has been shown to affect the topics covered. Each Wikipedia article has a talk page that volunteer editors use to discuss proposed changes. Research on the gender bias has focused on article contribution and topic coverage, but not t...

Wikipedia is an important source of information in today's world. Yet, the lack of gender diversity in its community has been shown to affect the topics covered. Each Wikipedia article has a talk page that volunteer editors use to discuss proposed changes. Research on the gender bias has focused on article contribution and topic coverage, but not t...

Recently, automated communication on social media has seen increased attention. Social bots, social media accounts controlled by algorithms that mimic human behaviour, have been found to attempt to influence users in several political contexts. However, their use in a commercial context, e.g. to boost sales of a product by aggressively promoting it...

During a crisis, authorities need to effectively disseminate information. We address the problem of deciding how crisis-related information should be published on Facebook to reach as many people as possible. We examine three recent terrorist attacks in Berlin, London and Stockholm. Our specific focus lies with official Facebook pages by municipali...

During a crisis, authorities need to effectively disseminate information. We address the problem of deciding how crisis-related information should be published on Facebook to reach as many people as possible. We examine three recent terrorist attacks in Berlin, London and Stockholm. Our specific focus lies with official Facebook pages by municipali...

So-called 'social bots' have garnered a lot of attention lately. Previous research showed that they attempted to influence political events such as the Brexit referendum and the US presidential elections. It remains, however, somewhat unclear what exactly can be understood by the term 'social bot'. This paper addresses the need to better understand...

The last few years have seen more and more employees using their personal mobile devices for work-related tasks. This phenomenon is part of a broader trend known as IT consumerization. Enterprises and employees have recognized that they might profit from these developments and implemented “Bring Your Own Device” (BYOD) policies, but they also have...

Wikipedia offers researchers unique insights into the collaboration and communication patterns of a large self-regulating community of editors. The main medium of direct communication between editors of an article is the article's talk page. However, a talk page file is unstructured and therefore difficult to analyse automatically. A few parsers ex...

Some users of social media are spreading racist, sexist, and otherwise hateful content. For the purpose of training a hate speech detection system, the reliability of the annotations is crucial, but there is no universally agreed-upon definition. We collected potentially hateful messages and asked two groups of internet users to determine whether t...