arXiv subjects

Björn Ross

Publications and source records attributed to Björn Ross.

At least 19 recordsLinked to original sources

arXiv2026

Gendered Communication Patterns of Political Elites on Truth Social

The influence of gender on online political communication remains contested, with existing scholarship providing mixed evidence as to whether gender shapes political messaging in digital environments. However, this debate has largely centred on mainstream platforms such as X (formerly Twitter), leaving the dynamics of alt-tech social media underexamined. This paper addresses this gap by analysing gendered patterns of political communication on Truth Social, a hyper-partisan platform that functions as a hub for the most committed followers of the American far right, a community closely associated with hegemonic masculine norms. To address this gap, we present the first large-scale analysis of political elite communication on Truth Social, using a novel dataset of 107k posts from 129 U.S. political figures. We examine the extent to which gender influences rhetorical style, topic framing, and audience engagement. We find that many gendered communication patterns documented on mainstream platforms persist on Truth Social. In particular, women political elites tend to express more joy and less anger than men and receive significantly higher levels of audience engagement. At the same time, more nuanced differences emerge. Although men and women political elites discuss largely similar conservative themes, they differ in how these issues are framed and in the rhetorical strategies employed. Notably, posts associated with women political elites contain higher levels of fear-based rhetoric, potentially suggesting selective adaptation in communicative style to navigate gender norms on the platform. These findings suggest that on Truth Social, an alt-tech platform with distinct ideological characteristics, mainstream gendered constraints persist, but are expressed through platform-specific communicative patterns shaped by its partisan orientation and sociotechnical environment.

cs.SI↗

arXiv2025

Evaluating Long-Term Memory for Long-Context Question Answering

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types of memory are most effective for long-context conversational tasks. We present a systematic evaluation of memory-augmented methods on long-context dialogues annotated for question-answering tasks that require diverse reasoning strategies. We analyse full-context prompting, semantic memory through retrieval-augmented generation and agentic memory, episodic memory through in-context learning, and procedural memory through prompt optimization. Our findings show that memory-augmented approaches reduce token usage by over 90\% while maintaining competitive accuracy. Memory architecture complexity should scale with model capability, with foundation models benefitting most from RAG, and stronger instruction-tuned models gaining from episodic learning through reflections and more complex agentic semantic memory. In particular, episodic memory can help LLMs recognise the limits of their own knowledge.

cs.CL↗

arXiv2025

Fabricating Holiness: Characterizing Religious Misinformation Circulators on Arabic Social Media

Misinformation is a growing concern in a decade involving critical global events. While social media regulation is mainly dedicated towards the detection and prevention of fake news and political misinformation, there is limited research about religious misinformation which has only been addressed through qualitative approaches. In this work, we study the spread of fabricated quotes (Hadith) that are claimed to belong to Prophet Muhammad (the prophet of Islam) as a case study demonstrating one of the most common religious misinformation forms on Arabic social media. We attempt through quantitative methods to understand the characteristics of social media users who interact with fabricated Hadith. We spotted users who frequently circulate fabricated Hadith and others who frequently debunk it to understand the main differences between the two groups. We used Logistic Regression to automatically predict their behaviors and analyzed its weights to gain insights about the characteristics and interests of each group. We find that both fabricated Hadith circulators and debunkers have generally a lot of ties to religious accounts. However, circulators are identified by many accounts that follow the Shia branch of Islam, Sunni Islamic public figures from the gulf countries, and many Sunni non-professional pages posting Islamic content. On the other hand, debunkers are identified by following academic Islamic scholars from multiple countries and by having more intellectual non-religious interests like charity, politics, and activism.

cs.SI↗

arXiv2025

SocioXplorer: An Interactive Tool for Topic and Network Analysis in Social Data

SocioXplorer is a powerful interactive tool that computational social science researchers can use to understand topics and networks in social data from Twitter (X) and YouTube. It integrates, among other things, artificial intelligence, natural language processing and social network analysis. It can be used with ``live" datasets that receive regular updates. SocioXplorer is an extension of a previous system called TwiXplorer, which was limited to the analysis of archival Twitter (X) data. SocioXplorer builds on this by adding the ability to analyse YouTube data, greater depth of analysis and batch data processing. We release it under the Apache 2 licence.

cs.SI↗

arXiv2025

Compositional Generalisation for Explainable Hate Speech Detection

Hate speech detection is key to online content moderation, but current models struggle to generalise beyond their training data. This has been linked to dataset biases and the use of sentence-level labels, which fail to teach models the underlying structure of hate speech. In this work, we show that even when models are trained with more fine-grained, span-level annotations (e.g., "artists" is labeled as target and "are parasites" as dehumanising comparison), they struggle to disentangle the meaning of these labels from the surrounding context. As a result, combinations of expressions that deviate from those seen during training remain particularly difficult for models to detect. We investigate whether training on a dataset where expressions occur with equal frequency across all contexts can improve generalisation. To this end, we create U-PLEAD, a dataset of ~364,000 synthetic posts, along with a novel compositional generalisation benchmark of ~8,000 manually validated posts. Training on a combination of U-PLEAD and real data improves compositional generalisation while achieving state-of-the-art performance on the human-sourced PLEAD.

cs.CL↗

arXiv2025

"Till I can get my satisfaction": Open Questions in the Public Desire to Punish AI

There are countless examples of how AI can cause harm, and increasing evidence that the public are willing to ascribe blame to the AI itself, regardless of how "illogical" this might seem. This raises the question of whether and how the public might expect AI to be punished for this harm. However, public expectations of the punishment of AI have been vastly underexplored. Understanding these expectations is vital, as the public may feel the lingering effect of harm unless their desire for punishment is satisfied. We synthesise research from psychology, human-computer and -robot interaction, philosophy and AI ethics, and law to highlight how our understanding of this issue is still lacking. We call for an interdisciplinary programme of research to establish how we can best satisfy victims of AI harm, for fear of creating a "satisfaction gap" where legal punishment of AI (or not) fails to meet public expectations.

cs.HC↗

arXiv2024

"The Prophet said so!": On Exploring Hadith Presence on Arabic Social Media

Hadith, the recorded words and actions of the prophet Muhammad, is a key source of the instructions and foundations of Islam, alongside the Quran. Interpreting individual hadiths and verifying their authenticity can be difficult, even controversial, and the subject has attracted the attention of many scholars who have established an entire science of Hadith criticism. Recent quantitative studies of hadiths focus on developing systems for automatic classification, authentication, and information retrieval that operate over existing hadith compilations. Qualitative studies on the other hand try to discuss different social and political issues from the perspective of hadiths, or they inspect how hadiths are used in specific contexts in official communications and press releases for argumentation and propaganda. However, there are no studies that attempt to understand the actual presence of hadiths among Muslims in their daily lives and interactions. In this study, we try to fill this gap by exploring the presence of hadiths on Twitter from January 2019 to January 2023. We highlight the challenges that quantitative methods should consider while processing texts that include hadiths and we provide a methodology for Islamic scholars to validate their hypotheses about hadiths on big data that better represent the position of the society and Hadith influence on it.

cs.SI↗

arXiv2024

The Only Way is Ethics: A Guide to Ethical Research with Large Language Models

There is a significant body of work looking at the ethical considerations of large language models (LLMs): critiquing tools to measure performance and harms; proposing toolkits to aid in ideation; discussing the risks to workers; considering legislation around privacy and security etc. As yet there is no work that integrates these resources into a single practical guide that focuses on LLMs; we attempt this ambitious goal. We introduce 'LLM Ethics Whitepaper', which we provide as an open and living resource for NLP practitioners, and those tasked with evaluating the ethical implications of others' work. Our goal is to translate ethics literature into concrete recommendations and provocations for thinking with clear first steps, aimed at computer scientists. 'LLM Ethics Whitepaper' distils a thorough literature review into clear Do's and Don'ts, which we present also in this paper. We likewise identify useful toolkits to support ethical work. We refer the interested reader to the full LLM Ethics Whitepaper, which provides a succinct discussion of ethical considerations at each stage in a project lifecycle, as well as citations for the hundreds of papers from which we drew our recommendations. The present paper can be thought of as a pocket guide to conducting ethical research with LLMs.

cs.CL↗

arXiv2024

Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models

This whitepaper offers an overview of the ethical considerations surrounding research into or with large language models (LLMs). As LLMs become more integrated into widely used applications, their societal impact increases, bringing important ethical questions to the forefront. With a growing body of work examining the ethical development, deployment, and use of LLMs, this whitepaper provides a comprehensive and practical guide to best practices, designed to help those in research and in industry to uphold the highest ethical standards in their work.

cs.CY↗

arXiv2024

Experiences of Censorship on TikTok Across Marginalised Identities

TikTok has seen exponential growth as a platform, fuelled by the success of its proprietary recommender algorithm which serves tailored content to every user - though not without controversy. Users complain of their content being unfairly suppressed by ''the algorithm'', particularly users with marginalised identities such as LGBTQ+ users. Together with content removal, this suppression acts to censor what is shared on the platform. Journalists have revealed biases in automatic censorship, as well as human moderation. We investigate experiences of censorship on TikTok, across users marginalised by their gender, LGBTQ+ identity, disability or ethnicity. We survey 627 UK-based TikTok users and find that marginalised users often feel they are subject to censorship for content that does not violate community guidelines. We highlight many avenues for future research into censorship on TikTok, with a focus on users' folk theories, which greatly shape their experiences of the platform.

cs.HC↗

arXiv2024

Explainability and Hate Speech: Structured Explanations Make Social Media Moderators Faster

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, sometimes explicitly motivated by a desire to help improve content moderation, but published research using real content moderators is scarce. In this work we investigate the effect of explanations on the speed of real-world moderators. Our experiments show that while generic explanations do not affect their speed and are often ignored, structured explanations lower moderators' decision making time by 7.4%.

cs.CL↗

arXiv2024

Detecting Statements in Text: A Domain-Agnostic Few-Shot Solution

Many tasks related to Computational Social Science and Web Content Analysis involve classifying pieces of text based on the claims they contain. State-of-the-art approaches usually involve fine-tuning models on large annotated datasets, which are costly to produce. In light of this, we propose and release a qualitative and versatile few-shot learning methodology as a common paradigm for any claim-based textual classification task. This methodology involves defining the classes as arbitrarily sophisticated taxonomies of claims, and using Natural Language Inference models to obtain the textual entailment between these and a corpus of interest. The performance of these models is then boosted by annotating a minimal sample of data points, dynamically sampled using the well-established statistical heuristic of Probabilistic Bisection. We illustrate this methodology in the context of three tasks: climate change contrarianism detection, topic/stance classification and depression-relates symptoms detection. This approach rivals traditional pre-train/fine-tune approaches while drastically reducing the need for data annotation.

cs.CL↗

arXiv2023

Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models

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 multimodal models handle diverse gender identities. Concretely, we conduct a thorough analysis in which we compare the output of three image generation models for prompts containing cisgender vs. non-cisgender identity terms. Our findings demonstrate that certain non-cisgender identities are consistently (mis)represented as less human, more stereotyped and more sexualised. We complement our experimental analysis with (a)~a survey among non-cisgender individuals and (b) a series of interviews, to establish which harms affected individuals anticipate, and how they would like to be represented. We find respondents are particularly concerned about misrepresentation, and the potential to drive harmful behaviours and beliefs. Simple heuristics to limit offensive content are widely rejected, and instead respondents call for community involvement, curated training data and the ability to customise. These improvements could pave the way for a future where change is led by the affected community, and technology is used to positively ``[portray] queerness in ways that we haven't even thought of'' rather than reproducing stale, offensive stereotypes.

cs.CL↗

arXiv2023

Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis

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 cases, even supervision data comes from other languages. Does cross-lingual transfer also import new biases? To answer this question, we use counterfactual evaluation to test whether gender or racial biases are imported when using cross-lingual transfer, compared to a monolingual transfer setting. Across five languages, we find that systems using cross-lingual transfer usually become more biased than their monolingual counterparts. We also find racial biases to be much more prevalent than gender biases. To spur further research on this topic, we release the sentiment models we used for this study, and the intermediate checkpoints throughout training, yielding 1,525 distinct models; we also release our evaluation code.

cs.CL↗

arXiv2022

A Robust Bias Mitigation Procedure Based on the Stereotype Content Model

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 stereotyped portrayals of minority groups. We find the SCM terms are better able to capture bias than demographic agnostic terms related to pleasantness. Further, we were able to reduce the presence of stereotypes in the model through a simple fine-tuning procedure that required minimal human and computer resources, without harming downstream performance. We present this work as a prototype of a debiasing procedure that aims to remove the need for a priori knowledge of the specifics of bias in the model.

cs.CL↗

arXiv2022

Explainable Abuse Detection as Intent Classification and Slot Filling

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 labelled examples and as a result base their predictions on spurious cues, such as the presence of group identifiers, which can be unreliable. In this work we introduce the concept of policy-aware abuse detection, abandoning the unrealistic expectation that systems can reliably learn which phenomena constitute abuse from inspecting the data alone. We propose a machine-friendly representation of the policy that moderators wish to enforce, by breaking it down into a collection of intents and slots. We collect and annotate a dataset of 3,535 English posts with such slots, and show how architectures for intent classification and slot filling can be used for abuse detection, while providing a rationale for model decisions.

cs.CL↗

arXiv2022

Towards a Better Understanding of Online Influence: Differences in Twitter CommunicationBetween Companies and Influencers

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 influential Twitter communication data during Black Friday 2018 with methods from social media analytics such as sentiment analysis and degree centrality. Results show significant differences in communication style between companies and influencers. Companies published longer textual content and created more tweets with a positive sentiment and more first-person pronouns than influencers. These findings shall serve as a basis for a future experimental study to examine the impact of text presence on consumer cognition and the willingness to purchase.

cs.SI↗

arXiv2019

Towards Successful Collaboration: Design Guidelines for AI-based Services enriching Information Systems in Organisations

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) describing AI as a component enriching IS aiming at collaborating with employees and assisting in the execution of work-related tasks. The study derives requirements from ten expert interviews to successful design AIBS following Design Science Research (DSR). For a successful deployment of AIBS in organisations the D&M IS Success Model will be considered to validated requirements within three major dimensions of quality: Information Quality, System Quality, and Service Quality. Amongst others, preliminary findings propose that AIBS must be preferably authentic. Further discussion and research on AIBS is forced, thus, providing first insights on the deployment of AIBS in organisations.

cs.AI↗