arXiv subjects

Emilio Ferrara

Publications and source records attributed to Emilio Ferrara.

At least 91 records · Page 5Linked to original sources

arXiv2024

Can Language Model Moderators Improve the Health of Online Discourse?

Conversational moderation of online communities is crucial to maintaining civility for a constructive environment, but it is challenging to scale and harmful to moderators. The inclusion of sophisticated natural language generation modules as a force multiplier to aid human moderators is a tantalizing prospect, but adequate evaluation approaches have so far been elusive. In this paper, we establish a systematic definition of conversational moderation effectiveness grounded on moderation literature and establish design criteria for conducting realistic yet safe evaluation. We then propose a comprehensive evaluation framework to assess models' moderation capabilities independently of human intervention. With our framework, we conduct the first known study of language models as conversational moderators, finding that appropriately prompted models that incorporate insights from social science can provide specific and fair feedback on toxic behavior but struggle to influence users to increase their levels of respect and cooperation.

cs.CL↗

arXiv2024

Hidden in Plain Sight: Exploring the Intersections of Mental Health, Eating Disorders, and Content Moderation on TikTok

Social media platforms actively moderate content glorifying harmful behaviors like eating disorders, which include anorexia and bulimia. However, users have adapted to evade moderation by using coded hashtags. Our study investigates the prevalence of moderation evaders on the popular social media platform TikTok and contrasts their use and emotional valence with mainstream hashtags. We notice that moderation evaders and mainstream hashtags appear together, indicating that vulnerable users might inadvertently encounter harmful content even when searching for mainstream terms. Additionally, through an analysis of emotional expressions in video descriptions and comments, we find that mainstream hashtags generally promote positive engagement, while moderation evaders evoke a wider range of emotions, including heightened negativity. These findings provide valuable insights for content creators, platform moderation efforts, and interventions aimed at cultivating a supportive online environment for discussions on mental health and eating disorders.

cs.SI↗

arXiv2024

Social Approval and Network Homophily as Motivators of Online Toxicity

Online hate messaging is a pervasive issue plaguing the well-being of social media users. This research empirically investigates a novel theory positing that online hate may be driven primarily by the pursuit of social approval rather than a direct desire to harm the targets. Results show that toxicity is homophilous in users' social networks and that a user's propensity for hostility can be predicted by their social networks. We also illustrate how receiving greater or fewer social engagements in the form of likes, retweets, quotes, and replies affects a user's subsequent toxicity. We establish a clear connection between receiving social approval signals and increases in subsequent toxicity. Being retweeted plays a particularly prominent role in escalating toxicity. Results also show that not receiving expected levels of social approval leads to decreased toxicity. We discuss the important implications of our research and opportunities to combat online hate.

cs.SI↗

arXiv2024

Coordinated Activity Modulates the Behavior and Emotions of Organic Users: A Case Study on Tweets about the Gaza Conflict

Social media has become a crucial conduit for the swift dissemination of information during global crises. However, this also paves the way for the manipulation of narratives by malicious actors. This research delves into the interaction dynamics between coordinated (malicious) entities and organic (regular) users on Twitter amidst the Gaza conflict. Through the analysis of approximately 3.5 million tweets from over 1.3 million users, our study uncovers that coordinated users significantly impact the information landscape, successfully disseminating their content across the network: a substantial fraction of their messages is adopted and shared by organic users. Furthermore, the study documents a progressive increase in organic users' engagement with coordinated content, which is paralleled by a discernible shift towards more emotionally polarized expressions in their subsequent communications. These results highlight the critical need for vigilance and a nuanced understanding of information manipulation on social media platforms.

cs.SI↗

arXiv2024

GET-Tok: A GenAI-Enriched Multimodal TikTok Dataset Documenting the 2022 Attempted Coup in Peru

TikTok is one of the largest and fastest-growing social media sites in the world. TikTok features, however, such as voice transcripts, are often missing and other important features, such as OCR or video descriptions, do not exist. We introduce the Generative AI Enriched TikTok (GET-Tok) data, a pipeline for collecting TikTok videos and enriched data by augmenting the TikTok Research API with generative AI models. As a case study, we collect videos about the attempted coup in Peru initiated by its former President, Pedro Castillo, and its accompanying protests. The data includes information on 43,697 videos published from November 20, 2022 to March 1, 2023 (102 days). Generative AI augments the collected data via transcripts of TikTok videos, text descriptions of what is shown in the videos, what text is displayed within the video, and the stances expressed in the video. Overall, this pipeline will contribute to a better understanding of online discussion in a multimodal setting with applications of Generative AI, especially outlining the utility of this pipeline in non-English-language social media. Our code used to produce the pipeline is in a public Github repository: https://github.com/gabbypinto/GET-Tok-Peru.

cs.SI↗

arXiv2024

FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs

Our society is facing rampant misinformation harming public health and trust. To address the societal challenge, we introduce FACT-GPT, a system leveraging Large Language Models (LLMs) to automate the claim matching stage of fact-checking. FACT-GPT, trained on a synthetic dataset, identifies social media content that aligns with, contradicts, or is irrelevant to previously debunked claims. Our evaluation shows that our specialized LLMs can match the accuracy of larger models in identifying related claims, closely mirroring human judgment. This research provides an automated solution for efficient claim matching, demonstrates the potential of LLMs in supporting fact-checkers, and offers valuable resources for further research in the field.

cs.CL↗

arXiv2024

The Butterfly Effect in Artificial Intelligence Systems: Implications for AI Bias and Fairness

The Butterfly Effect, a concept originating from chaos theory, underscores how small changes can have significant and unpredictable impacts on complex systems. In the context of AI fairness and bias, the Butterfly Effect can stem from a variety of sources, such as small biases or skewed data inputs during algorithm development, saddle points in training, or distribution shifts in data between training and testing phases. These seemingly minor alterations can lead to unexpected and substantial unfair outcomes, disproportionately affecting underrepresented individuals or groups and perpetuating pre-existing inequalities. Moreover, the Butterfly Effect can amplify inherent biases within data or algorithms, exacerbate feedback loops, and create vulnerabilities for adversarial attacks. Given the intricate nature of AI systems and their societal implications, it is crucial to thoroughly examine any changes to algorithms or input data for potential unintended consequences. In this paper, we envision both algorithmic and empirical strategies to detect, quantify, and mitigate the Butterfly Effect in AI systems, emphasizing the importance of addressing these challenges to promote fairness and ensure responsible AI development.

cs.CY↗

arXiv2024

GenAI Against Humanity: Nefarious Applications of Generative Artificial Intelligence and Large Language Models

Generative Artificial Intelligence (GenAI) and Large Language Models (LLMs) are marvels of technology; celebrated for their prowess in natural language processing and multimodal content generation, they promise a transformative future. But as with all powerful tools, they come with their shadows. Picture living in a world where deepfakes are indistinguishable from reality, where synthetic identities orchestrate malicious campaigns, and where targeted misinformation or scams are crafted with unparalleled precision. Welcome to the darker side of GenAI applications. This article is not just a journey through the meanders of potential misuse of GenAI and LLMs, but also a call to recognize the urgency of the challenges ahead. As we navigate the seas of misinformation campaigns, malicious content generation, and the eerie creation of sophisticated malware, we'll uncover the societal implications that ripple through the GenAI revolution we are witnessing. From AI-powered botnets on social media platforms to the unnerving potential of AI to generate fabricated identities, or alibis made of synthetic realities, the stakes have never been higher. The lines between the virtual and the real worlds are blurring, and the consequences of potential GenAI's nefarious applications impact us all. This article serves both as a synthesis of rigorous research presented on the risks of GenAI and misuse of LLMs and as a thought-provoking vision of the different types of harmful GenAI applications we might encounter in the near future, and some ways we can prepare for them.

cs.CY↗

arXiv2024

Moral Values Underpinning COVID-19 Online Communication Patterns

The COVID-19 pandemic has triggered profound societal changes, extending beyond its health impacts to the moralization of behaviors. Leveraging insights from moral psychology, this study delves into the moral fabric shaping online discussions surrounding COVID-19 over a span of nearly two years. Our investigation identifies four distinct user groups characterized by differences in morality, political ideology, and communication styles. We underscore the intricate relationship between moral differences and political ideologies, revealing a nuanced picture where moral orientations do not rigidly separate users politically. Furthermore, we uncover patterns of moral homophily within the social network, highlighting the existence of one potential moral echo chamber. Analyzing the moral themes embedded in messages, we observe that messages featuring moral foundations not typically favored by their authors, as well as those incorporating multiple moral foundations, resonate more effectively with out-group members. This research contributes valuable insights into the complex interplay between moral foundations, communication dynamics, and network structures on Twitter.

cs.SI↗

arXiv2023

Social-LLM: Modeling User Behavior at Scale using Language Models and Social Network Data

The proliferation of social network data has unlocked unprecedented opportunities for extensive, data-driven exploration of human behavior. The structural intricacies of social networks offer insights into various computational social science issues, particularly concerning social influence and information diffusion. However, modeling large-scale social network data comes with computational challenges. Though large language models make it easier than ever to model textual content, any advanced network representation methods struggle with scalability and efficient deployment to out-of-sample users. In response, we introduce a novel approach tailored for modeling social network data in user detection tasks. This innovative method integrates localized social network interactions with the capabilities of large language models. Operating under the premise of social network homophily, which posits that socially connected users share similarities, our approach is designed to address these challenges. We conduct a thorough evaluation of our method across seven real-world social network datasets, spanning a diverse range of topics and detection tasks, showcasing its applicability to advance research in computational social science.

cs.SI↗

arXiv2023

Social Bots: Detection and Challenges

While social media are a key source of data for computational social science, their ease of manipulation by malicious actors threatens the integrity of online information exchanges and their analysis. In this Chapter, we focus on malicious social bots, a prominent vehicle for such manipulation. We start by discussing recent studies about the presence and actions of social bots in various online discussions to show their real-world implications and the need for detection methods. Then we discuss the challenges of bot detection methods and use Botometer, a publicly available bot detection tool, as a case study to describe recent developments in this area. We close with a practical guide on how to handle social bots in social media research.

cs.SI↗

arXiv2023

Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies

The significant advancements in applying Artificial Intelligence (AI) to healthcare decision-making, medical diagnosis, and other domains have simultaneously raised concerns about the fairness and bias of AI systems. This is particularly critical in areas like healthcare, employment, criminal justice, credit scoring, and increasingly, in generative AI models (GenAI) that produce synthetic media. Such systems can lead to unfair outcomes and perpetuate existing inequalities, including generative biases that affect the representation of individuals in synthetic data. This survey paper offers a succinct, comprehensive overview of fairness and bias in AI, addressing their sources, impacts, and mitigation strategies. We review sources of bias, such as data, algorithm, and human decision biases - highlighting the emergent issue of generative AI bias where models may reproduce and amplify societal stereotypes. We assess the societal impact of biased AI systems, focusing on the perpetuation of inequalities and the reinforcement of harmful stereotypes, especially as generative AI becomes more prevalent in creating content that influences public perception. We explore various proposed mitigation strategies, discussing the ethical considerations of their implementation and emphasizing the need for interdisciplinary collaboration to ensure effectiveness. Through a systematic literature review spanning multiple academic disciplines, we present definitions of AI bias and its different types, including a detailed look at generative AI bias. We discuss the negative impacts of AI bias on individuals and society and provide an overview of current approaches to mitigate AI bias, including data pre-processing, model selection, and post-processing. We emphasize the unique challenges presented by generative AI models and the importance of strategies specifically tailored to address these.

cs.CY↗

arXiv2023

Tracking the Newsworthiness of Public Documents

Journalists must find stories in huge amounts of textual data (e.g. leaks, bills, press releases) as part of their jobs: determining when and why text becomes news can help us understand coverage patterns and help us build assistive tools. Yet, this is challenging because very few labelled links exist, language use between corpora is very different, and text may be covered for a variety of reasons. In this work we focus on news coverage of local public policy in the San Francisco Bay Area by the San Francisco Chronicle. First, we gather news articles, public policy documents and meeting recordings and link them using probabilistic relational modeling, which we show is a low-annotation linking methodology that outperforms other retrieval-based baselines. Second, we define a new task: newsworthiness prediction, to predict if a policy item will get covered. We show that different aspects of public policy discussion yield different newsworthiness signals. Finally we perform human evaluation with expert journalists and show our systems identify policies they consider newsworthy with 68% F1 and our coverage recommendations are helpful with an 84% win-rate.

cs.CL↗

arXiv2023

Leveraging Large Language Models to Detect Influence Campaigns in Social Media

Social media influence campaigns pose significant challenges to public discourse and democracy. Traditional detection methods fall short due to the complexity and dynamic nature of social media. Addressing this, we propose a novel detection method using Large Language Models (LLMs) that incorporates both user metadata and network structures. By converting these elements into a text format, our approach effectively processes multilingual content and adapts to the shifting tactics of malicious campaign actors. We validate our model through rigorous testing on multiple datasets, showcasing its superior performance in identifying influence efforts. This research not only offers a powerful tool for detecting campaigns, but also sets the stage for future enhancements to keep up with the fast-paced evolution of social media-based influence tactics.

cs.SI↗

arXiv2023

Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models

As the capabilities of generative language models continue to advance, the implications of biases ingrained within these models have garnered increasing attention from researchers, practitioners, and the broader public. This article investigates the challenges and risks associated with biases in large-scale language models like ChatGPT. We discuss the origins of biases, stemming from, among others, the nature of training data, model specifications, algorithmic constraints, product design, and policy decisions. We explore the ethical concerns arising from the unintended consequences of biased model outputs. We further analyze the potential opportunities to mitigate biases, the inevitability of some biases, and the implications of deploying these models in various applications, such as virtual assistants, content generation, and chatbots. Finally, we review the current approaches to identify, quantify, and mitigate biases in language models, emphasizing the need for a multi-disciplinary, collaborative effort to develop more equitable, transparent, and responsible AI systems. This article aims to stimulate a thoughtful dialogue within the artificial intelligence community, encouraging researchers and developers to reflect on the role of biases in generative language models and the ongoing pursuit of ethical AI.

cs.CY↗

arXiv2023

What are Your Pronouns? Examining Gender Pronoun Usage on Twitter

Stating your gender pronouns, along with your name, is becoming the new norm of self-introductions at school, at the workplace, and online. The increasing prevalence and awareness of nonconforming gender identities put discussions of developing gender-inclusive language at the forefront. This work presents the first empirical research on gender pronoun usage on large-scale social media. Leveraging a Twitter dataset of over 2 billion tweets collected continuously over two years, we find that the public declaration of gender pronouns is on the rise, with most people declaring as using she series pronouns, followed by he series pronouns, and a smaller but considerable amount of non-binary pronouns. From analyzing Twitter posts and sharing activities, we can discern users who use gender pronouns from those who do not and also distinguish users of various gender identities. We further illustrate the relationship between explicit forms of social network exposure to gender pronouns and their eventual gender pronoun adoption. This work carries crucial implications for gender-identity studies and initiates new research directions in gender-related fairness and inclusion, as well as support against online harassment and discrimination on social media.

cs.SI↗

arXiv2023

Unmasking the Web of Deceit: Uncovering Coordinated Activity to Expose Information Operations on Twitter

Social media platforms, particularly Twitter, have become pivotal arenas for influence campaigns, often orchestrated by state-sponsored information operations (IOs). This paper delves into the detection of key players driving IOs by employing similarity graphs constructed from behavioral pattern data. We unveil that well-known, yet underutilized network properties can help accurately identify coordinated IO drivers. Drawing from a comprehensive dataset of 49 million tweets from six countries, which includes multiple verified IOs, our study reveals that traditional network filtering techniques do not consistently pinpoint IO drivers across campaigns. We first propose a framework based on node pruning that emerges superior, particularly when combining multiple behavioral indicators across different networks. Then, we introduce a supervised machine learning model that harnesses a vector representation of the fused similarity network. This model, which boasts a precision exceeding 0.95, adeptly classifies IO drivers on a global scale and reliably forecasts their temporal engagements. Our findings are crucial in the fight against deceptive influence campaigns on social media, helping us better understand and detect them.

cs.SI↗

arXiv2023

Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation

In today's digital era, the rapid spread of misinformation poses threats to public well-being and societal trust. As online misinformation proliferates, manual verification by fact checkers becomes increasingly challenging. We introduce FACT-GPT (Fact-checking Augmentation with Claim matching Task-oriented Generative Pre-trained Transformer), a framework designed to automate the claim matching phase of fact-checking using Large Language Models (LLMs). This framework identifies new social media content that either supports or contradicts claims previously debunked by fact-checkers. Our approach employs GPT-4 to generate a labeled dataset consisting of simulated social media posts. This data set serves as a training ground for fine-tuning more specialized LLMs. We evaluated FACT-GPT on an extensive dataset of social media content related to public health. The results indicate that our fine-tuned LLMs rival the performance of larger pre-trained LLMs in claim matching tasks, aligning closely with human annotations. This study achieves three key milestones: it provides an automated framework for enhanced fact-checking; demonstrates the potential of LLMs to complement human expertise; offers public resources, including datasets and models, to further research and applications in the fact-checking domain.

cs.CL↗