Emilio Ferrara

Julie Jiang, Xiang Ren, Emilio Ferrara

Estimating the political leanings of social media users is a challenging and ever more pressing problem given the increase in social media consumption. We introduce Retweet-BERT, a simple and scalable model to estimate the political leanings of Twitter users. Retweet-BERT leverages the retweet network structure and the language used in users' profile descriptions. Our assumptions stem from patterns of networks and linguistics homophily among people who share similar ideologies. Retweet-BERT demonstrates competitive performance against other state-of-the-art baselines, achieving 96%-97% macro-F1 on two recent Twitter datasets (a COVID-19 dataset and a 2020 United States presidential elections dataset). We also perform manual validation to validate the performance of Retweet-BERT on users not in the training data. Finally, in a case study of COVID-19, we illustrate the presence of political echo chambers on Twitter and show that it exists primarily among right-leaning users. Our code is open-sourced and our data is publicly available.

Isabelle Augenstein, Timothy Baldwin, Meeyoung Cha et al.

The emergence of tools based on Large Language Models (LLMs), such as OpenAI's ChatGPT, Microsoft's Bing Chat, and Google's Bard, has garnered immense public attention. These incredibly useful, natural-sounding tools mark significant advances in natural language generation, yet they exhibit a propensity to generate false, erroneous, or misleading content -- commonly referred to as "hallucinations." Moreover, LLMs can be exploited for malicious applications, such as generating false but credible-sounding content and profiles at scale. This poses a significant challenge to society in terms of the potential deception of users and the increasing dissemination of inaccurate information. In light of these risks, we explore the kinds of technological innovations, regulatory reforms, and AI literacy initiatives needed from fact-checkers, news organizations, and the broader research and policy communities. By identifying the risks, the imminent threats, and some viable solutions, we seek to shed light on navigating various aspects of veracity in the era of generative AI.

Emilio Ferrara

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.

Emilio Ferrara

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.

Eun Cheol Choi, Emilio Ferrara

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.

Luca Luceri, Eric Boniardi, Emilio Ferrara

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.

Fatima Ezzeddine, Luca Luceri, Omran Ayoub et al.

The detection of state-sponsored trolls operating in influence campaigns on social media is a critical and unsolved challenge for the research community, which has significant implications beyond the online realm. To address this challenge, we propose a new AI-based solution that identifies troll accounts solely through behavioral cues associated with their sequences of sharing activity, encompassing both their actions and the feedback they receive from others. Our approach does not incorporate any textual content shared and consists of two steps: First, we leverage an LSTM-based classifier to determine whether account sequences belong to a state-sponsored troll or an organic, legitimate user. Second, we employ the classified sequences to calculate a metric named the "Troll Score", quantifying the degree to which an account exhibits troll-like behavior. To assess the effectiveness of our method, we examine its performance in the context of the 2016 Russian interference campaign during the U.S. Presidential election. Our experiments yield compelling results, demonstrating that our approach can identify account sequences with an AUC close to 99% and accurately differentiate between Russian trolls and organic users with an AUC of 91%. Notably, our behavioral-based approach holds a significant advantage in the ever-evolving landscape, where textual and linguistic properties can be easily mimicked by Large Language Models (LLMs): In contrast to existing language-based techniques, it relies on more challenging-to-replicate behavioral cues, ensuring greater resilience in identifying influence campaigns, especially given the potential increase in the usage of LLMs for generating inauthentic content. Finally, we assessed the generalizability of our solution to various entities driving different information operations and found promising results that will guide future research.

Akira Matsui, Emilio Ferrara

To extract essential information from complex data, computer scientists have been developing machine learning models that learn low-dimensional representation mode. From such advances in machine learning research, not only computer scientists but also social scientists have benefited and advanced their research because human behavior or social phenomena lies in complex data. However, this emerging trend is not well documented because different social science fields rarely cover each other's work, resulting in fragmented knowledge in the literature. To document this emerging trend, we survey recent studies that apply word embedding techniques to human behavior mining. We built a taxonomy to illustrate the methods and procedures used in the surveyed papers, aiding social science researchers in contextualizing their research within the literature on word embedding applications. This survey also conducts a simple experiment to warn that common similarity measurements used in the literature could yield different results even if they return consistent results at an aggregate level.

Alexander J. Bisberg, Emilio Ferrara

Win prediction is crucial to understanding skill modeling, teamwork and matchmaking in esports. In this paper we propose GCN-WP, a semi-supervised win prediction model for esports based on graph convolutional networks. This model learns the structure of an esports league over the course of a season (1 year) and makes predictions on another similar league. This model integrates over 30 features about the match and players and employs graph convolution to classify games based on their neighborhood. Our model achieves state-of-the-art prediction accuracy when compared to machine learning or skill rating models for LoL. The framework is generalizable so it can easily be extended to other multiplayer online games.

Jinyi Ye, Lei Cao, Ding Chen et al.

The scientific claims drawn from LLM social simulations should be no stronger than the robustness audits that support them. Generative agents bring new expressive power to agent-based modeling, enabling simulations of collective social processes like cooperation, polarization, and norm formation. Yet they also introduce complexity through additional architectural choices, such as agent specification, memory representation, interaction protocols, and environment design. Small perturbations that appear minor to researchers can cascade into macro-level outcomes through repeated interaction, creating a "butterfly effect." Consequently, scientific claims drawn from LLM social simulations may reflect implementation artifacts rather than the social mechanisms being modeled. We support this position with two case studies: a repeated Prisoner's Dilemma and a social media echo chamber simulation. Across multiple models, minor perturbations in persona format and game-instruction framing shift cooperation rates by up to 76 percentage points, while network homophily and hub assignment produce significant and consistent shifts in polarization metrics. We also find that sensitivity is unevenly distributed across both architectural choices and model families: the same perturbation that produces the 76 pp shift in one frontier model only shifts another by 1 pp. Robustness is therefore a property that should be measured per claim and per model, not assumed. To address this validation gap, we introduce TRAILS (Taxonomy for Robustness Audits In LLM Simulations), a robustness-audit taxonomy spanning three levels of simulation design: agent (micro-level), interaction (meso-level), and system (macro-level). We call for robustness to become a first-order validation requirement before LLM social simulations are used to explain mechanisms, evaluate interventions, or inform decisions.

Yilei Zeng, Jiali Duan, Yang Li et al.

Human-centered AI considers human experiences with AI performance. While abundant research has been helping AI achieve superhuman performance either by fully automatic or weak supervision learning, fewer endeavors are experimenting with how AI can tailor to humans' preferred skill level given fine-grained input. In this work, we guide the curriculum reinforcement learning results towards a preferred performance level that is neither too hard nor too easy via learning from the human decision process. To achieve this, we developed a portable, interactive platform that enables the user to interact with agents online via manipulating the task difficulty, observing performance, and providing curriculum feedback. Our system is highly parallelizable, making it possible for a human to train large-scale reinforcement learning applications that require millions of samples without a server. The result demonstrates the effectiveness of an interactive curriculum for reinforcement learning involving human-in-the-loop. It shows reinforcement learning performance can successfully adjust in sync with the human desired difficulty level. We believe this research will open new doors for achieving flow and personalized adaptive difficulties.

Tommaso Fornaciari, Luca Luceri, Emilio Ferrara et al.

Detecting misinformation threads is crucial to guarantee a healthy environment on social media. We address the problem using the data set created during the COVID-19 pandemic. It contains cascades of tweets discussing information weakly labeled as reliable or unreliable, based on a previous evaluation of the information source. The models identifying unreliable threads usually rely on textual features. But reliability is not just what is said, but by whom and to whom. We additionally leverage on network information. Following the homophily principle, we hypothesize that users who interact are generally interested in similar topics and spreading similar kind of news, which in turn is generally reliable or not. We test several methods to learn representations of the social interactions within the cascades, combining them with deep neural language models in a Multi-Input (MI) framework. Keeping track of the sequence of the interactions during the time, we improve over previous state-of-the-art models.

Siyi Zhou, Peiran Qiu, Tanishq Salkar et al.

While substantial efforts in anti-trafficking research and practice have focused on identifying and assisting victims after exploitation occurs, comparatively less attention has been paid to preventing victimization at the recruitment stage. Although some platforms offer preventive tools, such as background checks triggered by in-person meeting detection, these measures primarily protect potential victims rather than directly limiting traffickers' recruitment activities. In this paper, we propose a computational framework to identify human trafficking recruiters through their linguistic features and to characterize their online recruitment patterns. We introduce a network-driven labeling method to construct large-scale ground truth for trafficking-at-risk job advertisements. Our results reveal significant linguistic differences between safe and risky advertisements and demonstrate that language models and embedding representations behave distinctly across these linguistic spaces. Building on these insights, we propose a multi-model ensemble classifier to improve the detection of trafficking-at-risk job ads. Finally, we analyze the geographic, gender, industry, and contact-method preferences of trafficking recruiters, revealing systematic patterns in recruitment strategies.

Emily Chen, Alexander J. Bisberg, Dmitri Williams et al.

This paper examines how player flexibility -- a player's willingness to engage in a breadth of options or specialize -- manifests across two gaming environments: League of Legends (League) and Teamfight Tactics (TFT). We analyze the gameplay decisions of 4,830 players who have played at least 50 competitive games in both titles and explore cross-game dynamics of behavior retention and consistency. Our work introduces a novel cross-game analysis that tracks the same players' behavior across two different environments, reducing self-selection bias. Our findings reveal that while games incentivize different behaviors (specialization in League versus flexibility in TFT) for performance-based success, players exhibit consistent behavior across platforms. This study contributes to long-standing debate about agency versus structure, showing individual agency may be more predictive of cross-platform behavior than game-imposed structure in competitive settings. These insights offer implications for game developers, designers and researchers interested in building systems to promote behavior change.

Akira Matsui, Emilio Ferrara

Recent advances in digital platforms generate rich, high-dimensional logs of human behavior, and machine learning models have helped social scientists explain knowledge accumulation, communication, and information diffusion. Such models, however, almost always treat behavior as sequences of actions, abstracting the inter-temporal information among actions. To close this gap, we introduce a two-scale Action-Timing Context(ATC) framework that jointly embeds each action and its time interval. ATC obtains low-dimensional representations of actions and characterizes them with inter-temporal information. We provide three applications of ATC to real-world datasets and demonstrate that the method offers a unified view of human behavior. The presented qualitative findings demonstrate that explicitly modeling inter-temporal context is essential for a comprehensive, interpretable understanding of human activity on digital platforms.

Hyundong Cho, Shuai Liu, Taiwei Shi et al.

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.

Emily Chen, Alexander Bisberg, Emilio Ferrara

This study investigates the concept of flexibility within League of Legends, a popular online multiplayer game, focusing on the relationship between user adaptability and team success. Utilizing a dataset encompassing players of varying skill levels and play styles, we calculate two measures of flexibility for each player: overall flexibility and temporal flexibility. Our findings suggest that the flexibility of a user is dependent upon a user's preferred play style, and flexibility does impact match outcome. This work also shows that skill level not only indicates how willing a player is to adapt their play style but also how their adaptability changes over time. This paper highlights the duality and balance of specialization versus flexibility, providing insights that can inform strategic planning, collaboration and resource allocation in competitive environments.

Eun Cheol Choi, Ashwin Balasubramanian, Jinhu Qi et al.

Misinformation surrounding emerging outbreaks poses a serious societal threat, making robust countermeasures essential. One promising approach is stance detection (SD), which identifies whether social media posts support or oppose misleading claims. In this work, we finetune classifiers on COVID-19 misinformation SD datasets consisting of claims and corresponding tweets. Specifically, we test controllable misinformation generation (CMG) using large language models (LLMs) as a method for data augmentation. While CMG demonstrates the potential for expanding training datasets, our experiments reveal that performance gains over traditional augmentation methods are often minimal and inconsistent, primarily due to built-in safeguards within LLMs. We release our code and datasets to facilitate further research on misinformation detection and generation.

Alexander Spangher, Emilio Ferrara, Ben Welsh et al.

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.

Peiran Qiu, Siyi Zhou, Emilio Ferrara

This study examines information suppression mechanisms in DeepSeek, an open-source large language model (LLM) developed in China. We propose an auditing framework and use it to analyze the model's responses to 646 politically sensitive prompts by comparing its final output with intermediate chain-of-thought (CoT) reasoning. Our audit unveils evidence of semantic-level information suppression in DeepSeek: sensitive content often appears within the model's internal reasoning but is omitted or rephrased in the final output. Specifically, DeepSeek suppresses references to transparency, government accountability, and civic mobilization, while occasionally amplifying language aligned with state propaganda. This study underscores the need for systematic auditing of alignment, content moderation, information suppression, and censorship practices implemented into widely-adopted AI models, to ensure transparency, accountability, and equitable access to unbiased information obtained by means of these systems.

Vaibhav Kumar, Hana Koorehdavoudi, Masud Moshtaghi et al.

We propose CHRT (Control Hidden Representation Transformation) - a controlled language generation framework that steers large language models to generate text pertaining to certain attributes (such as toxicity). CHRT gains attribute control by modifying the hidden representation of the base model through learned transformations. We employ a contrastive-learning framework to learn these transformations that can be combined to gain multi-attribute control. The effectiveness of CHRT is experimentally shown by comparing it with seven baselines over three attributes. CHRT outperforms all the baselines in the task of detoxification, positive sentiment steering, and text simplification while minimizing the loss in linguistic qualities. Further, our approach has the lowest inference latency of only 0.01 seconds more than the base model, making it the most suitable for high-performance production environments. We open-source our code and release two novel datasets to further propel controlled language generation research.

Palash Goyal, Di Huang, Ankita Goswami et al.

Graph embedding is the task of representing nodes of a graph in a low-dimensional space and its applications for graph tasks have gained significant traction in academia and industry. The primary difference among the many recently proposed graph embedding methods is the way they preserve the inherent properties of the graphs. However, in practice, comparing these methods is very challenging. The majority of methods report performance boosts on few selected real graphs. Therefore, it is difficult to generalize these performance improvements to other types of graphs. Given a graph, it is currently impossible to quantify the advantages of one approach over another. In this work, we introduce a principled framework to compare graph embedding methods. Our goal is threefold: (i) provide a unifying framework for comparing the performance of various graph embedding methods, (ii) establish a benchmark with real-world graphs that exhibit different structural properties, and (iii) provide users with a tool to identify the best graph embedding method for their data. This paper evaluates 4 of the most influential graph embedding methods and 4 traditional link prediction methods against a corpus of 100 real-world networks with varying properties. We organize the 100 networks in terms of their properties to get a better understanding of the embedding performance of these popular methods. We use the comparisons on our 100 benchmark graphs to define GFS-score, that can be applied to any embedding method to quantify its performance. We rank the state-of-the-art embedding approaches using the GFS-score and show that it can be used to understand and evaluate novel embedding approaches. We envision that the proposed framework (https://www.github.com/palash1992/GEM-Benchmark) will serve the community as a benchmarking platform to test and compare the performance of future graph embedding techniques.

Palash Goyal, Sujit Rokka Chhetri, Ninareh Mehrabi et al.

DynamicGEM is an open-source Python library for learning node representations of dynamic graphs. It consists of state-of-the-art algorithms for defining embeddings of nodes whose connections evolve over time. The library also contains the evaluation framework for four downstream tasks on the network: graph reconstruction, static and temporal link prediction, node classification, and temporal visualization. We have implemented various metrics to evaluate the state-of-the-art methods, and examples of evolving networks from various domains. We have easy-to-use functions to call and evaluate the methods and have extensive usage documentation. Furthermore, DynamicGEM provides a template to add new algorithms with ease to facilitate further research on the topic.

Palash Goyal, Emilio Ferrara

Graphs, such as social networks, word co-occurrence networks, and communication networks, occur naturally in various real-world applications. Analyzing them yields insight into the structure of society, language, and different patterns of communication. Many approaches have been proposed to perform the analysis. Recently, methods which use the representation of graph nodes in vector space have gained traction from the research community. In this survey, we provide a comprehensive and structured analysis of various graph embedding techniques proposed in the literature. We first introduce the embedding task and its challenges such as scalability, choice of dimensionality, and features to be preserved, and their possible solutions. We then present three categories of approaches based on factorization methods, random walks, and deep learning, with examples of representative algorithms in each category and analysis of their performance on various tasks. We evaluate these state-of-the-art methods on a few common datasets and compare their performance against one another. Our analysis concludes by suggesting some potential applications and future directions. We finally present the open-source Python library we developed, named GEM (Graph Embedding Methods, available at https://github.com/palash1992/GEM), which provides all presented algorithms within a unified interface to foster and facilitate research on the topic.

Bijean Ghafouri, Eun Cheol Choi, Priyanka Dey et al.

RLHF assumes that annotation responses reflect genuine human preferences. We argue this assumption warrants systematic examination, and that behavioral science offers frameworks that bring clarity to when it holds and when it breaks down. Behavioral scientists have documented for sixty years that people routinely produce responses without holding genuine opinions, construct preferences on the spot based on contextual cues, and interpret identical questions differently. These phenomena are pervasive for precisely the value-laden judgments that matter most for alignment, yet this literature has not yet been systematically integrated into ML practice. We argue that the ML community must treat measurement validity as logically prior to preference aggregation. Specifically, we contend that measuring human preferences in RLHF is a social science problem. We present a taxonomy distinguishing genuine preferences from non-attitudes, constructed preferences, and measurement artifacts, along with diagnostic approaches for detecting each. This framework has two important implications. First, it raises the question of whether current RLHF practice may be systematically modeling noise as signal and elicitation artifacts as human values. Second, it provides a path forward by suggesting diagnostic tools that can distinguish valid preferences from artifacts before they enter the training pipeline.

Eun Cheol Choi, Emilio Ferrara

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.

Lincan Li, Jiaqi Li, Catherine Chen et al.

In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection. Meanwhile, the need to systematically understand how LLMs can further revolutionize the field also becomes urgent. In this work, we--a multidisciplinary team of researchers spanning computer science and political science--present the first principled framework termed Political-LLM to advance the comprehensive understanding of integrating LLMs into computational political science. Specifically, we first introduce a fundamental taxonomy classifying the existing explorations into two perspectives: political science and computational methodologies. In particular, from the political science perspective, we highlight the role of LLMs in automating predictive and generative tasks, simulating behavior dynamics, and improving causal inference through tools like counterfactual generation; from a computational perspective, we introduce advancements in data preparation, fine-tuning, and evaluation methods for LLMs that are tailored to political contexts. We identify key challenges and future directions, emphasizing the development of domain-specific datasets, addressing issues of bias and fairness, incorporating human expertise, and redefining evaluation criteria to align with the unique requirements of computational political science. Political-LLM seeks to serve as a guidebook for researchers to foster an informed, ethical, and impactful use of Artificial Intelligence in political science. Our online resource is available at: http://political-llm.org/.

Daniel M. Benjamin, Fred Morstatter, Ali E. Abbas et al. · stanford

Sound decision-making relies on accurate prediction for tangible outcomes ranging from military conflict to disease outbreaks. To improve crowdsourced forecasting accuracy, we developed SAGE, a hybrid forecasting system that combines human and machine generated forecasts. The system provides a platform where users can interact with machine models and thus anchor their judgments on an objective benchmark. The system also aggregates human and machine forecasts weighting both for propinquity and based on assessed skill while adjusting for overconfidence. We present results from the Hybrid Forecasting Competition (HFC) - larger than comparable forecasting tournaments - including 1085 users forecasting 398 real-world forecasting problems over eight months. Our main result is that the hybrid system generated more accurate forecasts compared to a human-only baseline which had no machine generated predictions. We found that skilled forecasters who had access to machine-generated forecasts outperformed those who only viewed historical data. We also demonstrated the inclusion of machine-generated forecasts in our aggregation algorithms improved performance, both in terms of accuracy and scalability. This suggests that hybrid forecasting systems, which potentially require fewer human resources, can be a viable approach for maintaining a competitive level of accuracy over a larger number of forecasting questions.

Julie Jiang, Emilio Ferrara

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.

Marco Minici, Luca Luceri, Francesco Fabbri et al.

Social media platforms have become vital spaces for public discourse, serving as modern agoràs where a wide range of voices influence societal narratives. However, their open nature also makes them vulnerable to exploitation by malicious actors, including state-sponsored entities, who can conduct information operations (IOs) to manipulate public opinion. The spread of misinformation, false news, and misleading claims threatens democratic processes and societal cohesion, making it crucial to develop methods for the timely detection of inauthentic activity to protect the integrity of online discourse. In this work, we introduce a methodology designed to identify users orchestrating information operations, a.k.a. IO drivers, across various influence campaigns. Our framework, named IOHunter, leverages the combined strengths of Language Models and Graph Neural Networks to improve generalization in supervised, scarcely-supervised, and cross-IO contexts. Our approach achieves state-of-the-art performance across multiple sets of IOs originating from six countries, significantly surpassing existing approaches. This research marks a step toward developing Graph Foundation Models specifically tailored for the task of IO detection on social media platforms.

Alexander Spangher, James Youn, Matt DeButts et al.

Human writers plan, then write. For large language models (LLMs) to play a role in longer-form article generation, we must understand the planning steps humans make before writing. We explore one kind of planning, source-selection in news, as a case-study for evaluating plans in long-form generation. We ask: why do specific stories call for specific kinds of sources? We imagine a generative process for story writing where a source-selection schema is first selected by a journalist, and then sources are chosen based on categories in that schema. Learning the article's plan means predicting the schema initially chosen by the journalist. Working with professional journalists, we adapt five existing schemata and introduce three new ones to describe journalistic plans for the inclusion of sources in documents. Then, inspired by Bayesian latent-variable modeling, we develop metrics to select the most likely plan, or schema, underlying a story, which we use to compare schemata. We find that two schemata: stance and social affiliation best explain source plans in most documents. However, other schemata like textual entailment explain source plans in factually rich topics like "Science". Finally, we find we can predict the most suitable schema given just the article's headline with reasonable accuracy. We see this as an important case-study for human planning, and provides a framework and approach for evaluating other kinds of plans. We release a corpora, NewsSources, with annotations for 4M articles.

Nikos Kanakaris, Heng Ping, Xiongye Xiao et al.

Detecting organized political campaigns is of paramount importance in fighting against disinformation on social media. Existing approaches for the identification of such organized actions employ techniques mostly from network science, graph machine learning and natural language processing. Their ultimate goal is to analyze the relationships and interactions (e.g. re-posting) among users and the textual similarities of their posts. Despite their effectiveness in recognizing astroturf campaigns, these methods face significant challenges, notably the class imbalance in available training datasets. To mitigate this issue, recent methods usually resort to data augmentation or increasing the number of positive samples, which may not always be feasible or sufficient in real-world settings. Following a different path, in this paper, we propose a novel framework for identifying astroturf campaigns based solely on large language models (LLMs), introducing a Balanced Retrieval-Augmented Generation (Balanced RAG) component. Our approach first gives both textual information concerning the posts (in our case tweets) and the user interactions of the social network as input to a language model. Then, through prompt engineering and the proposed Balanced RAG method, it effectively detects coordinated disinformation campaigns on X (Twitter). The proposed framework does not require any training or fine-tuning of the language model. Instead, by strategically harnessing the strengths of prompt engineering and Balanced RAG, it facilitates LLMs to overcome the effects of class imbalance and effectively identify coordinated political campaigns. The experimental results demonstrate that by incorporating the proposed prompt engineering and Balanced RAG methods, our framework outperforms the traditional graph-based baselines, achieving 2x-3x improvements in terms of precision, recall and F1 scores.

Amin Banayeeanzade, Ala N. Tak, Fatemeh Bahrani et al.

The ability to control LLMs' emulated emotional states and personality traits is essential for enabling rich, human-centered interactions in socially interactive settings. We introduce PsySET, a Psychologically-informed benchmark to evaluate LLM Steering Effectiveness and Trustworthiness across the emotion and personality domains. Our study spans four models from different LLM families paired with various steering strategies, including prompting, fine-tuning, and representation engineering. Our results indicate that prompting is consistently effective but limited in intensity control, whereas vector injections achieve finer controllability while slightly reducing output quality. Moreover, we explore the trustworthiness of steered LLMs by assessing safety, truthfulness, fairness, and ethics, highlighting potential side effects and behavioral shifts. Notably, we observe idiosyncratic effects; for instance, even a positive emotion like joy can degrade robustness to adversarial factuality, lower privacy awareness, and increase preferential bias. Meanwhile, anger predictably elevates toxicity yet strengthens leakage resistance. Our framework establishes the first holistic evaluation of emotion and personality steering, offering insights into its interpretability and reliability for socially interactive applications.

Alexander Spangher, Nanyun Peng, Jonathan May et al.

News articles are driven by the informational sources journalists use in reporting. Modeling when, how and why sources get used together in stories can help us better understand the information we consume and even help journalists with the task of producing it. In this work, we take steps toward this goal by constructing the largest and widest-ranging annotated dataset, to date, of informational sources used in news writing. We show that our dataset can be used to train high-performing models for information detection and source attribution. We further introduce a novel task, source prediction, to study the compositionality of sources in news articles. We show good performance on this task, which we argue is an important proof for narrative science exploring the internal structure of news articles and aiding in planning-based language generation, and an important step towards a source-recommendation system to aid journalists.

Julie Jiang, Kristina Lerman, Emilio Ferrara

While developments in machine learning led to impressive performance gains on big data, many human subjects data are, in actuality, small and sparsely labeled. Existing methods applied to such data often do not easily generalize to out-of-sample subjects. Instead, models must make predictions on test data that may be drawn from a different distribution, a problem known as \textit{zero-shot learning}. To address this challenge, we develop an end-to-end framework using a meta-learning approach, which enables the model to rapidly adapt to a new prediction task with limited training data for out-of-sample test data. We use three real-world small-scale human subjects datasets (two randomized control studies and one observational study), for which we predict treatment outcomes for held-out treatment groups. Our model learns the latent treatment effects of each intervention and, by design, can naturally handle multi-task predictions. We show that our model performs the best holistically for each held-out group and especially when the test group is distinctly different from the training group. Our model has implications for improved generalization of small-size human studies to the wider population.

Karishma Sharma, Emilio Ferrara, Yan Liu

Malicious accounts spreading misinformation has led to widespread false and misleading narratives in recent times, especially during the COVID-19 pandemic, and social media platforms struggle to eliminate these contents rapidly. This is because adapting to new domains requires human intensive fact-checking that is slow and difficult to scale. To address this challenge, we propose to leverage news-source credibility labels as weak labels for social media posts and propose model-guided refinement of labels to construct large-scale, diverse misinformation labeled datasets in new domains. The weak labels can be inaccurate at the article or social media post level where the stance of the user does not align with the news source or article credibility. We propose a framework to use a detection model self-trained on the initial weak labels with uncertainty sampling based on entropy in predictions of the model to identify potentially inaccurate labels and correct for them using self-supervision or relabeling. The framework will incorporate social context of the post in terms of the community of its associated user for surfacing inaccurate labels towards building a large-scale dataset with minimum human effort. To provide labeled datasets with distinction of misleading narratives where information might be missing significant context or has inaccurate ancillary details, the proposed framework will use the few labeled samples as class prototypes to separate high confidence samples into false, unproven, mixture, mostly false, mostly true, true, and debunk information. The approach is demonstrated for providing a large-scale misinformation dataset on COVID-19 vaccines.

Yahya H. Ezzeldin, Shen Yan, Chaoyang He et al.

Training ML models which are fair across different demographic groups is of critical importance due to the increased integration of ML in crucial decision-making scenarios such as healthcare and recruitment. Federated learning has been viewed as a promising solution for collaboratively training machine learning models among multiple parties while maintaining the privacy of their local data. However, federated learning also poses new challenges in mitigating the potential bias against certain populations (e.g., demographic groups), as this typically requires centralized access to the sensitive information (e.g., race, gender) of each datapoint. Motivated by the importance and challenges of group fairness in federated learning, in this work, we propose FairFed, a novel algorithm for fairness-aware aggregation to enhance group fairness in federated learning. Our proposed approach is server-side and agnostic to the applied local debiasing thus allowing for flexible use of different local debiasing methods across clients. We evaluate FairFed empirically versus common baselines for fair ML and federated learning, and demonstrate that it provides fairer models particularly under highly heterogeneous data distributions across clients. We also demonstrate the benefits of FairFed in scenarios involving naturally distributed real-life data collected from different geographical locations or departments within an organization.

Karishma Sharma, Emilio Ferrara, Yan Liu

Identifying and characterizing disinformation in political discourse on social media is critical to ensure the integrity of elections and democratic processes around the world. Persistent manipulation of social media has resulted in increased concerns regarding the 2020 U.S. Presidential Election, due to its potential to influence individual opinions and social dynamics. In this work, we focus on the identification of distorted facts, in the form of unreliable and conspiratorial narratives in election-related tweets, to characterize discourse manipulation prior to the election. We apply a detection model to separate factual from unreliable (or conspiratorial) claims analyzing a dataset of 242 million election-related tweets. The identified claims are used to investigate targeted topics of disinformation, and conspiracy groups, most notably the far-right QAnon conspiracy group. Further, we characterize account engagements with unreliable and conspiracy tweets, and with the QAnon conspiracy group, by political leaning and tweet types. Finally, using a regression discontinuity design, we investigate whether Twitter's actions to curb QAnon activity on the platform were effective, and how QAnon accounts adapt to Twitter's restrictions.

Alexander Spangher, Nanyun Peng, Jonathan May et al.

Journalists publish statements provided by people, or \textit{sources} to contextualize current events, help voters make informed decisions, and hold powerful individuals accountable. In this work, we construct an ontological labeling system for sources based on each source's \textit{affiliation} and \textit{role}. We build a probabilistic model to infer these attributes for named sources and to describe news articles as mixtures of these sources. Our model outperforms existing mixture modeling and co-clustering approaches and correctly infers source-type in 80\% of expert-evaluated trials. Such work can facilitate research in downstream tasks like opinion and argumentation mining, representing a first step towards machine-in-the-loop \textit{computational journalism} systems.

Alexander Spangher, Nanyun Peng, Jonathan May et al.

Journalists obtain "leads", or story ideas, by reading large corpora of government records: court cases, proposed bills, etc. However, only a small percentage of such records are interesting documents. We propose a model of "newsworthiness" aimed at surfacing interesting documents. We train models on automatically labeled corpora -- published newspaper articles -- to predict whether each article was a front-page article (i.e., \textbf{newsworthy}) or not (i.e., \textbf{less newsworthy}). We transfer these models to unlabeled corpora -- court cases, bills, city-council meeting minutes -- to rank documents in these corpora on "newsworthiness". A fine-tuned RoBERTa model achieves .93 AUC performance on heldout labeled documents, and .88 AUC on expert-validated unlabeled corpora. We provide interpretation and visualization for our models.

Julie Jiang, Kristina Lerman, Emilio Ferrara

Individual behavior and decisions are substantially influenced by their contexts, such as location, environment, and time. Changes along these dimensions can be readily observed in Multiplayer Online Battle Arena games (MOBA), where players face different in-game settings for each match and are subject to frequent game patches. Existing methods utilizing contextual information generalize the effect of a context over the entire population, but contextual information tailored to each individual can be more effective. To achieve this, we present the Neural Individualized Context-aware Embeddings (NICE) model for predicting user performance and game outcomes. Our proposed method identifies individual behavioral differences in different contexts by learning latent representations of users and contexts through non-negative tensor factorization. Using a dataset from the MOBA game League of Legends, we demonstrate that our model substantially improves the prediction of winning outcome, individual user performance, and user engagement.

Chris J. Kennedy, Julia Vassey, Ho-Chun Herbert Chang et al.

The U.S. Food & Drug Administration (FDA) requires that e-cigarette advertisements include a prominent warning label that reminds consumers that nicotine is addictive. However, the high volume of vaping-related posts on social media makes compliance auditing expensive and time-consuming, suggesting that an automated, scalable method is needed. We sought to develop and evaluate a deep learning system designed to automatically determine if an Instagram post promotes vaping, and if so, if an FDA-compliant warning label was included or if a non-compliant warning label was visible in the image. We compiled and labeled a dataset of 4,363 Instagram images, of which 44% were vaping-related, 3% contained FDA-compliant warning labels, and 4% contained non-compliant labels. Using a 20% test set for evaluation, we tested multiple neural network variations: image processing backbone model (Inceptionv3, ResNet50, EfficientNet), data augmentation, progressive layer unfreezing, output bias initialization designed for class imbalance, and multitask learning. Our final model achieved an area under the curve (AUC) and [accuracy] of 0.97 [92%] on vaping classification, 0.99 [99%] on FDA-compliant warning labels, and 0.94 [97%] on non-compliant warning labels. We conclude that deep learning models can effectively identify vaping posts on Instagram and track compliance with FDA warning label requirements.

Ankith Mohan, Aiichiro Nakano, Emilio Ferrara

We propose a model-agnostic pipeline to recover graph signals from an expert system by exploiting the content addressable memory property of restricted Boltzmann machine and the representational ability of a neural network. The proposed pipeline requires the deep neural network that is trained on a downward machine learning task with clean data, data which is free from any form of corruption or incompletion. We show that denoising the representations learned by the deep neural networks is usually more effective than denoising the data itself. Although this pipeline can deal with noise in any dataset, it is particularly effective for graph-structured datasets.

Samar Haider, Luca Luceri, Ashok Deb et al.

Social media have been deliberately used for malicious purposes, including political manipulation and disinformation. Most research focuses on high-resource languages. However, malicious actors share content across countries and languages, including low-resource ones. Here, we investigate whether and to what extent malicious actors can be detected in low-resource language settings. We discovered that a high number of accounts posting in Tagalog were suspended as part of Twitter's crackdown on interference operations after the 2016 US Presidential election. By combining text embedding and transfer learning, our framework can detect, with promising accuracy, malicious users posting in Tagalog without any prior knowledge or training on malicious content in that language. We first learn an embedding model for each language, namely a high-resource language (English) and a low-resource one (Tagalog), independently. Then, we learn a mapping between the two latent spaces to transfer the detection model. We demonstrate that the proposed approach significantly outperforms state-of-the-art models, including BERT, and yields marked advantages in settings with very limited training data -- the norm when dealing with detecting malicious activity in online platforms.

Akira Matsui, Emilio Ferrara, Fred Morstatter et al.

Crowdwork often entails tackling cognitively-demanding and time-consuming tasks. Crowdsourcing can be used for complex annotation tasks, from medical imaging to geospatial data, and such data powers sensitive applications, such as health diagnostics or autonomous driving. However, the existence and prevalence of underperforming crowdworkers is well-recognized, and can pose a threat to the validity of crowdsourcing. In this study, we propose the use of a computational framework to identify clusters of underperforming workers using clickstream trajectories. We focus on crowdsourced geopolitical forecasting. The framework can reveal different types of underperformers, such as workers with forecasts whose accuracy is far from the consensus of the crowd, those who provide low-quality explanations for their forecasts, and those who simply copy-paste their forecasts from other users. Our study suggests that clickstream clustering and analysis are fundamental tools to diagnose the performance of crowdworkers in platforms leveraging the wisdom of crowds.

Yilei Zeng, Deren Lei, Beichen Li et al.

Sequential reasoning is a complex human ability, with extensive previous research focusing on gaming AI in a single continuous game, round-based decision makings extending to a sequence of games remain less explored. Counter-Strike: Global Offensive (CS:GO), as a round-based game with abundant expert demonstrations, provides an excellent environment for multi-player round-based sequential reasoning. In this work, we propose a Sequence Reasoner with Round Attribute Encoder and Multi-Task Decoder to interpret the strategies behind the round-based purchasing decisions. We adopt few-shot learning to sample multiple rounds in a match, and modified model agnostic meta-learning algorithm Reptile for the meta-learning loop. We formulate each round as a multi-task sequence generation problem. Our state representations combine action encoder, team encoder, player features, round attribute encoder, and economy encoders to help our agent learn to reason under this specific multi-player round-based scenario. A complete ablation study and comparison with the greedy approach certify the effectiveness of our model. Our research will open doors for interpretable AI for understanding episodic and long-term purchasing strategies beyond the gaming community.

Keith Burghardt, Nazgol Tavabi, Emilio Ferrara et al.

Life events can dramatically affect our psychological state and work performance. Stress, for example, has been linked to professional dissatisfaction, increased anxiety, and workplace burnout. We explore the impact of positive and negative life events on a number of psychological constructs through a multi-month longitudinal study of hospital and aerospace workers. Through causal inference, we demonstrate that positive life events increase positive affect, while negative events increase stress, anxiety and negative affect. While most events have a transient effect on psychological states, major negative events, like illness or attending a funeral, can reduce positive affect for multiple days. Next, we assess whether these events can be detected through wearable sensors, which can cheaply and unobtrusively monitor health-related factors. We show that these sensors paired with embedding-based learning models can be used ``in the wild'' to capture atypical life events in hundreds of workers across both datasets. Overall our results suggest that automated interventions based on physiological sensing may be feasible to help workers regulate the negative effects of life events.

Akira Matsui, Teruyoshi Kobayashi, Daisuke Moriwaki et al.

Understanding consumer behavior is an important task, not only for developing marketing strategies but also for the management of economic policies. Detecting consumption patterns, however, is a high-dimensional problem in which various factors that would affect consumers' behavior need to be considered, such as consumers' demographics, circadian rhythm, seasonal cycles, etc. Here, we develop a method to extract multi-timescale expenditure patterns of consumers from a large dataset of scanned receipts. We use a non-negative tensor factorization (NTF) to detect intra- and inter-week consumption patterns at one time. The proposed method allows us to characterize consumers based on their consumption patterns that are correlated over different timescales.

Karel Mundnich, Brandon M. Booth, Michelle L'Hommedieu et al.

We present a novel longitudinal multimodal corpus of physiological and behavioral data collected from direct clinical providers in a hospital workplace. We designed the study to investigate the use of off-the-shelf wearable and environmental sensors to understand individual-specific constructs such as job performance, interpersonal interaction, and well-being of hospital workers over time in their natural day-to-day job settings. We collected behavioral and physiological data from $n = 212$ participants through Internet-of-Things Bluetooth data hubs, wearable sensors (including a wristband, a biometrics-tracking garment, a smartphone, and an audio-feature recorder), together with a battery of surveys to assess personality traits, behavioral states, job performance, and well-being over time. Besides the default use of the data set, we envision several novel research opportunities and potential applications, including multi-modal and multi-task behavioral modeling, authentication through biometrics, and privacy-aware and privacy-preserving machine learning.

Luca Luceri, Silvia Giordano, Emilio Ferrara

Since the 2016 US Presidential election, social media abuse has been eliciting massive concern in the academic community and beyond. Preventing and limiting the malicious activity of users, such as trolls and bots, in their manipulation campaigns is of paramount importance for the integrity of democracy, public health, and more. However, the automated detection of troll accounts is an open challenge. In this work, we propose an approach based on Inverse Reinforcement Learning (IRL) to capture troll behavior and identify troll accounts. We employ IRL to infer a set of online incentives that may steer user behavior, which in turn highlights behavioral differences between troll and non-troll accounts, enabling their accurate classification. As a study case, we consider the troll accounts identified by the US Congress during the investigation of Russian meddling in the 2016 US Presidential election. We report promising results: the IRL-based approach is able to accurately detect troll accounts (AUC=89.1%). The differences in the predictive features between the two classes of accounts enables a principled understanding of the distinctive behaviors reflecting the incentives trolls and non-trolls respond to.