Fred Morstatter

The shrinking landscape of linguistic diversity in the age of large language models

Zhivar Sourati, Farzan Karimi-Malekabadi, Meltem Ozcan, Colin McDaniel et autres

us (code pays fourni par la source)

Causal Language in Post Titles Shapes Deeper Topological Structures of Online Conversations

Zhuoyu Shi, Fred Morstatter

Causal reasoning is fundamental to human understanding and information organization. People prefer causal explanations because they offer coherence, predictability, and a sense of control. Conversational structures shape how knowledge and perspectives are shared, validated, and amplified in networked publics. Understanding the structural …

Gender Attribution in Causal Beliefs

Zhuoyu Shi, Fred Morstatter

For centuries, women have been cast as the source of harm in public narratives, from witch hunts in early modern Europe to contemporary stereotypes about emotional instability. These cultural patterns reflect enduring biases in how people attribute causality and assign blame, often …

TRIBE: Predicting Team Performance via Communication Behavior Ensembles

Ali Jalal-Kamali, Nikolos Gurney, David V. Pynadath, Fred Morstatter

Designing autonomous agents that effectively assist human teams hinges on understanding team dynamics, often without task specific knowledge. We present TRIBE, a domain independent approach that reveals team behavioral dynamics invisible to traditional performance metrics. We show that communication patterns can categorize …

TRIBE: Predicting Team Performance via Communication Behavior Ensembles

Ali Jalal-Kamali, Nikolos Gurney, David V. Pynadath, Fred Morstatter

Designing autonomous agents that effectively assist human teams hinges on understanding team dynamics, often without task specific knowledge. We present TRIBE, a domain independent approach that reveals team behavioral dynamics invisible to traditional performance metrics. We show that communication patterns can categorize …

us, dk (code pays fourni par la source)

On the Role of Anticausal Direction in LLM-based Data Synthesis

Bohan Jiang, Pingchuan Ma, Zhen Tan, Zhuoyu Shi et autres

Large Language Models (LLMs) are increasingly used to generate synthetic data. Most LLM-based data synthesis workflows are anticausal : the user injects Y into the prompt to enforce targeted generation of X (Y\rightarrow X). This anticausal direction seems contradictory to the natural …

us (code pays fourni par la source)

Forecasting the impact of the viral ‘Kia Boys’ social media trend on car thefts to 2050

P. Jeffrey Brantingham, Craig D. Uchida, Fred Morstatter, George Mohler

In 2022, Hyundai Sonatas became the most frequently stolen car model in Los Angeles, mirroring a nationwide trend. The sudden popularity of this mid-sized sedan among car thieves has, according to some, been linked to the viral spread of videos on TikTok …

us (code pays fourni par la source)

Changes in the Reproduction Number of Mass Shootings in the United States Following the COVID-19 Pandemic

Sarah Oliver, Sarah Penrice, P. Jeffrey Brantingham, Fred Morstatter et autres

The rate of mass shootings in the US has increased since the start of the COVID-19 pandemic; however, the mechanisms behind the increase are not well understood. We explore the extent to which the reproduction number, or contagiousness, of mass shootings has …

Innovations In Machine Assessment Of Replicability

Sarah Rajtmajer, Laxmaan Balaji, D. M. Benjamin, James Caverlee et autres

Automated methods for the assessment of replicability of scientific claims offer a scalable complement to replication studies and traditional peer review. Drawing on a large dataset of claims, human judgments, and a limited set of replication outcomes, we developed and evaluated three …

us (code pays fourni par la source)

Assessments of Credibility in the Social and Behavioral Sciences

Anna Lou Abatayo, Titipat Achakulvisut, Daniel E. Acuña, Balazs Aczel et autres

Credibility assessment — determining whether research findings are trustworthy or believable — is essential to the research process. One aspect of credibility is repeatability, which includes assessing whether consistent results are obtained when using new data to answer the same question (replicability), …

us (code pays fourni par la source)

Assessments of Credibility in the Social and Behavioral Sciences

Isabella Mandema, Anthony M. Kwasnica, Nishanth Sridhar Nakshatri, Morteza Dehghani et autres

Credibility assessment — determining whether research findings are trustworthy or believable — is essential to the research process. One aspect of credibility is repeatability, which includes assessing whether consistent results are obtained when using new data to answer the same question (replicability), …

On Causal and Anticausal LLM-based Data Synthesis

Bohan Jiang, Zhuoyu Shi, Fred Morstatter, Adrienne Raglin et autres

While Large Language Models (LLMs) have been increasingly used to generate synthetic data for various downstream tasks, researchers overlook the causal direction in the data synthesis process. A natural causal direction should contain two steps: diverse raw data are generated first, and …

us (code pays fourni par la source)