arXiv subjects

Peter Sheridan Dodds

Publications and source records attributed to Peter Sheridan Dodds.

At least 37 records · Page 2Linked to original sources

arXiv2026

Global brain drain and gain in high-potential student mobility

The mobility of high-potential individuals, particularly graduates from elite academic institutions, serves as a critical driver of global innovation and economic development. Despite its importance, granular data on the specific trajectories and demographic drivers of these flows remain scarce in traditional administrative sources. In this study, we leverage anonymized, aggregate-level digital trace data from the LinkedIn Advertising platform to map the international mobility of graduates from 1,504 QS-ranked universities across 102 countries. We find that global talent flows are highly concentrated, with the United States capturing 38.4\% of the mobile elite, followed by the United Kingdom (7.9\%) and Canada (6.8\%), while regional hubs like the United Arab Emirates (5.2\%) have emerged as significant talent magnets. Our analysis reveals a global Relative Gender Gap (RGG) of +3.16\%, indicating a modest male overrepresentation that varies sharply by destination, from extreme male skews in Ethiopia (+60.34\%) to female overrepresentation in Armenia ($-$30.77\%). Professional integration is highly structured; while Business Development and Operations are universal entry channels, technical specialization in Engineering and IT is concentrated in specific innovation hubs. Destination ``pull'' is primarily driven by economic capacity, institutional stability, and educational infrastructure, though female graduates demonstrate significantly higher sensitivity to the cost of living. These findings provide a high-resolution lens on the global ``brain circulation,'' highlighting the destination-specific comparative advantages that govern high-skilled relocation.

cs.CY↗

arXiv2026

False memories to fake news: The evolution of the term "misinformation" in academic literature

Since 2016, the term "misinformation" has become associated with a scientific paradigm that studies, at its core, people making, reading, and sharing false statements, usually on social media, and often warning of the harm to society resulting from the sum of many such events. By tracking the term through the academic literature, with special focus on the years 2011--2023, we connect the post-2016 paradigm with a strand of research dating to the Satanic panic of the 1980s. We argue that post-2016 misinformation research owes more to this intellectual lineage than is generally acknowledged, and we discuss the theoretical and practical implications of this connection. We conclude by drawing parallels between the Satanic panic and 2026, and, similarly, between misinformation research then and now.

cs.SI↗

arXiv2026

Identifying Body Composition Measures That Correlate with Self-Compassion and Social Support

This study explores the relationship between body composition metrics, self-compassion, and social support among college students. Using seasonal body composition data from the InBody770 system and psychometric measures from the Lived Experiences Measured Using Rings Study (LEMURS) (n=156; freshmen=66, sophomores=90), Canonical Correlation Analysis (CCA) reveals body composition metrics exhibit moderate correlation with self-compassion and social support. Certain physiological and psychological features showed strong and consistent relationships with well-being across the academic year. Trunk and leg impedance stood out as key physiological indicators, while mindfulness, over-identification, affectionate support, and tangible support emerged as recurring psychological and social correlates. This demonstrates that body composition metrics can serve as valuable biomarkers for indicating self-perceived psychosocial well-being, offering insights for future research on scalable mental health modeling and intervention strategies.

cs.CY↗

arXiv2025

Us-vs-Them bias in Large Language Models

This study investigates ``us versus them'' bias, as described by Social Identity Theory, in large language models (LLMs) under both default and persona-conditioned settings across multiple architectures (GPT-4.1, DeepSeek-3.1, Gemma-2.0, Grok-3.0, and LLaMA-3.1). Using sentiment dynamics, allotaxonometry, and embedding regression, we find consistent ingroup-positive and outgroup-negative associations across foundational LLMs. We find that adopting a persona systematically alters models' evaluative and affiliative language patterns. For the exemplar personas examined, conservative personas exhibit greater outgroup hostility, whereas liberal personas display stronger ingroup solidarity. Persona conditioning produces distinct clustering in embedding space and measurable semantic divergence, supporting the view that even abstract identity cues can shift models' linguistic behavior. Furthermore, outgroup-targeted prompts increased hostility bias by 1.19--21.76\% across models. These findings suggest that LLMs learn not only factual associations about social groups but also internalize and reproduce distinct ways of being, including attitudes, worldviews, and cognitive styles that are activated when enacting personas. We interpret these results as evidence of a multi-scale coupling between local context (e.g., the persona prompt), localizable representations (what the model ``knows''), and global cognitive tendencies (how it ``thinks''), which are at least reflected in the training data. Finally, we demonstrate ION, an ``us versus them'' bias mitigation approach using fine-tuning and direct preference optimization (DPO), which reduces sentiment divergence by up to 69\%, highlighting the potential for targeted mitigation strategies in future LLM development.

cs.CY↗

arXiv2025

Misalignment of LLM-Generated Personas with Human Perceptions in Low-Resource Settings

Recent advances enable Large Language Models (LLMs) to generate AI personas, yet their lack of deep contextual, cultural, and emotional understanding poses a significant limitation. This study quantitatively compared human responses with those of eight LLM-generated social personas (e.g., Male, Female, Muslim, Political Supporter) within a low-resource environment like Bangladesh, using culturally specific questions. Results show human responses significantly outperform all LLMs in answering questions, and across all matrices of persona perception, with particularly large gaps in empathy and credibility. Furthermore, LLM-generated content exhibited a systematic bias along the lines of the ``Pollyanna Principle'', scoring measurably higher in positive sentiment ($Φ_{avg} = 5.99$ for LLMs vs. $5.60$ for Humans). These findings suggest that LLM personas do not accurately reflect the authentic experience of real people in resource-scarce environments. It is essential to validate LLM personas against real-world human data to ensure their alignment and reliability before deploying them in social science research.

cs.CY↗

arXiv2025

LLMs for Low-Resource Dialect Translation Using Context-Aware Prompting: A Case Study on Sylheti

Large Language Models (LLMs) have demonstrated strong translation abilities through prompting, even without task-specific training. However, their effectiveness in dialectal and low-resource contexts remains underexplored. This study presents the first systematic investigation of LLM-based machine translation (MT) for Sylheti, a dialect of Bangla that is itself low-resource. We evaluate five advanced LLMs (GPT-4.1, GPT-4.1, LLaMA 4, Grok 3, and DeepSeek V3.2) across both translation directions (Bangla $\Leftrightarrow$ Sylheti), and find that these models struggle with dialect-specific vocabulary. To address this, we introduce Sylheti-CAP (Context-Aware Prompting), a three-step framework that embeds a linguistic rulebook, a dictionary (2{,}260 core vocabulary items and idioms), and an authenticity check directly into prompts. Extensive experiments show that Sylheti-CAP consistently improves translation quality across models and prompting strategies. Both automatic metrics and human evaluations confirm its effectiveness, while qualitative analysis reveals notable reductions in hallucinations, ambiguities, and awkward phrasing, establishing Sylheti-CAP as a scalable solution for dialectal and low-resource MT. Dataset link: \href{https://github.com/TabiaTanzin/LLMs-for-Low-Resource-Dialect-Translation-Using-Context-Aware-Prompting-A-Case-Study-on-Sylheti.git}{https://github.com/TabiaTanzin/LLMs-for-Low-Resource-Dialect-Translation-Using-Context-Aware-Prompting-A-Case-Study-on-Sylheti.git}

cs.CL↗

arXiv2025

One pathogen does not an epidemic make: A review of interacting contagions, diseases, beliefs, and stories

From pathogens and computer viruses to genes and memes, contagion models have found widespread utility across the natural and social sciences. Despite their success and breadth of adoption, the approach and structure of these models remain surprisingly siloed by field. Given the siloed nature of their development and widespread use, one persistent assumption is that a given contagion can be studied in isolation, independently from what else might be spreading in the population. In reality, countless contagions of biological and social nature interact within hosts (interacting with existing beliefs, or the immune system) and across hosts (interacting in the environment, or affecting transmission mechanisms). Additionally, from a modeling perspective, we know that relaxing these assumptions has profound effects on the physics and translational implications of the models. Here, we review mechanisms for interactions in social and biological contagions, as well as the models and frameworks developed to include these interactions in the study of the contagions. We highlight existing problems related to the inference of interactions and to the scalability of mathematical models and identify promising avenues of future inquiries. In doing so, we highlight the need for interdisciplinary efforts under a unified science of contagions and for removing a common dichotomy between social and biological contagions.

physics.soc-ph↗

arXiv2025

The Three Books of Science

We venture that the long evolution of science may be viewed as unfolding over three blurred epochs. The first epoch spans the slow, haphazard, error-ridden realization of scientific truths along with foundational scientific methods. The second epoch covers the discovery that everything is formed from atoms and other building blocks. And in the age of computation, the third epoch affords the science of complex systems.

physics.soc-ph↗

arXiv2025

Detecting sub-populations in online health communities: A mixed-methods exploration of breastfeeding messages in BabyCenter Birth Clubs

Parental stress is a nationwide health crisis according to the U.S. Surgeon General's 2024 advisory. To allay stress, expecting parents seek advice and share experiences in a variety of venues, from in-person birth education classes and parenting groups to virtual communities, for example, BabyCenter, a moderated online forum community with over 4 million members in the United States alone. In this study, we aim to understand how parents talk about pregnancy, birth, and parenting by analyzing 5.43M posts and comments from the April 2017--January 2024 cohort of 331,843 BabyCenter "birth club" users (that is, users who participate in due date forums or "birth clubs" based on their babies' due dates). Using BERTopic to locate breastfeeding threads and LDA to summarize themes, we compare documents in breastfeeding threads to all other birth-club content. Analyzing time series of word rank, we find that posts and comments containing anxiety-related terms increased steadily from April 2017 to January 2024. We used an ensemble of topic models to identify dominant breastfeeding topics within birth clubs, and then explored trends among all user content versus those who posted in threads related to breastfeeding topics. We conducted Latent Dirichlet Allocation (LDA) topic modeling to identify the most common topics in the full population, as well as within the subset breastfeeding population. We find that the topic of sleep dominates in content generated by the breastfeeding population, as well anxiety-related and work/daycare topics that are not predominant in the full BabyCenter birth club dataset.

cs.SI↗

arXiv2025

Story and essential meaning dynamics in Bangladesh's July 2024 Student-People's Uprising

News media serves a crucial role in disseminating information and shaping public perception, especially during periods of political unrest. Using over 50,0000 YouTube comments on news coverage from July 16 to August 6, 2024, we investigate the emotional dynamics and evolving discourse of public perception during the July 2024 Student-People's Uprising in Bangladesh. Through integrated analyses of sentiment, emotion, topic, lexical discourse, timeline progression, sentiment shifts, and allotaxonometry, we show how negative sentiment dominated during the movement. We find a negative correlation between comment happiness and number of protest deaths $(r = -0.45,\p = 0.00)$. Using an ousiometer to measure essential meaning, we find public responses reflect a landscape of power, aggression, and danger, alongside persistent expressions of hope, moral conviction, and empowerment through goodnesses. Topic discourse progressed during the movement, with peaks in `Political Conflict', `Media Flow', and `Student Violence' during crisis surges, while topics like `Social Resistance' and `Digital Movement' persisted amid repression. Sentiment shifts reveal that after the second internet blackout, average happiness increased, driven by the more frequent use of positive words such as `victory', `peace' and `freedom' and a decrease in negative terms such as `death' and `lies'. Finally, through allotaxonometric analysis, we observe a clear shift from protest to justice.

cs.CY↗

arXiv2025

BanglaMATH : A Bangla benchmark dataset for testing LLM mathematical reasoning at grades 6, 7, and 8

Large Language Models (LLMs) have tremendous potential to play a key role in supporting mathematical reasoning, with growing use in education and AI research. However, most existing benchmarks are limited to English, creating a significant gap for low-resource languages. For example, Bangla is spoken by nearly 250 million people who would collectively benefit from LLMs capable of native fluency. To address this, we present BanglaMATH, a dataset of 1.7k Bangla math word problems across topics such as Arithmetic, Algebra, Geometry, and Logical Reasoning, sourced from Bangla elementary school workbooks and annotated with details like grade level and number of reasoning steps. We have designed BanglaMATH to evaluate the mathematical capabilities of both commercial and open-source LLMs in Bangla, and we find that Gemini 2.5 Flash and DeepSeek V3 are the only models to achieve strong performance, with $\ge$ 80\% accuracy across three elementary school grades. Furthermore, we assess the robustness and language bias of these top-performing LLMs by augmenting the original problems with distracting information, and translating the problems into English. We show that both LLMs fail to maintain robustness and exhibit significant performance bias in Bangla. Our study underlines current limitations of LLMs in handling arithmetic and mathematical reasoning in low-resource languages, and highlights the need for further research on multilingual and equitable mathematical understanding. Dataset link: \href{https://github.com/TabiaTanzin/BanglaMATH-A-Bangla-benchmark-dataset-for-testing-LLM-mathematical-reasoning-at-grades-6-7-and-8.git}{https://github.com/BanglaMATH}

cs.CY↗

arXiv2025

A suite of allotaxonometric tools for the comparison of complex systems using rank-turbulence divergence

Describing and comparing complex systems requires principled, theoretically grounded tools. Built around the phenomenon of type turbulence, allotaxonographs provide map-and-list visual comparisons of pairs of heavy-tailed distributions. Allotaxonographs are designed to accommodate a wide range of instruments including rank- and probability-turbulence divergences, Jenson-Shannon divergence, and generalized entropy divergences. Here, we describe a suite of programmatic tools for rendering allotaxonographs for rank-turbulence divergence in Matlab, Javascript, and Python, all of which have different use cases.

cs.CL↗

arXiv2025

Aim High, Stay Private: Differentially Private Synthetic Data Enables Public Release of Behavioral Health Information with High Utility

Sharing health and behavioral data raises significant privacy concerns, as conventional de-identification methods are susceptible to privacy attacks. Differential Privacy (DP) provides formal guarantees against re-identification risks, but practical implementation necessitates balancing privacy protection and the utility of data. We demonstrate the use of DP to protect individuals in a real behavioral health study, while making the data publicly available and retaining high utility for downstream users of the data. We use the Adaptive Iterative Mechanism (AIM) to generate DP synthetic data for Phase 1 of the Lived Experiences Measured Using Rings Study (LEMURS). The LEMURS dataset comprises physiological measurements from wearable devices (Oura rings) and self-reported survey data from first-year college students. We evaluate the synthetic datasets across a range of privacy budgets, epsilon = 1 to 100, focusing on the trade-off between privacy and utility. We evaluate the utility of the synthetic data using a framework informed by actual uses of the LEMURS dataset. Our evaluation identifies the trade-off between privacy and utility across synthetic datasets generated with different privacy budgets. We find that synthetic data sets with epsilon = 5 preserve adequate predictive utility while significantly mitigating privacy risks. Our methodology establishes a reproducible framework for evaluating the practical impacts of epsilon on generating private synthetic datasets with numerous attributes and records, contributing to informed decision-making in data sharing practices.

cs.CR↗

arXiv2025

Curating corpora with classifiers: A case study of clean energy sentiment online

Well curated, large-scale corpora of social media posts containing broad public opinion offer an alternative data source to complement traditional surveys. While surveys are effective at collecting representative samples and are capable of achieving high accuracy, they can be both expensive to run and lag public opinion by days or weeks. Both of these drawbacks could be overcome with a real-time, high volume data stream and fast analysis pipeline. A central challenge in orchestrating such a data pipeline is devising an effective method for rapidly selecting the best corpus of relevant documents for analysis. Querying with keywords alone often includes irrelevant documents that are not easily disambiguated with bag-of-words natural language processing methods. Here, we explore methods of corpus curation to filter irrelevant tweets using pre-trained transformer-based models, fine-tuned for our binary classification task on hand-labeled tweets. We are able to achieve F1 scores of up to 0.95. The low cost and high performance of fine-tuning such a model suggests that our approach could be of broad benefit as a pre-processing step for social media datasets with uncertain corpus boundaries.

cs.CL↗

arXiv2024

Collective sleep and activity patterns of college students from wearable devices

To optimize interventions for improving wellness, it is essential to understand habits, which wearable devices can measure with greater precision. Using high temporal resolution biometric data taken from the Oura Gen3 ring, we examine daily and weekly sleep and activity patterns of a cohort of young adults (N=582) in their first semester of college. A high compliance rate is observed for both daily and nightly wear, with slight dips in wear compliance observed shortly after waking up and also in the evening. Most students have a late-night chronotype with a median midpoint of sleep at 5AM, with males and those with mental health impairment having more delayed sleep periods. Social jetlag, or the difference in sleep times between free days and school days, is prevalent in our sample. While sleep periods generally shift earlier on weekdays and later on weekends, sleep duration on both weekdays and weekends is shorter than during prolonged school breaks, suggesting chronic sleep debt when school is in session. Synchronized spikes in activity consistent with class schedules are also observed, suggesting that walking in between classes is a widespread behavior in our sample that substantially contributes to physical activity. Lower active calorie expenditure is associated with weekends and a delayed but longer sleep period the night before, suggesting that for our cohort, active calorie expenditure is affected less by deviations from natural circadian rhythms and more by the timing associated with activities. Our study shows that regular sleep and activity routines may be inferred from consumer wearable devices if high temporal resolution and long data collection periods are available.

cs.CY↗

arXiv2024

Hollywood's misrepresentation of death: A comparison of overall and by-gender mortality causes in film and the real world

The common phrase 'representation matters' asserts that media has a measurable and important impact on civic society's perception of self and others. The representation of health in media, in particular, may reflect and perpetuate a society's disease burden. Here, for the top 10 major causes of death in the United States, we examine how cinematic representation of overall and by-gender mortality diverges from reality. Using crowd-sourced data on film deaths from Cinemorgue Wiki, we employ natural language processing (NLP) techniques to analyze shifts in representation of deaths in movies versus the 2021 National Vital Statistic Survey (NVSS) top ten mortality causes. Overall, movies strongly overrepresent suicide and, to a lesser degree, accidents. In terms of gender, movies overrepresent men and underrepresent women for nearly every major mortality cause, including heart disease and cerebrovascular disease. The two exceptions for which women are overrepresented are suicide and accidents. We discuss the implications of under- and over-representing causes of death overall and by gender, as well as areas of future research.

cs.CY↗

arXiv2024

A blind spot for large language models: Supradiegetic linguistic information

Large Language Models (LLMs) like ChatGPT reflect profound changes in the field of Artificial Intelligence, achieving a linguistic fluency that is impressively, even shockingly, human-like. The extent of their current and potential capabilities is an active area of investigation by no means limited to scientific researchers. It is common for people to frame the training data for LLMs as "text" or even "language". We examine the details of this framing using ideas from several areas, including linguistics, embodied cognition, cognitive science, mathematics, and history. We propose that considering what it is like to be an LLM like ChatGPT, as Nagel might have put it, can help us gain insight into its capabilities in general, and in particular, that its exposure to linguistic training data can be productively reframed as exposure to the diegetic information encoded in language, and its deficits can be reframed as ignorance of extradiegetic information, including supradiegetic linguistic information. Supradiegetic linguistic information consists of those arbitrary aspects of the physical form of language that are not derivable from the one-dimensional relations of context -- frequency, adjacency, proximity, co-occurrence -- that LLMs like ChatGPT have access to. Roughly speaking, the diegetic portion of a word can be thought of as its function, its meaning, as the information in a theoretical vector in a word embedding, while the supradiegetic portion of the word can be thought of as its form, like the shapes of its letters or the sounds of its syllables. We use these concepts to investigate why LLMs like ChatGPT have trouble handling palindromes, the visual characteristics of symbols, translating Sumerian cuneiform, and continuing integer sequences.

cs.CL↗

arXiv2023

The Resume Paradox: Greater Language Differences, Smaller Pay Gaps

Over the past decade, the gender pay gap has remained steady with women earning 84 cents for every dollar earned by men on average. Many studies explain this gap through demand-side bias in the labor market represented through employers' job postings. However, few studies analyze potential bias from the worker supply-side. Here, we analyze the language in millions of US workers' resumes to investigate how differences in workers' self-representation by gender compare to differences in earnings. Across US occupations, language differences between male and female resumes correspond to 11% of the variation in gender pay gap. This suggests that females' resumes that are semantically similar to males' resumes may have greater wage parity. However, surprisingly, occupations with greater language differences between male and female resumes have lower gender pay gaps. A doubling of the language difference between female and male resumes results in an annual wage increase of $2,797 for the average female worker. This result holds with controls for gender-biases of resume text and we find that per-word bias poorly describes the variance in wage gap. The results demonstrate that textual data and self-representation are valuable factors for improving worker representations and understanding employment inequities.

physics.soc-ph↗