Poverty maps are essential tools for governments and NGOs to track socioeconomic changes and adequately allocate infrastructure and services in places in need. Sensor and online crowd-sourced data combined with machine learning methods have provided a recent breakthrough in poverty map inference. However, these methods do not capture local wealth fluctuations, and are not optimized to produce accountable results that guarantee accurate predictions to all sub-populations. Here, we propose a pipeline of machine learning models to infer the mean and standard deviation of wealth across multiple geographically clustered populated places, and illustrate their performance in Sierra Leone and Uganda. These models leverage seven independent and freely available feature sources based on satellite images, and metadata collected via online crowd-sourcing and social media. Our models show that combined metadata features are the best predictors of wealth in rural areas, outperforming image-based models, which are the best for predicting the highest wealth quintiles. Our results recover the local mean and variation of wealth, and correctly capture the positive yet non-monotonous correlation between them. We further demonstrate the capabilities and limitations of model transfer across countries and the effects of data recency and other biases. Our methodology provides open tools to build towards more transparent and interpretable models to help governments and NGOs to make informed decisions based on data availability, urbanization level, and poverty thresholds.
Jan Bachmann, Lisette Espín-Noboa, Gerardo Iñiguez et al.
Science is a collaborative endeavor in which "who collaborates with whom" profoundly influences scientists' career trajectories and success. Despite its relevance, little is known about how scholars facilitate new collaborations among their peers. In this study, we quantify brokerage in academia and study its effect on the careers of physicists worldwide. We find that early-career participation in brokerage increases later-stage involvement for all researchers, with increasing participation rates and greater career impact among more successful scientists. This cumulative advantage process suggests that brokerage contributes to the unequal distribution of success in academia. Surprisingly, this affects both women and men equally, despite women being more junior in all brokerage roles and lagging behind men's participation due to their late and slow arrival to physics. Because of its cumulative nature, promoting brokerage opportunities to early career scientists might help reduce the inequalities in academic success.
Annabella Sánchez-Guzmán, Lukas Eberhard, Denis Helic et al.
Large language models (LLMs) are increasingly used as scholar recommenders, shaping who is seen as an expert in academia. Existing audits remain English-centric, single discipline, and persona-agnostic, leaving the source of output variability poorly understood. To this end, we propose a benchmark that disentangles the effects of model choice and prompt design on recommendations. We audit 43 LLMs by varying persona prompts (language, location, role-and-task) and context (field, seniority, k). Recommended scholars are compared against Semantic Scholar over six scientific disciplines to measure technical quality (factuality, coverage) and social representativeness (diversity, parity). Basic technical quality is driven by model choice, factuality and parity by context, and diversity by location. South Africa prompts yield less factual lists, while Japan prompts yield highly factual but homogeneous lists skewed toward highly productive scholars. Prompt design is thus a non-trivial axis of LLM-based scholar discovery and should be systematically audited alongside model choice.
Mingrong She, Liuhuaying Yang, Ana Maria Jaramillo et al.
Disambiguating scholars with identical names is essential for accurate authorship assignment and robust large-scale scientometric research. Existing methods are often designed for Latin-script metadata and perform poorly on Chinese names. In international publications, Chinese names typically appear as Romanized Pinyin, which is highly ambiguous as it can map to multiple distinct characters. Chinese characters, in contrast, reduce but do not eliminate this ambiguity, and are rarely available in international records. To address both challenges, we propose a rule-based disambiguation framework that integrates co-authorship networks, citation networks, author affiliations, and content similarity. We apply this framework to 65,241 physics papers from the China National Knowledge Infrastructure (CNKI), spanning over 70 years of data. On a human annotated sample of 80 name pairs, our method achieves F1-scores of 0.88 for Pinyin names and 0.89 for character-based names, outperforming two baseline approaches, with improvements driven primarily by higher recall. The comparable performance across both writing systems shows that our approach is script-agnostic, enabling reliable large-scale scientometric analyses.
Jan Bachmann, Samuel Martin-Gutierrez, Lisette Espín-Noboa et al.
Inequalities in social networks arise from linking mechanisms, such as preferential attachment (connecting to popular nodes), homophily (connecting to similar others), and triadic closure (connecting through mutual contacts). While preferential attachment mainly drives degree inequality and homophily drives segregation, their three-way interaction remains understudied. This gap limits our understanding of how network inequalities emerge. Here, we introduce PATCH, a network growth model combining the three mechanisms to understand how they create disparities among two groups in synthetic networks. Extensive simulations confirm that homophily and preferential attachment increase segregation and degree inequalities, while triadic closure has countervailing effects: conditional on the other mechanisms, it amplifies population-wide degree inequality while reducing segregation and between-group degree disparities. We demonstrate PATCH's explanatory potential on fifty years of Physics and Computer Science collaboration and citation networks exhibiting persistent gender disparities. PATCH accounts for these gender disparities with the joint presence of preferential attachment, moderate gender homophily, and varying levels of triadic closure. By connecting mechanisms to observed inequalities, PATCH shows how their interplay sustains group disparities and provides a framework for designing interventions that promote more equitable social networks.
Poverty map inference has become a critical focus of research, utilizing both traditional and modern techniques, ranging from regression models to convolutional neural networks applied to tabular data, satellite imagery, and networks. While much attention has been given to validating models during the training phase, the final predictions have received less scrutiny. In this study, we analyze the International Wealth Index (IWI) predicted by Lee and Braithwaite (2022) and Espín-Noboa et al. (2023), alongside the Relative Wealth Index (RWI) inferred by Chi et al. (2022), across six Sub-Saharan African countries. Our analysis reveals trends and discrepancies in wealth predictions between these models. In particular, significant and unexpected discrepancies between the predictions of Lee and Braithwaite and Espín-Noboa et al., even after accounting for differences in training data. In contrast, the shape of the wealth distributions predicted by Espín-Noboa et al. and Chi et al. are more closely aligned, suggesting similar levels of skewness. These findings raise concerns about the validity of certain models and emphasize the importance of rigorous audits for wealth prediction algorithms used in policy-making. Continuous validation and refinement are essential to ensure the reliability of these models, particularly when they inform poverty alleviation strategies.
Large language models (LLMs) are increasingly used for academic expert recommendation. Existing audits typically evaluate model outputs in isolation, largely ignoring end-user inference-time interventions. As a result, it remains unclear whether failures such as refusals, hallucinations, and uneven coverage stem from model choice or deployment decisions. We introduce LLMScholarBench, a benchmark for auditing LLM-based scholar recommendation that jointly evaluates model infrastructure and end-user interventions across multiple tasks. LLMScholarBench measures both technical quality and social representation using nine metrics. We instantiate the benchmark in physics expert recommendation and audit 22 LLMs under temperature variation, representation-constrained prompting, and retrieval-augmented generation (RAG) via web search. Our results show that end-user interventions do not yield uniform improvements but instead redistribute error across dimensions. Higher temperature degrades validity, consistency, and factuality. Representation-constrained prompting improves diversity at the expense of factuality, while RAG primarily improves technical quality while reducing diversity and parity. Overall, end-user interventions reshape trade-offs rather than providing a general fix. We release code and data that can be adapted to other disciplines by replacing domain-specific ground truth and metrics.
Juhi Kulshrestha, Muhammad Bilal Zafar, Lisette Espin-Noboa et al.
With the widespread adoption of social media sites like Twitter and Facebook, there has been a shift in the way information is produced and consumed. Earlier, the only producers of information were traditional news organizations, which broadcast the same carefully-edited information to all consumers over mass media channels. Whereas, now, in online social media, any user can be a producer of information, and every user selects which other users she connects to, thereby choosing the information she consumes. Moreover, the personalized recommendations that most social media sites provide also contribute towards the information consumed by individual users. In this work, we define a concept of information diet -- which is the topical distribution of a given set of information items (e.g., tweets) -- to characterize the information produced and consumed by various types of users in the popular Twitter social media. At a high level, we find that (i) popular users mostly produce very specialized diets focusing on only a few topics; in fact, news organizations (e.g., NYTimes) produce much more focused diets on social media as compared to their mass media diets, (ii) most users' consumption diets are primarily focused towards one or two topics of their interest, and (iii) the personalized recommendations provided by Twitter help to mitigate some of the topical imbalances in the users' consumption diets, by adding information on diverse topics apart from the users' primary topics of interest.
Simon Walk, Lisette Espín-Noboa, Denis Helic et al.
Ontologies in the biomedical domain are numerous, highly specialized and very expensive to develop. Thus, a crucial prerequisite for ontology adoption and reuse is effective support for exploring and finding existing ontologies. Towards that goal, the National Center for Biomedical Ontology (NCBO) has developed BioPortal---an online repository designed to support users in exploring and finding more than 500 existing biomedical ontologies. In 2016, BioPortal represents one of the largest portals for exploration of semantic biomedical vocabularies and terminologies, which is used by many researchers and practitioners. While usage of this portal is high, we know very little about how exactly users search and explore ontologies and what kind of usage patterns or user groups exist in the first place. Deeper insights into user behavior on such portals can provide valuable information to devise strategies for a better support of users in exploring and finding existing ontologies, and thereby enable better ontology reuse. To that end, we study and group users according to their browsing behavior on BioPortal using data mining techniques. Additionally, we use the obtained groups to characterize and compare exploration strategies across ontologies. In particular, we were able to identify seven distinct browsing-behavior types, which all make use of different functionality provided by BioPortal. For example, Search Explorers make extensive use of the search functionality while Ontology Tree Explorers mainly rely on the class hierarchy to explore ontologies. Further, we show that specific characteristics of ontologies influence the way users explore and interact with the website. Our results may guide the development of more user-oriented systems for ontology exploration on the Web.
Lisette Espín-Noboa, Florian Lemmerich, Philipp Singer et al.
Nowadays, human movement in urban spaces can be traced digitally in many cases. It can be observed that movement patterns are not constant, but vary across time and space. In this work,we characterize such spatio-temporal patterns with an innovative combination of two separate approaches that have been utilized for studying human mobility in the past. First, by using non-negative tensor factorization (NTF), we are able to cluster human behavior based on spatio-temporal dimensions. Second, for understanding these clusters, we propose to use HypTrails, a Bayesian approach for expressing and comparing hypotheses about human trails. To formalize hypotheses we utilize data that is publicly available on the Web, namely Foursquare data and census data provided by an open data platform. By applying this combination of approaches to taxi data in Manhattan, we can discover and explain different patterns in human mobility that cannot be identified in a collective analysis. As one example, we can find a group of taxi rides that end at locations with a high number of party venues (according to Foursquare) on weekend nights. Overall, our work demonstrates that human mobility is not one-dimensional but rather contains different facets both in time and space which we explain by utilizing online data. The findings of this paper argue for a more fine-grained analysis of human mobility in order to make more informed decisions for e.g., enhancing urban structures, tailored traffic control and location-based recommender systems.