Vanessa Frias-Martinez

Smartphone applications routinely collect precise location data from users by offering free services and this information is often monetized for advertising and marketing purposes. While many companies limit sales to aggregate behaviors, data aggregators and data brokers (DA&DB) provide access to individual-level location data. Some DA&DB have implemented privacy-preserving rules and the Federal Trade Commission (FTC) has also intensified its regulations on location-data practices. This paper presents an in-depth exploration of U.S. privacy perceptions regarding specific location features that can be derived from data made available by DA&DB. These findings can provide policy-relevant insights that could assist organizations such as the FTC in defining clearer access rules. Using a factorial vignette survey, we collected responses from 1,405 participants to assess comfort levels with sharing various types of location features, including individual trajectories and visits to points of interest, which are currently available for purchase from DA&DB worldwide. Our results show that trajectory-related features elicit higher privacy concerns, that certain data broker based obfuscation practices increase comfort, and that race, ethnicity and education have an effect on data sharing privacy perceptions.

Background: COVID-19 forecasting models have been used to inform decision-making around resource allocation and intervention decisions, such as hospital beds or stay-at-home orders. State-of-the-art forecasting models often use multimodal data, including mobility or sociodemographic data, to enhance COVID-19 case prediction models. Nevertheless, related work has revealed under-reporting bias in COVID-19 cases as well as sampling bias in mobility data for certain minority racial and ethnic groups, which affects the fairness of COVID-19 predictions across racial and ethnic groups. Objective: This study aims to introduce a fairness correction method that works for forecasting COVID-19 cases at an aggregate geographic level. Methods: We use hard and soft error parity analyses on existing fairness frameworks and demonstrate that our proposed method, Demographic Optimization (DemOpts), performs better in both scenarios. Results: We first demonstrate that state-of-the-art COVID-19 deep learning models produce mean prediction errors that are significantly different across racial and ethnic groups at larger geographic scales. We then propose a novel debiasing method, DemOpts, to increase the fairness of deep learning–based forecasting models trained on potentially biased datasets. Our results show that DemOpts can achieve better error parity than other state-of-the-art debiasing approaches, thus effectively reducing the differences in the mean error distributions across racial and ethnic groups. Conclusions: We introduce DemOpts, which reduces error parity differences compared with other approaches and generates fairer forecasting models compared with other approaches in the literature.

UNSTRUCTURED COVID-19 forecasting models have been used to inform decision making around resource allocation and intervention decisions e.g., hospital beds or stay-at-home orders. State of the art forecasting models often use multimodal data such as mobility or socio-demographic data to enhance COVID-19 case prediction models. Nevertheless, related work has revealed under-reporting bias in COVID-19 cases as well as sampling bias in mobility data for certain minority racial and ethnic groups, which could affect the fairness of the COVID-19 predictions among racial and ethnic groups. In this paper, we first show that state of the art COVID-19 deep learning models output mean prediction errors that are significantly different across racial and ethnic groups; which could, in turn, support unfair policy decisions. We also propose a novel de-biasing method, DemOpts, to increase the fairness of deep learning based forecasting models trained on potentially biased datasets. Our results show that DemOpts can achieve better error parity than other state of the art de-biasing approaches, thus effectively reducing the differences in the mean error distributions across more racial and ethnic groups.

People affected by crises increasingly rely on social media platforms for real-time information and assistance. This underscores the need for a robust and reliable approach to provide accurate and timely information to affected individuals. Large Language Models (LLMs), which can understand user queries and generate responses, have the potential to act as assistants in crisis response. We explore various approaches, including instruction prompts, retrieval-augmented generation, and dynamic fusion of LLMs, to generate responses that address the information needs of affected individuals on social media platforms. Experiments demonstrate that the dynamic fusion approach produces better crisis responses across key evaluation dimensions, including professionalism, actionability, empathy, and relevance.

Xiaoying Song, Anirban Saha Anik, Eduardo Blanco, Vanessa Frias-Martinez, Lingzi Hong. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.