Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2201.05070

Applying Machine Learning and AI Explanations to Analyze Vaccine Hesitancy

Carsten Lange·Jian Lange
View original source ↗Read source document ↗Export metadata ↓

Abstract

The paper quantifies the impact of race, poverty, politics, and age on COVID-19 vaccination rates in counties in the continental US. Both, OLS regression analysis and Random Forest machine learning algorithms are applied to quantify factors for county-level vaccination hesitancy. The machine learning model considers joint effects of variables (race/ethnicity, partisanship, age, etc.) simultaneously to capture the unique combination of these factors on the vaccination rate. By implementing a state-of-the-art Artificial Intelligence Explanations (AIX) algorithm, it is possible to solve the black box problem with machine learning models and provide answers to the "how much" question for each measured impact factor in every county. For most counties, a higher percentage vote for Republicans, a greater African American population share, and a higher poverty rate lower the vaccination rate. While a higher Asian population share increases the predicted vaccination rate. The impact on the vaccination rate from the Hispanic population proportion is positive in the OLS model, but only positive for counties with a high Hispanic population (>65%) in the Random Forest model. Both the proportion of seniors and the one for young people in a county have a significant impact in the OLS model - positive and negative, respectively. In contrast, the impacts are ambiguous in the Random Forest model. Because results vary between geographies and since the AIX algorithm is able to quantify vaccine impacts individually for each county, this research can be tailored to local communities. An interactive online mapping dashboard that identifies impact factors for individual U.S. counties is available at https://www.cpp.edu/~clange/vacmap.html. It is apparent that the influence of impact factors is not universally the same across different geographies.

Explore related subjects

cs.LGcs.CY

Keep this discovery

BibTeXRIS

Carsten Lange, Jian Lange. 2022-01-07. Applying Machine Learning and AI Explanations to Analyze Vaccine Hesitancy. https://arxiv.org/abs/2201.05070

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

AUC Maximization from Biased Positive-unlabeled Data with Confidence

Maximizing the area under the receiver operating characteristic curve (AUC) is a standard approach to imbalanced binary classification. Although positive and negative data are required for maximizing the AUC, negative data are often difficult to collect in some real-world applications due to privacy concerns or the need for specialized expertise to annotate them. Thus, AUC maximization from positive and unlabeled (PU) data has been attracting attention. Existing methods assume that labeled positive data are unbiased samples from the true positive distribution. However, this ideal assumption is often violated in practice. In this paper, we propose a method to maximize the AUC from biased PU data. To address the bias, our key idea is to exploit {\it confidence}, i.e., the probability that an instance is positive, associated with the small number of labeled positive data. We derive an estimator of the AUC risk using biased PU data with confidence, enabling AUC maximization under such bias. We further show that the rewritten AUC risk induces a Bayes-optimal AUC ranking even when the available confidence is any strictly increasing transformation of the true posterior probability. We experimentally show the effectiveness of our method on eight real-world datasets.

cs.LG↗
arXiv2026

Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation

Continual world models must decide whether new data justify changing the model. Fixed replay schedules and prediction-error triggers specify when to update, but neither reveals the value of an individual update: one deployment run cannot show how the same model would have performed at that moment had it held its parameters. We introduce the fork ledger, which branches a deployment stream at pre-registered decision points into matched update and hold continuations under common random numbers. It evaluates both continuations on the same episodes and records $\Delta R = R_{\mathrm{update}} - R_{\mathrm{hold}}$. Always applying one fixed update mechanism lowers return on all three simulated control tasks: CartPole ($-144.0$; checkpoint-bootstrap $95\%$ CI $[-185.4,-116.1]$, against a converged return near $650$), Walker ($-82.8$; $[-101.1,-61.7]$) and Cheetah ($-18.6$; $[-29.0,-6.6]$). Divergence is an outcome of applying the update, so the estimand counts every attempted fork; restricted to the $693$ of $720$ that did not collapse, CartPole and Walker are unchanged in sign ($-113.4$ and $-82.1$) and Cheetah becomes unresolved ($-3.9$; $[-17.5,+13.0]$). The task is the unit of inference: each contributes $240$ attempted forks over five pretrained checkpoints crossed with two drift directions. The ledger makes counterfactual utility observable for a fixed mechanism, allowing triggers to be judged by the updates they select rather than by surprise detection alone.

cs.LG↗
arXiv2026

When More Is Not Better: Component Anti-Synergy in a P300 Speller

P300 brain-computer interface (BCI) spellers can provide hands-free communication for people with severe motor impairments. Modern pipelines combine multiple individually promising components, often assuming that 'more-is-better'. We tested this assumption using a four-component full-factorial experiment varying the inclusion of Euclidean Alignment (EA), xDAWN spatial filtering, subject calibration, and language model priors on a public P300 dataset. Performance was evaluated using accuracy, repetitions, and information transfer rate (ITR) with mixed-effects models. Results show that the value of components is conditional rather than additive. Calibration was the strongest singular contributor, while EA compensated for its absence in zero-calibration settings. Adding independently useful components could also reduce performance, revealing component anti-synergy. Contrary to conventional wisdom, LM support was not universally beneficial: its effect depends strongly on the strength of the underlying EEG pipeline, while results from a larger LM showed a similar pattern. Together, these findings challenge maximal 'all-on' pipeline design and highlight the value of selecting spatial and language-support components according to the quality of available EEG evidence.

cs.LG↗