Residential smart-charging access requires both domestic charging infrastructure and smart-capable equipment. We examined the parking-associated disparity across these stages using England’s 2024 National Travel Survey (NTS). Stage 1 included 478 plug-in vehicle records; Stage 2 included 342 with domestic access and known smart status, only 15 of which lacked private off-street parking (11 smart and 4 non-smart). We used NTS interview weights (W3) in logistic models with primary-sampling-unit (PSU)-cluster-robust coefficient inference, marginal standardization, and a PSU-cluster bootstrap for derived quantities. Original sampling strata were not reconstructed. Standardized joint probabilities were 18.5% without and 59.6% with private off-street parking: a 41.1-percentage-point contrast (95% confidence interval 27.5–51.8). The symmetric decomposition allocated 40.6 points to domestic access and 0.5 to conditional smart status. The latter remains imprecise because of the small subgroup without off-street parking and does not establish equivalence. Sensitivity-analysis point estimates of the adjusted joint contrast ranged from 39.8 to 43.3 percentage points. The disparity was concentrated at the domestic-access stage. The NTS measures reported infrastructure, not charging behavior or electricity-system effects. This framework can support future monitoring of changes in domestic access and smart capability.
Hate speech on social media reproduces norms of inequality and gender stereotypes, disproportionately affecting women. This study proposes a hybrid approach that integrates emotional tone classification with explicit hostility detection to strengthen preventive moderation. We constructed a corpus from three open datasets (1,236,371 records; 1,003,991 after ETL) and represented the text using TF-IDF and contextual RoBERTa embeddings. We trained individual models (RoBERTa fine-tuned, Random Forest, and XGBoost) and a stacking metamodel (Gradient Boosting) that combines their probabilities. On the test set, the ensemble outperformed the base classifiers, achieving accuracy of 0.93 in hate detection and 0.90 in emotion classification, with an AUC of 0.98 for emotion classification. We implemented a RESTful API and a web client to validate the moderation flow before publication, along with an administration panel for auditing. Performance tests showed viability under moderate loads and concurrency limitations starting at 300 users, associated with deployment via an Ngrok tunnel. In general, the results indicate that incorporating emotional tone analysis improves the model's ability to identify implicit hostility and offers a practical way to promote safer digital environments. The probabilistic results obtained by the ensemble model were subsequently analyzed using the Bayesian Calibration and Optimal Design under Asymmetric Risk (BACON-AR) framework, which serves as a mathematical post-hoc validation layer to optimize the decision threshold under unequal costs. This framework does not modify the trained architecture but adjusts the estimated probabilities and selects the threshold that minimizes the total expected risk. By combining TF-IDF and RoBERTa embeddings with a stacked metamodel, the ensemble's decision function was optimized via regularization, improving generalizability and the stability of predictions. The incorporation of the BACON-AR framework strengthened the system's probabilistic consistency, ensuring that final decisions were aligned with the actual consequences of errors under an asymmetric risk scheme.
Hate speech on social media reproduces norms of inequality and gender stereotypes, disproportionately affecting women. This study proposes a hybrid approach that integrates emotional tone classification with explicit hostility detection to strengthen preventive moderation. We constructed a corpus from three open data sets (1,236,371 records; 1,003,991 after ETL) and represented the text using TF-IDF and contextual RoBERTa embeddings. We trained individual models (RoBERTa fine-tuned, Random Forest, and XGBoost) and a stacking metamodel (Gradient Boosting) that combines their probabilities. On the test set, the ensemble outperformed the base classifiers, achieving accuracy of 0.93 in hate detection and 0.90 in emotion classification, with an AUC of 0.98 for emotion classification. We implemented a RESTful API and a web client to validate the moderation flow before publication, along with an administration panel for auditing. Performance tests in a prototype deployment (Google Colab exposed through an Ngrok tunnel) provided proof-of-concept validation, revealing concurrency limitations from around 300 users due to infrastructure constraints. In general, the results indicate that incorporating emotional tone analysis improves the model’s ability to identify implicit hostility and offers a practical way to promote safer digital environments. The probabilistic outputs produced by the ensemble model were subsequently analyzed using the Bayesian Calibration and Optimal Design under Asymmetric Risk (BACON-AR) framework, which serves as a mathematical post hoc decision layer for evaluating classification behaviour under unequal error costs. Rather than modifying the trained architecture or improving its predictive performance, the framework identifies a cost-sensitive operating threshold that minimizes the total expected risk under the selected asymmetric cost configuration. The experiments were conducted using an English-language data set; therefore, the findings of this study are limited to hate speech detection in English.
17 September 2026 in Transport Economics and Management