Climate change is intensifying hydrological extremes, yet most frameworks assess drought and flood hazards independently, limiting integrated risk management. This study proposes a two-dimensional analytical framework to characterize the drought-flood continuum, moving beyond single-index approaches. We introduce the Hydro-Hazard Index (HHI) as a directionality metric (HHI = Flood Severity − Drought Severity) to classify the dominant hazard type, and the Total Severity Index (TSI = Flood Severity + Drought Severity) as a complementary metric to quantify overall hazard magnitude. Analyzing multi-temporal data from 115 hexagonal units (2018–2024), we employed dynamic features (trends, changes, volatility) and four machine learning models to classify areas as “flood-prone” based on validated flood records. Our results show HHI values ranging from −2.44 to 8.81, with 20.9% of areas classified as Flood-Dominated (mean HHI = 4.58) and 79.1% as Normal (mean HHI = 0.76). Crucially, the two-dimensional analysis revealed that areas with identical HHI values can have vastly different TSI values, under scoring the importance of our dual-index approach. Random Forest achieved the highest performance in predicting flood-prone status (Accuracy = 0.913, AUC = 0.967, Recall = 1.00), with flood_volatility as the most important predictor (24.2%). Spatial autocorrelation confirmed strong clustering of high-risk areas (Moran’s I = 0.716, p < 0.001). By analyzing flood and drought as distinct but interacting dimensions, this framework provides a more robust and nuanced tool for integrated risk assessment. While acknowledging limitations related to data availability and the need for further independent validation, the proposed framework supports sustainable water resource management and climate adaptation planning under increasing hydrological uncertainty.

Cross-domain sentiment analysis remains challenging due to distributional shifts and heterogeneous sentiment expressions across platforms. Existing domain adaptation approaches primarily focus on enforcing domain-invariant representations. However, such symmetry-preserving strategies often overlook directional and expression-level asymmetries. These asymmetries naturally arise in real-world sentiment data, particularly for context-inferred sentiment expressions. In this work, we propose a novel symmetry- and asymmetry-aware domain adaptation framework for cross-domain sentiment classification. The framework models symmetry through explicit multi-source distribution alignment, which captures transferable sentiment knowledge across domains. Additionally, aspect-level structural supervision organizes representations according to shared linguistic aspects. To address asymmetry, a directional divergence regularization is introduced. This component models expression-level and directional discrepancies between source and target domains. Importantly, the framework operates without requiring target-domain annotations. Experiments are conducted under a multi-source unsupervised domain adaptation setting using sentence-level hotel review datasets collected from multiple online platforms. Empirical results demonstrate strong performance for the proposed framework. It achieves an average Accuracy of 82.0% and Macro-F1 of 80.6%. The framework consistently and statistically significantly outperforms source-only, multi-source, and transformer-based adversarial adaptation baselines across all evaluated target domains (p < 0.05). Additional analyses confirm improved robustness to implicit sentiment expressions and platform-induced asymmetries. These findings highlight the importance of jointly modeling symmetry and asymmetry for robust cross-domain sentiment adaptation and provide a unified and deployable solution for sentiment analysis under realistic platform shifts.

Bug severity classification supports software maintenance by helping developers prioritize defect resolution. Most existing approaches combine bug report titles and descriptions into a single representation, often assuming that both textual components contribute equally to severity prediction. However, concise titles and detailed descriptions may provide different types of severity-related information. This study investigates their relative contribution and proposes an Adaptive Title–Description Fusion (ATDF) framework that separately encodes title and description representations and adaptively estimates their contribution during feature fusion. Experiments were conducted on Mozilla Bugzilla repositories using a multiclass classification setting with five severity categories. The proposed framework was compared with title-only, description-only, direct concatenation, and standard gated fusion baselines. ATDF achieved the highest overall performance, with a Macro-F1 score of 0.771, compared with 0.756 for standard gated fusion and 0.739 for direct concatenation. Additional analyses showed that title and description contributions varied across severity categories and repositories under the current experimental setting. Overall, the findings suggest that considering the relative contribution of title and description information can provide a practical approach to improving bug severity classification while offering additional insight into title–description fusion behavior in software repositories.