This paper proposes a hybrid deep learning model for robust and interpretable sentiment classification of Twitter data. The model integrates Bidirectional Encoder Representations from Transformers (BERT)-based contextual embeddings, a Bidirectional Long Short-Term Memory (BiLSTM) network, and a custom attention mechanism to classify tweets into four sentiment categories: Positive, Negative, Neutral, and Irrelevant. Addressing the challenges of noisy and multilingual social media content, the model incorporates a comprehensive preprocessing pipeline and data augmentation strategies including back-translation and synonym replacement. An ablation study demonstrates that combining BERT with BiLSTM improves the model’s sensitivity to sequence dependencies, while the attention mechanism enhances both classification accuracy and interpretability. Empirical results show that the proposed model outperforms BERT-only and BERT+BiLSTM baselines, achieving F1-scores (F1) above 0.94 across all sentiment classes. Attention weight visualizations further reveal the model’s ability to focus on sentiment-bearing tokens, providing transparency in decision-making. The proposed framework is well-suited for deployment in real-time sentiment monitoring systems and offers a scalable solution for multilingual and multi-class sentiment analysis in dynamic social media environments. We also include a focused characterization of the dataset via an Exploratory Data Analysis in the Methods section.

Bank telemarketing campaigns often experience low subscription rates due to customer heterogeneity and severe class imbalance, which pose challenges for reliable predictive modeling. This study investigates a data-driven approach that integrates synthetic minority oversampling and cost-sensitive learning to improve the prediction of telemarketing outcomes. Experiments are conducted using the Portuguese Bank Marketing dataset, comprising 41,188 instances with a positive response rate of 11.3%. Eight machine learning models are evaluated under a unified preprocessing pipeline and five-fold stratified cross-validation, including Logistic Regression, Decision Tree, Random Forest, and Ensemble methods. The results show that Ensemble models, particularly CatBoost, XGBoost, and LightGBM, achieve improved performance compared with traditional baselines, with notable gains in minority-class recall and overall discrimination ability. The best-performing model attains an F1-score of 0.540, a recall of 0.812 for the positive class, and a ROC–AUC of 0.908. To enhance interpretability, SHAP-based analysis is applied to quantify feature contributions, identifying campaign duration, previous contact outcomes, and selected macroeconomic indicators as key predictors. These findings indicate that combining resampling strategies with cost-sensitive optimization provides a robust and transparent approach for learning from imbalanced telemarketing data, thereby supporting reproducible and data-driven financial decision-making by explicitly addressing difficulty in minority-class identification under imbalance and class imbalance under cross-entropy training in imbalanced banking data.

Graphical 【Graphical abstract showing a conceptual framework for intergovernmental cooperation in watershed governance in arid northwest China. The central circle presents the study topic and notes use of SPSS 26.0. On the left, key challenges are listed as water scarcity, cross-boundary interdependence, and upstream-downstream conflicts. At the top, structure/process factors include a cooperation network and governance processes of communication, oversight, and incentives and constraints. On the right, performance outcomes include ecological health, conflict reduction, and adaptive capacity. At the lower left, methods include survey and analysis, regression and mediation, and SPSS 26.0. At the lower right, policy messages are strengthen accountability, align incentives, and enhance communication. A small circle at the bottom highlights 4 goals, 23 processes, and 89 conditions. Arrows indicate that cooperation links governance structure and process to watershed performance, with some effects mediated through cooperation.】 Rivers and watersheds in arid regions face severe governance challenges because hydrological interdependence crosses administrative boundaries, while water scarcity intensifies conflicts between upstream and downstream jurisdictions and among ecological and socio-economic goals. This study examines how intergovernmental cooperation affects watershed governance performance in arid Northwest China using a structure-process-performance framework. We conceptualize cooperation as the structure of intergovernmental networks and four mechanisms: interest coordination, communication and consultation, oversight accountability, and incentives and constraints. Based on a questionnaire survey of government agencies and basin-management organizations in the Kashgar River Basin, we test reliability and validity and estimate multiple linear regression and mediation models in SPSS 26.0. The results show that oversight accountability and incentives and constraints significantly improve governance performance, whereas cooperation networks and interest coordination have no significant direct effects. Communication and consultation mediate the effects of cooperation networks and selected mechanisms on performance. These findings indicate that, under scarcity, soft collaborative arrangements are insufficient without credible accountability, aligned incentives, and transparent information disclosure. Policy priorities include refining performance indicators, strengthening enforcement and disclosure, and institutionalizing cross-jurisdiction communication platforms.