With the rapid development of social media, short-text data have become increasingly important in fields such as public opinion monitoring, user feedback analysis, and intelligent recommendation systems. However, existing short-text sentiment analysis models often suffer from limited cross-domain adaptability and poor generalization performance. To address these challenges, this study proposes a novel short-text sentiment classification model based on the Bidirectional Encoder Representations from Transformers (BERTs) and a dual-stream Transformer gated attention mechanism. This model first employs Bidirectional Encoder Representations from Transformers (BERTs) and the Chinese Robustly Optimized BERT Pretraining Approach (Chinese-RoBERTa) to achieve data augmentation and multilevel semantic mining, thereby expanding the training corpus and enhancing minority class coverage. Second, a dual-stream Transformer gated attention mechanism was developed to dynamically adjust feature fusion weights, enhancing adaptability to heterogeneous texts. Finally, the model integrates a Bidirectional Gated Recurrent Unit (BiGRU) with Multi-Head Self-Attention (MHSA) to strengthen sequence information modeling and global context capture, enabling the precise identification of key sentiment dependencies. The model’s superior performance in handling data imbalance and complex textual sentiment logic scenarios is demonstrated by the experimental results, achieving significant improvements in accuracy and F1 score. The F1 score reached 92.4%, representing an average increase of 8.7% over the baseline models. This provides an effective solution for enhancing the performance and expanding the application scenarios of short-text sentiment analysis models.

With the continuous growth of user reviews, identifying underlying sentiment across multi-source texts efficiently and accurately has become a significant challenge in NLP. Traditional single models in cross-domain sentiment analysis often exhibit insufficient stability, limited generalization capabilities, and sensitivity to class imbalance. Existing ensemble methods predominantly rely on static weighting or voting strategies among homogeneous models, failing to fully leverage the complementary advantages between models. To address these issues, this study proposes a heterogeneous ensemble sentiment classification model integrating multi-view features and dynamic weighting. At the feature learning layer, the model constructs three complementary base learners, a RoBERTa-FC for extracting global semantic features, a BERT-BiGRU for capturing temporal dependencies, and a TextCNN-Attention for focusing on local semantic features, thereby achieving multi-level text representation. At the decision layer, a meta-learner is used to fuse multi-view features, and dynamic uncertainty weighting and attention weighting strategies are employed to adaptively adjust outputs from different base learners. Experimental results across multiple domains demonstrate that the proposed model consistently outperforms single learners and comparison methods in terms of Accuracy, Precision, Recall, F1 Score, and Macro-AUC. On average, the ensemble model achieves a Macro-AUC of 0.9582 ± 0.023 across five datasets, with an Accuracy of 0.9423, an F1 Score of 0.9590, and a Macro-AUC of 0.9797 on the AlY_ds dataset. Moreover, in cross-dataset ranking evaluation based on equally weighted metrics, the model consistently ranks within the top two, confirming its superior cross-domain adaptability and robustness. These findings highlight the effectiveness of the proposed framework in enhancing sentiment classification performance and provide valuable insights for future research on lightweight dynamic ensembles, multilingual, and multimodal applications.

In complex and dynamic scenes, pedestrian detection faces significant challenges, including large-scale variations, severe occlusion, and strong background interference. To enhance detection robustness and contextual perception capability, this paper proposes an improved pedestrian detection framework named HCA-YOLOv8, which introduces a unified holistic context-aware modeling mechanism within the YOLOv8 architecture.First, an efficient channel context awareness mechanism based on the ECA attention is adopted to capture local channel dependencies and strengthen semantic responses related to pedestrian structures while maintaining computational efficiency. To further enhance feature representation, a channel–space–direction collaborative context modeling mechanism (CSD-Attention) is designed to jointly model channel semantic dependencies, spatial saliency distribution, and directional structural information.On this basis, a multi-source context enhancement framework is constructed to expand contextual perception capability. This framework integrates three complementary modules: multi-scale context fusion (MSCF) for handling scale variations, edge enhancement module (EEM) for strengthening boundary and contour information, and global context block (GCB) for capturing image-level semantic relationships. These modules are integrated into a unified Holistic Contextual Attention (HCA) block, which is embedded into the BottleneckCSP structure of the YOLOv8 backbone through residual connections and LayerScale, enabling effective multi-source context modeling while maintaining nearly unchanged model parameters.Extensive experiments conducted on five public datasets, including ICCV, MOT17, WiderPerson, CrowdHuman, and KITTI, demonstrate that HCA-YOLOv8 consistently outperforms several mainstream detection models across multiple evaluation metrics such as Precision, Recall, F1-score, mAP@0.5, and mAP@0.5:0.95. Ablation studies further verify the effectiveness and complementary contributions of each context modeling component. With the same parameter scale as YOLOv8s, the proposed method improves mAP@0.5 by 12.89% and 8.29% on the CrowdHuman and KITTI datasets, respectively, while maintaining stable training performance and computational efficiency.Overall, the proposed HCA-YOLOv8 provides an effective and reliable solution for pedestrian detection in complex scenes by integrating multi-dimensional contextual information within a unified attention framework.