Stance detection, which aims to identify public opinion towards specific targets using social media data, is an important yet challenging task. With the proliferation of diverse multimodal social media content including text, and images multimodal stance detection (MSD) has become a crucial research area. However, existing MSD studies have focused on modeling stance within individual text-image pairs, overlooking the multi-party conversational contexts that naturally occur on social media. This limitation stems from a lack of datasets that authentically capture such conversational scenarios, hindering progress in conversational MSD. To address this, we introduce a new multimodal multi-turn conversational stance detection dataset (called MmMtCSD). To derive stances from this challenging dataset, we propose a novel multimodal large language model stance detection framework (MLLM-SD), that learns joint stance representations from textual and visual modalities. Experiments on MmMtCSD show state-of-the-art performance of our proposed MLLM-SD approach for multimodal stance detection. We believe that MmMtCSD will contribute to advancing real-world applications of stance detection research.

For solving the facial expression recognition (FER) problem, we introduce a novel feature extractor called the coordinate-based neighborhood attention mechanism (CNAM), which uses the coordinate attention (CA) method to capture the directional relationships in separate horizontal and vertical directions, the input features from a preprocessing unit, and then passes this to two residual blocks, one consisting of the neighborhood attention (NA) mechanism, which captures the local interaction of features within the neighborhood of a feature vector, while the other one contains a channel attention implemented by a multilayer perceptron (MLP). We apply the feature extractor, the CNAM module, to four FER benchmark datasets, namely, RAF-DB, AffectNet(7cls), AffectNet(8cls), and CK+, and through qualitative and quantitative analysis techniques, we conclude that the insertion of the CNAM module could decrease the intra-cluster distances and increase the inter-cluster distances among the high-dimensional feature vectors. The CNAM compares well with other state-of-the-art (SOTA) methods, being the best-performing method for the AffectNet(7cls) and CK+ datasets, while for the RAF-DB and AffectNet(8cls) datasets, its performance is among the top-performing SOTA methods.

In studying the joint object detection and classification problem for facial expression recognition (FER) deploying the YOLOX framework, we introduce a novel feature extractor, called neighborhood coordinate attention Mamba (NCAMamba) to substitute for the original feature extractor in the Feature Pyramid Network (FPN). NCAMamba combines the background information reduction capabilities of Mamba, the local neighborhood relationship understanding of neighborhood attention, and the directional relationship understanding of coordinate attention. The resulting FER-YOLO-NCAMamba model, when applied to two unaligned FER benchmark datasets, RAF-DB and SFEW, obtains significantly improved mean average precision (mAP) scores when compared with those obtained by other state-of-the-art methods. Moreover, in ablation studies, it is found that the NCA module is relatively more important than the Visual State Space (VSS), a version of using Mamba for image processing, and in visualization studies using the grad-CAM method, it reveals that regions around the nose tip are critical to recognizing the expression; if it is too large, it may lead to erroneous prediction, while a small focused region would lead to correct recognition; this may explain why FER of unaligned faces is such a challenging problem.

Investigating public attitudes on social media is crucial for opinion mining systems. Stance detection aims to predict the attitude towards a specific target expressed in a text. However, effective neural stance detectors require substantial training data, which are challenging to curate due to the dynamic nature of social media. Moreover, deep neural networks (DNNs) lack explainability, rendering them unsuitable for scenarios requiring explanations. We propose a distantly supervised explainable stance detection framework (DS-ESD), comprising an instruction-based chain-of-thought (CoT) method, a generative network, and a transformer-based stance predictor. The CoT method employs prompt templates to extract stance detection explanations from a very large language model (VLLM). The generative network learns the input-explanation mapping, and a transformer-based stance classifier is trained with VLLM-annotated stance labels, implementing distant supervision. We propose a label rectification strategy to mitigate the impact of erroneous labels. Experiments on three benchmark datasets showed that our model outperformed the compared methods, validating its efficacy in stance detection tasks. This research contributes to the advancement of explainable stance detection frameworks, leveraging distant supervision and label rectification strategies to enhance performance and interpretability.

Stance detection is a crucial task in natural language processing and social computing, focusing on classifying expressed attitudes towards specific targets based on the input text. Conventional methods predominantly view stance detection as a task of target-oriented, sentence-level text classification. On popular social media platforms like Twitter, users often express their opinions through hashtags in addition to textual content within tweets. However, current methods primarily treat hashtags as data retrieval labels, neglecting to effectively utilize the semantic information they carry. In this paper, we propose a large language model knowledge-enhanced stance detection framework (LKESD) for stance detection. LKESD contains three main components: an instruction-prompted background knowledge acquisition module (IPBKA) that retrieves background knowledge of hashtags by providing handcrafted prompts to large language models (LLMs); a graph convolutional feature-enhancement module (GCFEM) is designed to extract the semantic representations of words that frequently co-occur with hashtags in the dataset by leveraging textual associations; an a knowledge fusion network (KFN) is proposed to selectively integrate graph representations and LLM features using a prompt-tuning framework. Extensive experimental results on three benchmark datasets demonstrate that our LKESD method outperforms 2.7% on all setups over compared methods, validating its effectiveness in stance detection tasks.