Fake news detection has been a long-standing research focus in social networks. Recent studies suggest that incorporating sentiment information from both news content and user comments can enhance detection performance. However, existing approaches typically treat sentiment features as auxiliary signals, overlooking role differentiation, that is, the same sentiment polarity may originate from users with distinct roles, thereby limiting their ability to capture nuanced patterns for effective detection. To address this issue, we propose SARC, a Sentiment-Augmented Role Clustering framework which utilizes sentiment-enhanced deep clustering to identify user roles for improved fake news detection. The framework first generates user features through joint comment text representation (with BiGRU and Attention mechanism) and sentiment encoding. It then constructs a differentiable deep clustering module to automatically categorize user roles. Finally, unlike existing approaches which take fake news label as the unique supervision signal, we propose a joint optimization objective integrating role clustering and fake news detection to further improve the model performance. Experimental results on two benchmark datasets, RumourEval-19 and Weibo-comp, demonstrate that SARC achieves superior performance across all metrics compared to baseline models. The code is available at: https://github.com/jxshang/SARC.

Fake news detection is a hot topic in the social media mining research community. Recent studies have shown that sentiment signals could significantly benefit the detection performance. However, most existing methods treat sentiment merely as auxiliary features, while the more sophisticated social sentiment interactions were rarely explored. In this paper, we propose a novel framework named ReFEND, which leverages the sentiment resonances among the social users (i.e., social sentiment resonances) and the sentiment relationship between news content and user comments to improve the detection performance. Specifically, we first utilize sentiment scorers to assess the sentiment of comments and identify users' emotional tendencies. Then we creatively construct a sentiment-aware multi-relational graph to capture social sentiment resonances evoked by the content and the interactions between comments and news. Next, we leverage the relational graph convolutional network (RGCN), which specializes in handling multi-relational graph data, to learn the interactions on sentiment-aware graph. To our best knowledge, this is the first effort to leverage social sentiment resonances for fake news detection. Experimental results on three datasets indicate that ReFEND significantly outperforms the state-of-the-art sentiment-based methods in terms of F1 and accuracy. Besides, ablation studies demonstrate the effectiveness of components designed in ReFEND.

Nowadays, social media platforms have become primary channels for dissemination of fake news. On these platforms, user comments provide direct reactions and insights into the content being shared, offering valuable clues for effective fake news detection. However, existing approaches predominantly analyze comments from an isolated, single-comment perspective, overlooking the broader insights from the entire comment section. To address this limitation, this paper comprehensively considers three key factors within the comment section: emotional evolution, semantic evolution, and diversity of user attention, based on which a novel fake news detection model MESE is proposed by mining the emotional and semantic evolution from user comments. Specifically, to capture the diversity of user attention toward different news segments, we first propose a news-conditioned comment attention mechanism to obtain news-enhanced comment representations. Next, a gating mechanism is introduced to deeply integrate emotional and semantic features. Additionally, we develop a comment emotional and semantic evolution module to capture shifts in public reactions over time. Finally, these diverse representations are fused to generate prediction results. Extensive experiments on two public datasets demonstrate the superior performance of MESE. Further case studies and ablation experiments validate the rationality of our design and the effectiveness of the model components.

Abstract Aspect sentiment triplet extraction (ASTE), which aims to extract aspect terms, opinion terms, and sentiment polarity from textual comments, is a crucial task in aspect-based sentiment analysis. Most existing approaches focus on leveraging contextual information while neglecting the effective utilization of syntactic structures within the text. To improve extraction performance, this paper proposes a syntax-enhanced multi-task learning model, SE-ASTE, which jointly extracts aspect sentiment triplets by incorporating syntax connections and dependency edge type information. Specifically, the ASTE task is decomposed into three sub-tasks: opinion entity extraction, relation detection, and sentiment extraction. To capture syntactic dependencies, we employ a graph convolutional network with an attention mechanism, which computes the importance of dependency edges and aggregates node information in a targeted manner to generate a syntax-enhanced contextual representation. Subsequently, a self-attention module is utilized to generate task-specific features, while a sentiment extraction module, based on a affine scorer, captures sentiment relationships between words. Experimental results on the ASTE-Data-V2 dataset demonstrate that SE-ASTE achieves an average improvement of 1.45% in the F1-score compared to baseline models, highlighting its effectiveness in aspect sentiment triplet extraction.

Robustness is paramount for ensuring the reliability of knowledge graph models in safety-sensitive applications. While recent research has delved into adversarial attacks on static knowledge graph models, the exploration of more practical temporal knowledge graphs has been largely overlooked. To fill this gap, we present the Adaptive Temporal Perturbation Framework (ATPF), a novel adversarial attack framework aimed at probing the robustness of temporal knowledge graph (TKG) models. The general idea of ATPF is to inject perturbations into the victim model input to undermine the prediction. First, we propose the Temporal Perturbation Prioritization (TPP) algorithm, which identifies the optimal time sequence for perturbation injection before initiating attacks. Subsequently, we design the Rank-Based Edge Manipulation (RBEM) algorithm, enabling the generation of both edge addition and removal perturbations under black-box setting. With ATPF, we present two adversarial attack methods: the stringent ATPF-hard and the more lenient ATPF-soft, each imposing different perturbation constraints. Our experimental evaluations on the link prediction task for TKGs demonstrate the superior attack performance of our methods compared to baseline methods. Furthermore, we find that strategically placing a single perturbation often suffices to successfully compromise a target link.

Predicting information popularity in social networks has become a central focus of network analysis. While recent advancements have been made, most existing approaches rely solely on the final cascade size as the primary supervision signal for model optimization. This narrow focus limits the model generalization ability, particularly when faced with highly heterogeneous cascades. Additionally, in real-world scenarios, obtaining detailed social relationships is challenging, complicating effective structural feature learning. To address these issues, this paper proposes a semi-supervised model called Dual Variational Cascade AutoEncoders (DVCAE), which leverages parallel structural and temporal variational autoencoders for enhanced feature learning and popularity prediction. The model first aggregates multiple cascades into a global interaction graph, enabling structural information sharing across cascades. Then, it applies sparse matrix factorization-based graph embedding and graph filtering techniques on global and local cascade graphs respectively, generating initial node embeddings that are insensitive to topological perturbations. After that, two parallel variational autoencoders are designed to generate hidden representations for structural and temporal features respectively, with two self-supervised reconstruction losses integrated into the prediction loss to enrich supervision signals. Extensive experiments conducted on three real-world datasets demonstrate that DVCAE outperforms state-of-the-art models in terms of prediction accuracy.

Influence maximization, which seeks to find top influential individuals from a social network, has been extensively investigated in recent years. However, previous studies mainly focused on single diffusion or the diffusion of positive and negative messages, in which a competitor dominates the diffusion process. However, in a more realistic scenario, there is a level playing field between similar competitors. To cope with this, we introduce a new Balanced Competitive Influence Maximization (BaCIM) problem which considers the balance in information dissemination. We propose a Balanced Competitive Independent Cascade (BCIC) model to describe how two similar competitive products spread and compete in the same mobile social network. Given the competitor's seeding strategy, BaCIM aims to find a size-k seed set to maximize its own influence spread. We prove that the problem is NP-hard and the objective function is submodular, based on which a greedy algorithm is proposed with (1-1/e-ε) approximation guarantee. To handle large networks, we further propose a Blocked Reverse Influence Sampling algorithm named BRIS, in which we redesign the reverse influence sampling procedure to support the diffusion model. Experimental results on two location-based social networks and several large-scale real datasets validate effectiveness and efficiency of our algorithm.