Sequential recommendation aims to recommend the next item that matches a user’s interest, based on the sequence of items he/she interacted with before. Although effective, existing work suffers from the following limitations: (1) Existing diffusion-based recommendation methods have undertaken tailored refinements to the diffusion process without considering the difference between recommendation and other tasks, leading to the ignorance of the user’s personalized preferences; (2) Self-supervised contrastive learning, widely used to mitigate the data sparsity issue in sequential recommendation, typically employs random augmentation to create multiple views of user sequences. However, random augmentation can disrupt the semantic integrity and interest patterns within the sequence, resulting in semantically divergent augmented views that may misrepresent user preferences. To address these challenges, we propose the Context-Aware Diffusion-based Sequential Recommendation (CADSR) model, which leverages context information to generate more semantically consistent positive samples during contrastive learning. This ensures that the model captures both user preferences and their evolution more accurately. Extensive experiments on four public benchmark datasets show that CADSR outperforms 11 state-of-the-art baselines, achieving an average improvement of 10.94% in Recall@10 and 10.54% in NDCG@10 over the best baseline. Source code is available at https://github.com/queenjocey/CADSR.

Even though users interacted diversely on items (e.g., click, add-to-cart, and buy), traditional recommendations were mostly built using only the user-item interaction data on the target behavior (e.g., buy), making them suffer from the severe data sparsity issue. To alleviate the problem, recent works on multi-behavior recommendation incorporated multiple types of user-item interactions such as click, add-to-cart, and buy. However, the latest approaches are still limited by overlooking early-stage interactions, and have limited expressiveness of Euclidean geometry. To overcome these issues, in this paper, we propose a Multi-behavior Hyperbolic Graph Recommender (MB-HGR) with two novel aspects. First, it uses multiple heterogeneous graphs to learn multiple user behavior types, where each heterogeneous graph represents a user-item interaction type. This will help not only alleviate the serious data sparsity problem, but also allow the model to explicitly weight different behavior types and prevent information loss. Second, it leverages the expressiveness of the hyperbolic geometry over Euclidean geometry, where exponential growth of distances in the hyperbolic geometry matches the exponential growth of nodes in the hierarchical structures and learns better users/items representations. Experimental results on two public benchmark datasets show that on average our proposed model achieves a significant improvement of 28.32% at Recall@10 and 30.14% at NDCG@10 over the best baseline.

Quaternion space has brought several benefits over the traditional Euclidean space: Quaternions (i) consist of a real and three imaginary components, encouraging richer representations; (ii) utilize Hamilton product which better encodes the inter-latent interactions across multiple Quaternion components; and (iii) result in a model with smaller degrees of freedom and less prone to overfitting. Unfortunately, most of the current recommender systems rely on real-valued representations in Euclidean space to model either user's long-term or short-term interests. In this paper, we fully utilize Quaternion space to model both user's long-term and short-term preferences. We first propose a QUaternion-based self-Attentive Long term user Encoding (QUALE) to study the user's long-term intents. Then, we propose a QUaternion-based self-Attentive Short term user Encoding (QUASE) to learn the user's short-term interests. To enhance our models' capability, we propose to fuse QUALE and QUASE into one model, namely QUALSE, by using a Quaternion-based gating mechanism. We further develop Quaternion-based Adversarial learning along with the Bayesian Personalized Ranking (QABPR) to improve our model's robustness. Extensive experiments on six real-world datasets show that our fused QUALSE model outperformed 11 state-of-the-art baselines, improving 8.43% at [email protected] and 10.27% at [email protected] on average compared with the best baseline.

Fake news has been generated and widely spread although journalists and researchers created fact-checking websites (e.g., Snopes and PolitiFact) and analyzed characteristics of fake news. To fill this gap, in this paper we focus on developing machine learning models based on only text information in news articles toward automatically detecting fake news. In particular, we proposed a framework which extracts 134 features and builds traditional known machine learning models like Random Forest and XGBoost. We also propose a deep learning based model (LSTM with self-attention mechanism) to see which one performs better in the fake news article detection in both political news and celebrity news domains. In the experiments, we compare our models against 7 baselines. The results show that our XGBoost model improved 16.4% and 13.1% over the best baseline in terms of accuracy in both political news articles and celebrity news articles, respectively.

To combat fake news, researchers mostly focused on detecting fake news and journalists built and maintained fact-checking sites (e.g., Snopes.com and Politifact.com). However, fake news dissemination has been greatly promoted via social media sites, and these fact-checking sites have not been fully utilized. To overcome these problems and complement existing methods against fake news, in this paper we propose a deep-learning based fact-checking URL recommender system to mitigate impact of fake news in social media sites such as Twitter and Facebook. In particular, our proposed framework consists of a multi-relational attentive module and a heterogeneous graph attention network to learn complex/semantic relationship between user-URL pairs, user-user pairs, and URL-URL pairs. Extensive experiments on a real-world dataset show that our proposed framework outperforms eight state-of-the-art recommendation models, achieving at least 3$\sim$5.3% improvement. Our source code and dataset are available at \urlhttps://web.cs.wpi.edu/~kmlee/data.html .