Sequential recommendation (SR) learns users’ preferences by capturing the sequential patterns from users’ behaviors evolution. As discussed in many works, user–item interactions of SR generally present the intrinsic power-law distribution, which can be ascended to hierarchy-like structures. Previous methods usually handle such hierarchical information by making user–item sectionalization empirically under Euclidean space, which may cause distortion of user–item representation in real online scenarios. In this article, we propose a Poincaré-based heterogeneous graph neural network named Poincaré Heterogeneous Graph Neural Networks for Sequential Recommendation (PHGR) to model the sequential pattern information as well as hierarchical information contained in the data of SR scenarios simultaneously. Specifically, for the purpose of explicitly capturing the hierarchical information, we first construct a weighted user–item heterogeneous graph by aliening all the user–item interactions to improve the perception domain of each user from a global view. Then the output of the global representation would be used to complement the local directed item–item homogeneous graph convolution. By defining a novel hyperbolic inner product operator, the global and local graph representation learning are directly conducted in Poincaré ball instead of commonly used projection operation between Poincaré ball and Euclidean space, which could alleviate the cumulative error issue of general bidirectional translation process. Moreover, for the purpose of explicitly capturing the sequential dependency information, we design two types of temporal attention operations under Poincaré ball space. Empirical evaluations on datasets from the public and financial industry show that PHGR outperforms several comparison methods.

Multimodality sentiment analysis in the social Internet of Things is a developing field, which is basic to empathetic mechanisms, affective computing, and artificial intelligence. Current works in this domain do not explicitly consider the influence of contextual information fusion based on correlation coefficient and memory network with branch structure for sentiment analysis. Unlike present works, this article presents a hierarchical self-attention fusion (H-SATF) model for capturing contextual information better among utterances, a contextual self-attention temporal convolutional network (CSAT-TCN) for sentiment recognition in the social Internet of Things, and a multibranch memory (MBM) network that stores self-speaker and interspeaker sentimental states into global memories. For MOSI data sets, the hybrid H-SATF-CSAT-TCN-MBM model outperforms the state-of-the-art networks and shows 0.31%-9.93% improvement.

The existing sequential recommendation methods focus on modeling the temporal relationships of user behaviors and are good at using additional item information to improve performance. However, these methods rarely consider the influences of users' sequential subjective sentiments on their behaviors---and sometimes the temporal changes in human sentiment patterns plays a decisive role in users' final preferences. To investigate the influence of temporal sentiments on user preferences, we propose generating preferences by guiding user behavior through sequential sentiments. Specifically, we design a dual-channel fusion mechanism. The main channel consists of sentiment-guided attention to match and guide sequential user behavior, and the secondary channel consists of sparse sentiment attention to assist in preference generation. In the experiments, we demonstrate the effectiveness of these two sentiment modeling mechanisms through ablation studies. Our approach outperforms current state-of-the-art sequential recommendation methods that incorporate sentiment factors.

In Context-Aware Recommendation, contextual information is usually represented as attributes (or features). Most approaches utilize the static values of attributes to facilitate rating predictions—and some try to capture all the attribute interactions to generate more accurate recommendations. However, attribute connotations vary significantly across different users or items, which means that static attributes can become powerless to express personalized preferences. Moreover, capturing all attribute interactions is pointless because some interactions benefit prediction, while others reduce the performance. In this paper, we refine the attributes dynamically through three interacting aspects: attribute types, user preferences and item relations. By following this process, called Attribute Boosting (AB), attribute interactions are targeted to provide more accurate rating predictions. Furthermore, Gradient Boosted Regression Trees (GBRT) are tailored to act as the Global Boosting (GB) part of our model to create personalized global biases that are separated from the AB process. Finally, the prediction is generated from the combination of these two components. The experimental results demonstrate that the Attribute and GB approach addresses the limitations of fixed attributes, outperforms other representative methods and is flexible by adjusting the attribute type granularities.