Embedding Heterogeneous Information Network in Hyperbolic Spaces

Heterogeneous information network (HIN) embedding, aiming to project HIN into a low-dimensional space, has attracted considerable research attention. Most of the existing HIN embedding methods focus on preserving the inherent network structure and semantic correlations in Euclidean spaces. However, one fundamental problem is whether the Euclidean spaces are the intrinsic spaces of HIN? Recent researches find the complex network with hyperbolic geometry can naturally reflect some properties, e.g., hierarchical and power-law structure. In this article, we make an effort toward embedding HIN in hyperbolic spaces. We analyze the structures of three HINs and discover some properties, e.g., the power-law distribution, also exist in HINs. Therefore, we propose a novel HIN embedding model HHNE. Specifically, to capture the structure and semantic relations between nodes, HHNE employs the meta-path guided random walk to sample the sequences for each node. Then HHNE exploits the hyperbolic distance as the proximity measurement. We also derive an effective optimization strategy to update the hyperbolic embeddings iteratively. Since HHNE optimizes different relations in a single space, we further propose the extended model HHNE++. HHNE++ models different relations in different spaces, which enables it to learn complex interactions in HINs. The optimization strategy of HHNE++ is also derived to update the parameters of HHNE++ in a principle manner. The experimental results demonstrate the effectiveness of our proposed models.

Network Embedding-Based Approach for Detecting Collusive Spamming Groups on E-Commerce Platforms

Information security is one of the key issues in e-commerce Internet of Things (IoT) platform research. The collusive spamming groups on e-commerce platforms can write a large number of fake reviews over a period of time for the evaluated products, which seriously affect the purchase decision behaviors of consumers and destroy the fair competition environment among merchants. To address this problem, we propose a network embedding based approach to detect collusive spamming groups. First, we use the idea of a meta-graph to construct a heterogeneous information network based on the user review dataset. Second, we exploit the modified DeepWalk algorithm to learn the low-dimensional vector representations of user nodes in the heterogeneous information network and employ the clustering methods to obtain candidate spamming groups. Finally, we leverage an indicator weighting strategy to calculate the spamming score of each candidate group, and the top-k groups with high spamming scores are considered to be the collusive spamming groups. The experimental results on two real-world review datasets show that the overall detection performance of the proposed approach is much better than that of baseline methods.

Identifying the Relatedness between Tourism Attractions from Online Reviews with Heterogeneous Information Network Embedding

The relatedness between tourism attractions can be used in a variety of tourism applications, such as destination collaboration, commercial marketing, travel recommendations, and so on. Existing studies have identified the relatedness between attractions through measuring their co-occurrence—these attractions are mentioned in a text at the same time—extracted from online tourism reviews. However, the implicit semantic information in these reviews, which definitely contributes to modelling the relatedness from a more comprehensive perspective, is ignored due to the difficulty of quantifying the importance of different dimensions of information and fusing them. In this study, we considered both the co-occurrence and images of attractions and introduce a heterogeneous information network (HIN) to reorganize the online reviews representing this information, and then used HIN embedding to comprehensively identify the relatedness between attractions. First, an online review-oriented HIN was designed to form the different types of elements in the reviews. Second, a topic model was employed to extract the nodes of the HIN from the review texts. Third, an HIN embedding model was used to capture the semantics in the HIN, which comprehensively represents the attractions with low-dimensional vectors. Finally, the relatedness between attractions was identified by calculating the similarity of their vectors. The method was validated with mass tourism reviews from the popular online platform MaFengWo. It is argued that the proposed HIN effectively expresses the semantics of attraction co-occurrences and attraction images in reviews, and the HIN embedding captures the differences in these semantics, which facilitates the identification of the relatedness between attractions.