User Social Relationships Research Articles

KGCF: Social relationship-aware graph collaborative filtering for recommendation

With the increasing popularity of recommendation techniques and social networks, social network recommendation has become a significant research field, i.e., predicting a user's preferences based on her or his historical interaction data, because the social relationships of users can not only enrich their interaction information, but also imply the accurate characterization of their preferences. Although there are some existing studies that predict users' preferences by using the characteristics of social relationships, their time complexity and hardware resource consumption are often very expensive, which limits the feasibility in large-scale real-world scenarios. To address these issues, in this paper, we propose a simple and effective K-core Graph Collaborative Filtering (KGCF) model to incorporate the user's social features into a recommendation framework. The user's interaction information is auto-encoded linearly by incorporating the social relationship graph into the user's interaction information and constructing a multi-layer graph filter. The linear autoencoder graph filter alleviates the highly sparse data problem and dramatically reduces the training time and hardware resource consumption. Experimental results on several real-world datasets show the superior effectiveness and spatiotemporal efficiency compared with the existing baselines, especially the training speed is significantly accelerated for large-scale datasets.

Heterogeneous Adaptive Preference Learning for Recommendation

Graph-based collaborative filtering techniques have emerged as a promising recommendation approach by modeling user-item interaction as graphs. Recently, contrastive learning has been employed in graph collaborative through data augmentation, which can effectively offer data efficiency and reduce labeling costs. Nonetheless, most existing contrastive learning approaches overlook the heterogeneous auxiliary information pertaining to users and items, such as user social relationships and item categories, which are crucial to alleviate the data sparsity issue. In this paper, we propose a novel contrastive learning method, referred to as Heterogeneous Adaptive Preference Learning for Recommendation (HAPLRec), which explicitly incorporates fine-grained preference information from both users and items. Specifically, we construct user relationship graphs and item relationship graphs based on specific meta-paths in a heterogeneous graph. Subsequently, we conduct data augmentation on these graphs individually to obtain auxiliary contrastive tasks. Moreover, we introduce an optimization algorithm that leverages the gradient similarity between the main task and the auxiliary tasks, dynamically adjusting the weight assigned to each task to expedite achieving superior performance within a shorter time frame. The effectiveness of the proposed model is demonstrated through extensive experiments conducted on three publicly available datasets.

Emerging Online Trends of Fashion Brands Buying: A Post-Pandemic Analysis

The COVID-19 pandemic emerged as a stronger predictor of transforming the world into a virtual world of social media and online communities. The year 2020 was seen as extraordinary amidst the pandemic, witnessing online trends in advertising, services, and buying. To understand this shift in online trends, this research used the adaptive structure framework, which suggests how technology helps users in decision-making. This study analyzed the audience’s buying behavior and the construction of social relationships in early & post-pandemic times, employing a longitudinal survey design. From November 2020 to July 2023, 3 surveys were conducted among Pakistani audiences, with a sample size of 200 each time. Results suggest that, after the pandemic, audiences explore the social media content of fashion products before actually buying them. Additionally, the online presence of fashion products, the adoption of technological applications in the fashion industry, and the role of social media as a tech assistant simultaneously affect the buying habits and social relationships of users.

Joint item recommendation and trust prediction with graph neural networks

Item recommendation and trust prediction are desired by users on social network platforms since they can help users find their favourite items or friends faster. Existing methods usually utilize users’ social relationships to facilitate the item recommendation task and leverage users’ preferences to assist the trust prediction task. While sociological researchers have shown that users’ preferences and users’ social relationships are not isolated but influenced by each other, there are a few studies that model these two tasks jointly. However, in these studies, the incorporation of distrust relations and the dynamic item-specific mutual influence between users’ preferences and users’ social relationships are ignored. In this paper, we propose a joint learning method using graph neural networks for item recommendation and trust prediction tasks, named JoRTGNN. First, users’ distrust relations are incorporated along with trust relations to extract more potential user social relationships, which can benefit both the item recommendation and trust prediction tasks. In addition, a dynamic item-specific mutual influence between users’ preferences and users’ social relationships is highlighted with attention mechanisms for the joint learning tasks. Experiments have been conducted on the Epinions datasets, and the experimental results show a superior performance of JoRTGNN over baselines in item recommendation and trust prediction tasks, which demonstrates that item recommendation and trust prediction can be effectively improved in the process of the mutual influence between users’ preferences and users’ social relationships.

A Social-aware Gaussian Pre-trained model for effective cold-start recommendation

The use of pre-training is an emerging technique to enhance a neural model’s performance, which has been shown to be effective for many neural language models such as BERT. This technique has also been used to enhance the performance of recommender systems. In such recommender systems, pre-training models are used to learn a better initialisation for both users and items. However, recent existing pre-trained recommender systems tend to only incorporate the user interaction data at the pre-training stage, making it difficult to deliver good recommendations, especially when the interaction data is sparse. To alleviate this rcommon data sparsity issue, we propose to pre-train the recommendation model not only with the interaction data but also with other available information such as the social relations among users, thereby providing the recommender rsystem with a better initialisation compared with solely relying on the ruser interaction data. We propose a novel recommendation model, the Social-aware Gaussian Pre-trained model (SGP), which encodes the user social relations and interaction data at the pre-training stage in a Graph Neural Network (GNN). Afterwards, in the subsequent fine-tuning stage, our SGP model adopts a Gaussian Mixture Model (GMM) to factorise these pre-trained embeddings for further training, thereby benefiting the cold-start users from these pre-built social relations. Our extensive experiments on three public datasets show that, in comparison to 16 competitive baselines, our SGP model significantly outperforms the best baseline by upto 7.7% in terms of NDCG@10. In addition, we show that SGP permits to effectively alleviate the cold-start problem, especially when users newly register to the system through their friends’ suggestions.

SSTP: Social and Spatial-Temporal Aware Next Point-of-Interest Recommendation

The expansion of available information in location-based social networks (LBSNs) has led to information overload, making it urgent to discover users’ next point-of-interest (POI). Some existing works only consider certain modal information in LBSNs and do not transform them into high-dimensional structures, which hinders the alleviation of the data sparsity problem. Moreover, many approaches rely solely on social relationships, making it difficult to recommend POIs to new users without association information. To tackle these challenges, we propose a social- and spatial–temporal-aware next point-of-Interest (SSTP) recommendation model. SSTP uses two feature encoders based on self-attention mechanism and gate recurrent unit to model users’ check-in enhancement sequence hierarchically. We also design a random neighborhood sampling approach to mine user social relationships, thus alleviating the user cold start problem. Finally, we propose a geographical-aware graph attention network to learn the sensitivity of users to distance. Extensive experiments on two real-world datasets show that SSTP outperforms state-of-the-art models, improving Hit@k by 2.26–6.55% and MAP@k by 3.49–6.55%. Moreover, SSTP has better performance on sparse data, with an average improvement of 6.09% on the Hit@k. The code can be downloaded at https://github.com/Rih0/sstp.

Community-based social recommendation under local differential privacy protection

Social recommendation refers to recommendation technology taking social relations as additional input to improve merchandise sales and user satisfaction. It has been widely used in various social networking services. Social recommendation requires the collection of each user's social relations to build a social graph, posing the risk of user privacy intrusion caused by untrusted servers. Local differential privacy is a widely adopted approach for providing privacy protection while allowing acceptable utility of the protected data for analytics. Growing research interest has been applying local differential privacy protection to social graph analysis. However, local differential privacy is suitable for analyzing coarse-grained statistics from perturbed user data, and it is difficult to obtain the fine-grained user relations needed for social recommendation. This paper proposes a novel locally differentially private social recommendation method. It first perturbs the degrees of users in a given interval and discovers coarse-grained communities from them, then generates a fine-grained social graph according to the features of intra-community and inter-community relations, thus ensuring the accuracy of the recommendation results. Experimental results show that the social recommendation accuracy of our proposed method improves by about 20% compared to existing methods in a community-structured ego-network dataset, and by about 10% in two non-community-structured page-page network datasets. The experimental results show that compared with the state-of-the-art methods such as LDPGen, LFGDPR, and AsgLDP, the social recommendation accuracy of our proposed method is improved by about 20% in one community-structured ego-network dataset, and 10% in two non-community-structured page-page network datasets.

User-Context Collaboration and Tensor Factorization for GNN-Based Social Recommendation

One goal of social recommendation is to utilize social information to alleviate data sparsity and improve recommendation accuracy. User social relationships are inherently graph-structured, graph neural network (GNN) has recently attracted extensive attention in social recommendation because of its capability to integrate structural information and topology. However, current graph neural network (GNN)-based social recommendation models fail to consider context information during user interactions, which hinders more accurate modeling of user interest features. To address this problem, we propose a new social recommendation model based on context-aware graph neural network named CENTRIC (User- <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b> ont <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</b> xt Collaboratio <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</b> and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</b> enso <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</b> Factorization for GNN-based Soc <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</b> al Re <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b> ommendation). Specifically, first a multi-channel GNN model with user-context collaboration module is designed, so that context can directly affect user features and participate in the calculation of user interaction probability with items. Then tensor factorization is adopted in output layer to effectively fuse the features extracted from different channels. Experiments on three public datasets show that CENTRIC significantly outperforms other state-of-the-art social recommendation models, further experiments also demonstrate that context information and tensor factorization help improve the accuracy of GNN-based social recommendation.

Social Recommendation Based on Multi-Auxiliary Information Constrastive Learning

Social recommendation can effectively alleviate the problems of data sparseness and the cold start of recommendation systems, attracting widespread attention from researchers and industry. Current social recommendation models use social relations to alleviate the problem of data sparsity and improve recommendation performance. Although self-supervised learning based on user–item interaction can enhance the performance of such models, multi-auxiliary information is neglected in the learning process. Therefore, we propose a model based on self-supervision and multi-auxiliary information using multi-auxiliary information, such as user social relationships and item association relationships, to make recommendations. Specifically, the user social relationship and item association relationship are combined to form a multi-auxiliary information graph. The user–item interaction relationship is also integrated into the same heterogeneous graph so that multiple pieces of information can be spread in the same graph. In addition, we utilize the graph convolution method to learn user and item embeddings, whereby the user embeddings reflect both user–item interaction and user social relationships, and the item embeddings reflect user–item interaction and item association relationships. We also design multi-view self-supervising auxiliary tasks based on the constructed multi-auxiliary views. Signals generated by self-supervised auxiliary tasks can alleviate the problem of data sparsity, further improving user/item embedding quality and recommendation performance. Extensive experiments on two public datasets verify the superiority of the proposed model.

Learning user sentiment orientation in social networks for sentiment analysis

Sentiment analysis on social networks mines users’ opinions, emotions, and attitudes to derive useful insights into community opinions and can improve the sales strategies of e-commerce platforms. Existing sentiment analysis methods are primarily based on complex user social relations and text data. However, they only use social relations among users and ignore the interactions of user sentiment orientation. In this paper, we designed a novel USON model to learn user sentiment orientation in social networks that fuses the interaction of users and their opinions. We define the score of the user sentiment orientation according to the sentiment polarity distribution of the opinion datasets. Then, we rebuilt a user social network, which is an attribute network with scores of user sentiment orientation as node attributes and social relations as edges. Finally, we integrated user representations with opinion representations for sentiment analysis. Experimental results on Amazon and Yelp show that the performance of our proposed model is significantly higher than that of state-of-the-art methods.

Web Service Applications and Consumer Environments Based on ICT-Driven Optimization

Networking is the use of physical links to connect individual isolated workstations or hosts together to form data links for the purpose of resource sharing and communication. In the field of web service application and consumer environment optimization, it has been shown that the introduction of network embedding methods can effectively alleviate the problems such as data sparsity in the recommendation process. However, existing network embedding methods mostly target a specific structure of network and do not collaborate with multiple relational networks from the root. Therefore, this paper proposes a service recommendation model based on the hybrid embedding of multiple networks and designs a multinetwork hybrid embedding recommendation algorithm. First, the user social relationship network and the user service heterogeneous information network are constructed; then, the embedding vectors of users and services in the same vector space are obtained through multinetwork hybrid embedding learning; finally, the representation vectors of users and services are applied to recommend services to target users. To verify the effectiveness of this paper’s method, a comparative analysis is conducted with a variety of representative service recommendation methods on three publicly available datasets, and the experimental results demonstrate that this paper’s multinetwork hybrid embedding method can effectively collaborate with multirelationship networks to improve service recommendation quality, in terms of recommendation efficiency and accuracy.

Exploring the effect of WeChat on adjustment of international students in China

WeChat is a popular social network application in China, which has fundamentally impacted users social interaction, communication, and personal relationships. In this study, we propose a conceptual...

Unifying Online and Offline Preference for Social Link Prediction

Recent advances in network representation learning have enabled significant improvement in the link prediction task, which is at the core of many downstream applications. As an increasing amount of mobility data become available because of the development of location-based technologies, we argue that this resourceful mobility data can be used to improve link prediction tasks. In this paper, we propose a novel link prediction framework that utilizes user offline check-in behavior combined with user online social relations. We model user offline location preference via a probabilistic factor model and represent user social relations using neural network representation learning. To capture the interrelationship of these two sources, we develop an anchor link method to align these two different user latent representations. Furthermore, we employ locality-sensitive hashing to project the aggregated user representation into a binary matrix, which not only preserves the data structure but also improves the efficiency of convolutional network learning. By comparing with several baseline methods that solely rely on social networks or mobility data, we show that our unified approach significantly improves the link prediction performance.Summary of Contribution: This paper proposes a novel framework that utilizes both user offline and online behavior for social link prediction by developing several machine learning algorithms, such as probabilistic factor model, neural network embedding, anchor link model, and locality-sensitive hashing. The scope and mission has the following aspects: (1) We develop a data and knowledge modeling approach that demonstrates significant performance improvement. (2) Our method can efficiently manage large-scale data. (3) We conduct rigorous experiments on real-world data sets and empirically show the effectiveness and the efficiency of our proposed method. Overall, our paper can contribute to the advancement of social link prediction, which can spur many downstream applications in information systems and computer science.

An improved user interest modelling by considering user social relationship

An improved user interest modelling by considering user social relationship

An improved user interest modelling by considering user social relationship

An improved user interest modelling by considering user social relationship

On Both Cold-Start and Long-Tail Recommendation with Social Data

The number of “hits” has been widely regarded as the lifeblood of many web systems, e.g., e-commerce systems, advertising systems and multimedia consumption systems. However, users would not hit an item if they cannot see it, or they are not interested in the item. Recommender system plays a critical role of discovering interesting items from near-infinite inventory and exhibiting them to potential users. Yet, two issues are crippling the recommender systems. One is “how to handle new users”, and the other is “how to surprise users”. The former is well-known as cold-start recommendation. In this paper, we show that the latter can be investigated as long-tail recommendation. We also exploit the benefits of jointly challenging both cold-start and long-tail recommendation, and propose a novel approach which can simultaneously handle both of them in a unified objective. For the cold-start problem, we learn from side information, e.g., user attributes, user social relationships, etc. Then, we transfer the learned knowledge to new users. For the long-tail recommendation, we decompose the overall interesting items into two parts: a low-rank part for short-head items and a sparse part for long-tail items. The two parts are independently revealed in the training stage, and transfered into the final recommendation for new users. Furthermore, we effectively formulate the two problems into a unified objective and present an iterative optimization algorithm. A fast extension of the method is proposed to reduce the complexity, and extensive theoretical analysis are provided to proof the bounds of our approach. At last, experiments of social recommendation on various real-world datasets, e.g., images, blogs, videos and musics, verify the superiority of our approach compared with the state-of-the-art work.

Hybrid graph convolutional networks with multi-head attention for location recommendation

Recommending yet-unvisited points of interest (POIs) which may be of interest to users is one of the fundamental applications in location-based social networks. It mainly replies on the understanding of users, POIs, and their interactions. Previous studies either develop matrix factorization-based approaches or utilize deep learning frameworks to learn better representation of users and POIs in order to estimate users’ latent preference. However, most of existing methods still confront the challenges like in traditional recommender systems, such as data sparsity and cold-start. In particular, they have difficulties in fully utilizing rich semantic information, such as social influence, geographical constraints and interactions between users and POIs. To fill this research gap, we propose a new recommendation framework – Hybrid Graph convolutional networks with Multi-head Attention for POI recommendation (HGMAP). HGMAP constructs a spatial graph based on the geographical distance between pairs of POIs and leverages Graph Convolutional Networks (GCNs) to express the high-order connectivity among POIs, which not only incorporates the spatial constraints but also provides an effective way to alleviate the sparse check-in problem. In addition, HGMAP exploits the user social relationship with another GCN and differentiates user preference over different aspects of POIs with a multi-head attention mechanism. We conducted extensive experiments on three public datasets and the results demonstrate that HGMAP significantly improves the recommendation performance over several state-of-the-art models, for example, up to approximately 4.8% and 7% for Precision@10 and Recall@10, respectively.

Urban Area Function Zoning Based on User Relationships in Location-Based Social Networks

With advanced development of Internet communication and ubiquitous computing, Social Networks are providing an important information channel for smart city construction. Therefore, analyzing Location-based Social Network is a very valuable work in achieving reasonable urban zoning. In Social Networks, a main purpose of prestige assessment is to extract influential users who are regarded as the key nodes for community detection from Onine Social Networks (OSNs). However, social relationships of users are rarely used to evaluate the popularity of physical locations and zone physical locations. In order to achieve urban area function zoning by evaluating the prestige of geographic regions based on user relationships in Location based Social Networks (LBSNs), this paper proposes a Prestige Density-Based Spatial Clustering of Applications with Noise algorithm (P-DBSCAN) by improving the existing DBSCAN algorithm. Specifically, the algorithm first calculates the centrality of users in the social network, and then converts the centrality of users into the location-centrality through the users’ check-in data. After the centrality of each location is obtained, the discrete locations are clustered according to four constraints of the given radius. After clustering, the result of urban area function zoning can be achieved. Extensive experiments are conducted for demonstrating the effectiveness of our proposed algorithm in this paper. In addition, the visualization results reveal the correctness of our proposed approach.

Network Coding-Based Socially-Aware Caching Strategy in D2D

By caching the most popular content into mobile devices, users can retrieve content directly from nearby devices through Device to Device (D2D) communications, which can significantly reduce backhaul traffic and improve network performance. Most existing D2D cache placement strategies are proactive approaches, which cannot deal with the problem of timely cache updating. In this paper, we propose a network coding-based socially-aware D2D caching strategy, which takes geographical proximity and the social relationships of users into consideration. First, a physical D2D network with high communication reliability is built according to the geographical proximity, composed of devices with high probability of communicating to each other through stable D2D communications. According to the social relationship between users within the physical D2D network, we partition the devices into communities and rank the devices within same community by their influence degree. Within a community, each caching decision is made independently according to the user-content contribution degree. To calculate the contribution degree, the impact between devices on requesting same content is modeled using an Indian Buffet Process. Devices cache coded blocks instead of the whole content to improve caching efficiency. Simulation results show that the proposed strategy achieves higher cache hit and sum rates compared to other schemes.

Personalized travel route recommendation algorithm based on improved genetic algorithm

The analysis of user trajectory information and social relationships in social media, combined with the personalization of travel needs, allows users to better plan their travel routes. However, existing methods take only local factors into account, which results in a lack of pertinence and accuracy for the recommended route. In this study, we propose a method by which user clustering, improved genetic, and rectangular region path planning algorithms are combined to design personalized travel routes for users. First, the social relationships of users are analyzed, and close friends are clustered into categories to obtain several friend clusters. Next, the historical trajectory data of users in the cluster are analyzed to obtain joint points in the trajectory map, these are matched according to the keywords entered by users. Finally, the search area is narrowed and the recommended travel route is obtained through improved genetic and rectangular region path planning algorithms. Theoretical analyses and experimental evaluations show that the proposed method is more accurate at path prediction and regional coverage than other methods. In particular, the average area coverage rate of the proposed method is better than that of the existing algorithm, with a maximum increasement ratio of 31.80%.