Multimodal data can more comprehensively portray changes in user interests, and thus, multimodal sequential recommendation (MSRS) has gained widespread attention in recent years. However, the MSRS faces two key challenges: (1) how to effectively model long-range dependencies in user interaction sequence; and (2) how to efficiently fuse multimodal features. To address these challenges, this article proposes a novel multimodal sequential recommendation architecture based on pure convolutional neural network (CNN), named PCMSRec. PCMSRec contains two key innovations: first, by using the global receptive field of large kernel convolution, it models the long-range dependencies of multimodal user interaction sequence, breaking through the limitation that existing CNN-based methods can only capture local short-distance dependencies; second, by taking advantage of the high flexibility of the CNN architecture, it models the relationships among multimodal features of items through a carefully designed convolutional layer architecture and fusion strategy. Specifically, PCMSRec consists of two blocks: sequence-feature block and modal block. The sequence-feature block models long-range dependencies in user interaction sequence through large kernel convolutional layer and extracts item features by incorporating a bottleneck architecture. The modal block models the complex relationships between multimodal features using multiple convolutional layer. Experimental results on five public datasets show that PCMSRec outperforms existing methods.

The Next POI recommendation, which has attracted many attentions recently, is a complex study due to the sparsity of check-in data and numerous sequential patterns. The recent methods based on sequential modeling have shown promising applicability for this task. However, most of existing next POI recommendation researches only model users’ preferences based on their own sequences and ignore the influence of partners who visit POI with the target user and may change with time. Inspired by dynamic Graph neural networks, we propose a Group-aware Dynamic Graph Representation Learning (GDGRL) method for next POI recommendation. GDGRL connects different user sequences and specific partners via dynamic graph structure, which contains interactions between users and POIs as well as influence of partners. The users’ dynamic preferences are learned from group-aware dynamic graph and context-aware dynamic graph through dynamic graph neural networks. Finally, the next POI recommendation task is transformed into a link prediction between user node and POI node in the dynamic graph. Extensive experiments on two real-world datasets show that GDGRL outperforms several state-of-the-art approaches.

Recommendations for events play a pivotal role in facilitating the discovery of upcoming intriguing events within Event-Based Social Networks (EBSNs). Previous research has established the crucial significance of mining contextual features and implicit relationships to enhance recommendation performance and alleviate data sparsity issues. However, the noise inherent in contextual features exacerbates data sparsity and hampers the ability of previous methods to explore implicit relationships for mitigating data sparsity. To address this challenge, we propose a variational type graph autoencoder model that attenuates the influence of noise in different types of context features by introducing type-specific latent variables. First, we introduce a heterogeneous denoising convolution module composed of two components: (1) Denoising attention aggregation is proposed to mitigate the influence of noisy structures and uncover implicit relationships. (2) A heterogeneous normalization module leverages context features within the same type to alleviate the effects of noise in context features and data sparsity. Furthermore, we propose a learnable heterogeneous mixture prior that assists in assigning different priors to distinct types of latent variables, effectively modeling different types of contextual features. Through comprehensive experiments conducted on real-world datasets, we demonstrate the compelling performance of our model compared to state-of-the-art competitive approaches.

Point of interest (POI) recommendation has received significant attention in recent years, most existing studies exploit multiple auxiliary information to alleviate the problem of data sparsity, and consider the sequential features of user mobility. However, few studies consider the category-level characteristics derived from each user's historical check-in frequencies, and the characteristics between different latent factors. In this paper, we exploit category-level multiple characteristics to generate recommendation. First, we obtain the frequency characteristics by in-depth analysis of the historical check-in frequencies for different categories by each user, and propose a scheme including KL-divergence and text analysis algorithm. Then we propose a category-level sequential- and non-sequential influence-aware probabilistic generative model (CSNS), which models the characteristics (correlation and indeterminate decisiveness) between user latent behavior topics and latent sequence patterns. We design two stages to generate recommendations. In the first stage, CSNS and frequencies characteristics are exploited jointly to recommend the POI categories that users may visit. In the second stage, we depend on user profiles and poi features, and sort the candidate POI sets by combining the POI categories provided in the first stage. Comprehensive experiments on two real-world datasets demonstrate that our method outperforms the existing state-of-the-art POI recommendation models.

In recent years, context-aware recommender systems (CARSs), which incorporate contextual information to achieve better recommendations, become a hot topic in the domain of recommender systems. Many context-aware recommendation methods have been proposed in the past decades. Some literatures provide survey of the research on CARSs. However, they mainly focus on context-aware recommendation methods and overlook the evaluation of them. The evaluation methods, evaluation properties and datasets of CARSs are different from those of traditional recommender systems where contexts are not considered. In this paper, we provide a review for evaluation of CARSs. We will introduce the basic concepts of CARSs, propose a new dataset partition method for each category of CARSs according to our classification of CARSs, summarize the evaluation method. Then we summarize the evaluation properties that CARSs pays attention to, which are different from the NCARSs. In addition, we also summarize the datasets specifically for CARSs, its applicable CARSs type and its evaluation dimensions and metrics. Based on our review, we draw some conclusions from evaluation perspective and point out future research directions.

Location-based social networks (LBSNs) have become a popular platform for users to share their activities with friends and families, which provide abundant information for us to study issues of group venue recommendation by utilizing the characteristics of check-in data. Although there are some studies on group recommendation for venues, few studies consider the group’s venue preference in different temporal patterns. In this article, we discover that the group’s activity venue has a temporal effect, that is, the group’s preference for the activity venue is different at different times. For example, a couple of lovers prefer to travel to tropical regions in winter and relax in bars in the evening. Based on this discovery, we present a Time-aware Multi-pattern (TaMp) topic model to capture the group’s interest in the activity venue in multiple temporal patterns (including the daily pattern, the weekly pattern, the monthly pattern, and the quarterly pattern). The TaMp model takes into account the topic, members, temporality, and venue information of group activities and the latent relations among them, especially the strong correlation between the activity time and the corresponding activity venue. Then, we propose a group venue recommendation method based on the TaMp model. In addition, an improved grouping algorithm (iGA) in LBSNs is put forward to enhance the rationality of grouping and the accuracy of group venue recommendation. We conduct comprehensive experiments to evaluate the performance of TaMp on two real-world datasets. The results show that our proposed method outperforms the state-of-the-art group venue recommendation and demonstrates the significance of temporal effects in explaining group activities.

Personalized venues recommendation is essential to help people find attractive venue to visit as growth of location-based social networks. Existing approaches never distinguish user individual interests from her social preferences, which leads to a bottleneck of modeling user check-in behaviors accurately. In this paper, we find the differences between user interests and her social preferences clearly and investigate the time law of user check-in behaviors in depth. Consequently, we propose a social-period-aware topic model (SPATM) to learn the influence weights of both user interests and her social preferences on making-decision for each check-in time automatically. Especially, we model latent topic by leveraging smaller size of dynamic activities instead of static categories, which can alleviate the data sparsity problem by using more co-occurrent activities information. Moreover, our approach can automatically judge whether a user’s social preference is periodic or aperiodic and learn the periodicity of periodic one. Furthermore, the Alias Sampling based training approach is introduced to improve sampling efficiency. The results demonstrate our proposed model is effective and outperforms the state-of-the-art approaches in terms of effectiveness and efficiency. Besides, SPATM can learn semantically coherent latent topics and geographically dispersed latent social topics which are useful to explain recommendation.

Newly emerging Event-based Social Network (EBSN) concentrates on connecting both online social relationships and offline local events. For the growing amount of events published on EBSNs, personalized event recommendation becomes essential to help users choose attractive events. But most of existing event recommendation algorithms fail to distinguish constraint factors of users’ event participation behaviors from preference factors, which reflects the cost of event participation that hinders users from attending interested events. To take full advantage of influences from contextual information on users’ event participation, we differentiate preference and constraint factors which contribute to users’ decision for event participation, and extract the soft spatial and temporal constraints from event venue and start time contexts respectively. Then we propose the Preference and Constraint Factor Model (PCFM) based on factorization machine model, using attentive mechanism to weight feature interactions and incorporate latent factors of users and contextual features for personalized perference modeling and event recommendation. Moreover, learning-to-rank techniques are utilized to train PCFM as a ranking model for the implicit feedback nature of responses from users. Extensive experiments evaluate the performance of our proposed recommendation model on real-world EBSN datasets, and demonstrate the outperformance than state-of-art event recommendation methods on many metrics.

POI recommendation has become an essential means to help people discover attractive places. Intuitively, activities have an important impact on users’ decision-making, because users select POIs to attend corresponding activities. However, many existing studies ignore the social motivation of user behaviors and regard all check-ins as influenced only by individual user interests. As a result, they cannot model user preferences accurately, which degrades recommendation effectiveness. In this article, from the perspective of activities, this study proposes a probabilistic generative model called STARec. Specifically, based on the social effect of activities, STARec defines users’ social preferences as distinct from their individual interests and combines these with individual user activity interests to effectively depict user preferences. Moreover, the inconsistency between users’ social preferences and their decisions is modeled. An activity frequency feature is introduced to acquire accurate user social preferences because of close correlation between these and the key impact factor of corresponding check-ins. An alias sampling-based training method was used to accelerate training. Extensive experiments were conducted on two real-world datasets. Experimental results demonstrated that the proposed STARec model achieves superior performance in terms of high recommendation accuracy, robustness to data sparsity, effectiveness in handling cold-start problems, efficiency, and interpretability.