Despite increasing research on product rating prediction, very few studies have considered user-item interaction relationships at multiple levels. To address this critical limitation, we propose a novel rating prediction method based on multi-interaction attention (RPMIA) by learning user-item interaction relationships at three levels simultaneously from online consumer reviews for predicting product ratings with reasonable interpretability. Specifically, RPMIA first deploys a multihead cross-attention mechanism to capture the interaction between contexts of items and users. Then, it uses a bilayer gate-based mechanism to extract the aspects of items and users and a self-attention mechanism to learn their interaction at the aspect level. Finally, the aspects of users and items are coupled together to form meaningful user-item aspect pairs via a joint attention. A multitask predictor that integrates a factorization machine and a feedforward neural network is designed to generate a rating prediction. We empirically evaluated RPMIA with seven real-world data sets. The results demonstrate that RPMIA outperforms the state-of-the-art methods consistently and significantly. We also conduct a user study to assess the interpretability of the RPMIA method. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: The research is supported by Beijing Social Science Foundation [24XCB012], Suzhou Key Laboratory of Artificial Intelligence and Social Governance Technologies [SZS2023007], and Smart Social Governance Technology and Innovative Application Platform [YZCXPT2023101]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0131 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0131 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

The live streaming e-commerce paradigm is experiencing a meteoric surge, distinguished by hosts dynamically showcasing products via live videos and fostering interactive engagement with their viewers. Although a streamer may not cater to every individual’s tastes, it is imperative that it resonates with the majority of viewers’ preferences. Nevertheless, a common challenge arises when the products featured in the live streams often fail to align with the collective interests of the viewers in the live rooms, leading to a significant portion of them disengaging from the broadcast due to a lack of interest in the streamed content. To address this issue, we introduce an Attention-based Group Recommendation for E-commerce Live Stream viewers (AGES). Specifically, AGES employs a dual-attention network that meticulously captures the nuanced preferences of viewer groups in a live streaming room. Furthermore, the product representation is intricately crafted from viewer-product interaction data, coupled with insights into the similarities among products broadcasted by the streamers. To validate the efficacy of AGES, we conduct a comprehensive comparison against existing live recommendation models on two real datasets. The results show its superior performance and demonstrate its ability to better align with the diverse preferences of e-commerce live stream viewers.

Personalized micro video recommendation aims to recommend the micro videos tailored to user preference based on the user’s interaction history with the micro videos, which has drawn increasing attention from both the academic and industrial communities. Existing solutions primarily concentrate on video-level interactions between users and micro videos to model their preferences, and cannot distinguish the finer-grained users’ interactions with various modalities. Ignoring modality-level interactions prevents the full understanding of the user’s true and subtle preferences on micro videos. To this end, in this article, we propose a Contrastive Multimodal Interaction Graph Learning ( MVideoRec ) model to automatically and explicitly learn the modality-level interaction between users and micro videos for recommendations. Specifically, we designed a graph structure learning module with a sparsification strategy to infer modality-level interaction graph, which will be dynamically and iteratively updated based on the node representations obtained from the node representation learning module. Furthermore, to address the lack of ground truth labels, we propose to generate teacher view from video-level interaction graph and student view from modality-level interaction graph, as well as construct intra-modality and inter-modality contrastive pairwise instances to provide self-supervised signals. Extensive experiments on three real-world micro video datasets validate the effectiveness of MVideoRec.

Cross-domain recommender systems could potentially improve the recommendation performance by means of transferring abundant knowledge from the auxiliary domain to the target domain. They could help address some key challenges in recommender systems, such as data sparsity and cold start. However, most existing cross-domain recommendation approaches represent the user preferences based on a single kind of user’s feature or behavior and fail to explore the hidden interaction effects of different kinds of features or behaviors. In this article, we propose the S equential and G raphical Cross -Domain Recommendations with a Multi-View Hierarchical Transfer Gate (SGCross) to transfer user representations from multiple perspectives. The SGCross model constructs a user profile by learning the personal preference from a personal view, the dynamic preference from a temporal view, as well as the collaborative preference from a collaborative view. Specifically, a Multi-view Hierarchical Gate (MHG) is designed to transfer the informative representations of user knowledge on different views from the auxiliary domain separately, aiming to enhance the user representations. Furthermore, a two-stage attentive fusion module is designed to integrate transferred information at two levels: the domain level and the view level. Extensive experiments on the Amazon dataset and the Douban dataset have demonstrated that SGCross effectively improves the accuracy of cross-domain recommendations and outperforms the state-of-the-art baseline models.

Serendipity is a notion that means an unexpected but valuable discovery. Due to its elusive and subjective nature, serendipity is difficult to study even with today's advances in machine learning and deep learning techniques. Both ground truth data collecting and model developing are the open research questions. This paper addresses both the data and the model challenges for identifying serendipity in recommender systems. For the ground truth data collecting, it proposes a new and scalable approach by using both user generated reviews and a crowd sourcing method. The result is a large-scale ground truth data on serendipity. For model developing, it designed a self-enhanced module to learn the fine-grained facets of serendipity in order to mitigate the inherent data sparsity problem in any serendipity ground truth dataset. The self-enhanced module is general enough to be applied with many base deep learning models for serendipity. A series of experiments have been conducted. As the result, a base deep learning model trained on our collected ground truth data, as well as with the help of the self-enhanced module, outperforms the state-of-the-art baseline models in predicting serendipity.

Next basket recommendation aims to provide users a basket of items on the next visit by considering the sequence of their historical baskets. However, since a user’s purchase interests vary over time, historical baskets often contain many irrelevant items to his/her next choices. Therefore, it is necessary to denoise the sequence of historical baskets and reserve the indeed relevant items to enhance the recommendation performance. In this work, we propose a Hierarchical Reinforcement Learning framework for next Basket recommendation, named HRL4Ba, which learns the personalized inter-basket and intra-basket contexts of the user for dynamic denoising. Specifically, the high-level and the low-level agent in the denoising module perform hierarchical decisions, i.e., revise baskets and remove items; the recommendation module serves as the environment to give feedback to agents and recommends the next basket. Extensive experiments on two e-commerce datasets show the HRL4Ba outperforms existing state-of-the-art methods, and our ablation studies further show the effectiveness of each component in HRL4Ba.

Social recommendation (SR) aims to enhance the performance of recommendations by incorporating social information. However, such information is not always reliable, e.g., some of the friends may share similar preferences with the user on a specific item, while others may be irrelevant to this item due to domain differences. Therefore, modeling all of the user’s social relationships without considering the relevance of friends will introduce noises to the social context. To address this issue, in this work, we propose a Denoisingguided deep Reinforcement Learning framework for Social recommendation (DRL4So). Specifically, the agent (i.e., social denoiser) in our framework automatically masks the user’s friends who are irrelevant to the target item; Then, the environment (i.e., recommender) is designed to give rewards to the agent for social denoising without supervised signals; Finally, the two components are jointly trained by DPG to ensure that social denoising correctly guides the recommendation. We conduct extensive experiments on three public datasets, and the results show that DRL4So outperforms existing state-of-the-art SR methods (improving 38.67% and 19.81% in terms of HR@10 and NDCG@10, respectively).

Personalized recommendation of micro-videos is crucial for many content sharing platforms. Micro-videos typically com-prise fruitful multimodal contents. Existing methods have limitations in learning multimodal representations: (i) They suffer from data sparsity problems as only rely on the inter-action prediction loss to train the whole model. (ii) They do not consider the correlation among multimodal contents into the representation learning. To tackle these limitations, we propose a cross-Modal context enhanced method via Mutual infoMax for Recommendation, termed M3Rec. Specifically, we design the cross-modal graph neural network to inter-change multimodal information to generate modality-aware representations. Then, based on the coupled modality con-text, we design the masked modality prediction (MMP) with three self-supervised objectives to learn the correlation among visual, textual, and acoustic contents empowered by the mu-tual information maximization principle. Finally, we enhance representations via self-supervised pre-training to boost rec-ommendation. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art methods.

As the popularity of online travel platforms increases, users tend to make ad-hoc decisions on places to visit rather than preparing the detailed tour plans in advance. Under the situation of timeliness and uncertainty of users’ demand, how to integrate real-time context into dynamic and personalized recommendations have become a key issue in travel recommender system. In this article, by integrating the users’ historical preferences and real-time context, a location-aware recommender system called TRACE ( T ravel R einforcement Recommendations Based on Location- A ware C ontext E xtraction) is proposed. It captures users’ features based on location-aware context learning model, and makes dynamic recommendations based on reinforcement learning. Specifically, this research: (1) designs a travel reinforcing recommender system based on an Actor-Critic framework, which can dynamically track the user preference shifts and optimize the recommender system performance; (2) proposes a location-aware context learning model, which aims at extracting user context from real-time location and then calculating the impacts of nearby attractions on users’ preferences; and (3) conducts both offline and online experiments. Our proposed model achieves the best performance in both of the two experiments, which demonstrates that tracking the users’ preference shifts based on real-time location is valuable for improving the recommendation results.

Cross-domain recommendation (CDR) technology is proved to be an effective way to tackle the difficulties encountered by traditional recommender technology (e.g. CF), such as data sparsity and cold-start. However, on account of the heterogeneity, it is difficult to enhance the representation of user preferences with the informative knowledge of shared user learned from auxiliary domain. In this paper, we propose a CDR method with co-capsule networks based knowledge transfer to implement the recommendation for the cold-start users. Concretely, the model captures the preference of users with a two-tier structure, the attentive GRU is employed to learn the primary intent from item level and the capsule network is used to further refer the user interests in feature level. After studying the mapping matrix, NeuMF is adapted to execute the recommendation task. We conduct extensive experiments on public datasets and the results demonstrate that the proposed model outperforms many state-of-the-art models.

Nowadays, there are more and more papers submitted to various periodicals and conferences. Typically, reviewers need to read through the paper and give a review comment and score to it based on somehow certain criterion. This review process is labor intensive and time-consuming. Recently, AI technology is widely used to alleviate human labor burden. Can machine learn from human to review papers automatically? In this paper, we propose a collaborative grammar and innovation model - DeepReviewer to achieve automatic paper review. This model learning the semantic, grammar and innovative features of an article by three main well-designed components simultaneously. Moreover, these three factors are integrated by an attention layer to get the final review score of the paper. We crawled paper review data from Openreview and built a real data set. Experimental results demonstrate that our model exceeds many baselines.