Set-Sequence-Graph: A Multi-View Approach Towards Exploiting Reviews for Recommendation

Gao, Jingyue; Yang, Lin; Wang, Yasha; Wang, Xiting; Zhao, Youjian; He, Yuanduo; Chu, Xu

doi:10.1145/3340531.3411939

Cited by 30 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the most extensively studied research topics involving personalization in E-Commerce is the personalized recommendation [24,67], which typically explores the utilities of user-item interaction data to model the user preferences towards different items. Recently, several attempts [21,25,49] have been made on leveraging UGC data, such as reviews, for personalized recommendation. The UGC data can not only be served as a measurement of semantic relevance for user preference modeling [64], but also be adopted as the explicit justifications for explainable recommendation [11].…”

Section: Personalization With Ugc In E-commercementioning

confidence: 99%

Toward Personalized Answer Generation in E-Commerce via Multi-perspective Preference Modeling

Deng

Zhang

et al. 2022

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

Recently, Product Question Answering (PQA) on E-Commerce platforms has attracted increasing attention as it can act as an intelligent online shopping assistant and improve the customer shopping experience. Its key function, automatic answer generation for product-related questions, has been studied by aiming to generate content-preserving while question-related answers. However, an important characteristic of PQA, i.e., personalization, is neglected by existing methods. It is insufficient to provide the same “completely summarized” answer to all customers, since many customers are more willing to see personalized answers with customized information only for themselves, by taking into consideration their own preferences towards product aspects or information needs. To tackle this challenge, we propose a novel P ersonalized A nswer GE neration method ( PAGE ) with multi-perspective preference modeling, which explores historical user-generated contents to model user preference for generating personalized answers in PQA. Specifically, we first retrieve question-related user history as external knowledge to model knowledge-level user preference. Then we leverage Gaussian Softmax distribution model to capture latent aspect-level user preference. Finally, we develop a persona-aware pointer network to generate personalized answers in terms of both content and style by utilizing personal user preference and dynamic user vocabulary. Experimental results on real-world E-Commerce QA datasets demonstrate that the proposed method outperforms existing methods by generating informative and customized answers, and show that answer generation in E-Commerce can benefit from personalization.

show abstract

Section: Personalization With Ugc In E-commercementioning

confidence: 99%

Toward Personalized Answer Generation in E-Commerce via Multi-perspective Preference Modeling

Deng

Zhang

et al. 2022

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

show abstract

“…The prediction is calculated based on the concatenation of learned representations based on review features and node embeddings. Moreover, Gao et al [11] designed a novel Set-Sequence-Graph (SSG) network to jointly model the multi-view historical reviews, user-item sequences, and the user-item bipartite graph for better user and item embedding learning.…”

Section: Related Work 21 Review-based Recommendationmentioning

confidence: 99%

“…• SSG [11] jointly models review sets, review sequences, and user-item graphs. The authors design the Review-aware graph attention network (RGAT) to capture the graph signals for the user-item graph.…”

Section: Baselinesmentioning

confidence: 99%

“…Above mentioned methods can briefly categorized into five groups: (1) Traditional rating-based collaborative filtering methods, SVD [21] and NCF [15]; (2) Historical review-based methods: DeepCoNN [54], NARRE [6], DAML [24]; (3) Target review-based methods: TransNets [5], SDNet [9]; (4) Graph-based method: GC-MC [37]. ( 5) Graph and review fusing methods: RMG [43] and SSG [11]. We have to note that we reimplement RMG, replace the attentive graph neural with GC-MC, and assign separate convolution channels for each rating of RGAT in SSG for a fair comparison.…”

Section: Baselinesmentioning

confidence: 99%

See 1 more Smart Citation

A Review-aware Graph Contrastive Learning Framework for Recommendation

Shuai,

Zhang,

et al. 2022

Preprint

View full text Add to dashboard Cite

Most modern recommender systems predict users' preferences with two components: user and item embedding learning, followed by the user-item interaction modeling. By utilizing the auxiliary review information accompanied with user ratings, many of the existing review-based recommendation models enriched user/item embedding learning ability with historical reviews or better modeled user-item interactions with the help of available user-item target reviews. Though significant progress has been made, we argue that current solutions for review-based recommendation suffer from two drawbacks. First, as review-based recommendation can be naturally formed as a user-item bipartite graph with edge features from corresponding user-item reviews, how to better exploit this unique graph structure for recommendation? Second, while most current models suffer from limited user behaviors, can we exploit the unique self-supervised signals in the review-aware graph to guide two recommendation components better? To this end, in this paper, we propose a novel Review-aware Graph Contrastive Learning (RGCL) framework for review-based recommendation. Specifically, we first construct a review-aware user-item graph with feature-enhanced edges from reviews, where each edge feature is composed of both the user-item rating and the corresponding review semantics. This graph with feature-enhanced edges can help attentively learn each neighbor node weight for user and item representation learning. After that, we design two additional contrastive learning tasks (i.e., Node Discrimination and Edge Discrimination) to provide self-supervised signals for the two components in recommendation process. Finally, extensive experiments over five benchmark datasets demonstrate the superiority of our proposed RGCL compared to the state-of-the-art baselines.

show abstract

“…For review based recommendation, researchers argued that most content based user and item representation models neglected the interaction behavior between user-item pairs, and a dual attention model named DAML is proposed to learn the mutual enhanced user and item representations [96]. As item content sometimes is presented in multi-view forms (e.g., title, body, keywords and so on), multi-view attention networks are applied to learn unified item representations by aggregating multiple representations from different views [97], [98], [99]. With both the textual descriptions and the image visual information, co-attention is utilized to learn the correlation between the two modalities for better item representation learning [100], [101].…”

Section: Modeling Textual Contentmentioning

confidence: 99%

A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation

Wu,

He,

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

Influenced by the stunning success of deep learning in computer vision and language understanding, research in recommendation has shifted to inventing new recommender models based on neural networks. In recent years, we have witnessed significant progress in developing neural recommender models, which generalize and surpass traditional recommender models owing to the strong representation power of neural networks. In this survey paper, we conduct a systematic review on neural recommender models, aiming to summarize the field to facilitate future progress. Distinct from existing surveys that categorize existing methods based on the taxonomy of deep learning techniques, we instead summarize the field from the perspective of recommendation modeling, which could be more instructive to researchers and practitioners working on recommender systems. Specifically, we divide the work into three types based on the data they used for recommendation modeling: 1) collaborative filtering models, which leverage the key source of user-item interaction data; 2) content enriched models, which additionally utilize the side information associated with users and items, like user profile and item knowledge graph; and 3) context enriched models, which account for the contextual information associated with an interaction, such as time, location, and the past interactions. After reviewing representative works for each type, we finally discuss some promising directions in this field, including benchmarking recommender systems, graph reasoning based recommendation models, and explainable and fair recommendations for social good.

show abstract

Set-Sequence-Graph: A Multi-View Approach Towards Exploiting Reviews for Recommendation

Cited by 30 publications

References 25 publications

Toward Personalized Answer Generation in E-Commerce via Multi-perspective Preference Modeling

Toward Personalized Answer Generation in E-Commerce via Multi-perspective Preference Modeling

A Review-aware Graph Contrastive Learning Framework for Recommendation

A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation

Contact Info

Product

Resources

About