Case amazon

Leino, Juha; Räihä, Kari-Jouko

doi:10.1145/1297231.1297255

Cited by 30 publications

(3 citation statements)

References 5 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Best/Worst It has been shown [29] that looking at the best/worst reviews is beneficial when a user makes a decision about an item. Extending this idea to Active Learning we hypothesize with the "best/worst" principle that in order to make a decision about a user's preferences it may also be beneficial to obtain his/her best/worst ratings (as it may capture user preferences well).…”

Section: Other Considerationsmentioning

confidence: 99%

Active Learning in Recommender Systems

Rubens

Elahi

Sugiyama

et al. 2015

Recommender Systems Handbook

155

139

View full text Add to dashboard Cite

Section: Other Considerationsmentioning

confidence: 99%

Active Learning in Recommender Systems

Rubens

Elahi

Sugiyama

et al. 2015

Recommender Systems Handbook

155

139

View full text Add to dashboard Cite

“…In fact, consumers' economic incentives play an important role when making decisions in online economic systems such as ecommerce [14,51]. A common observation in practical recommendation systems is that customers may use rating scores and review information to support their buying decisions [26,28,33]. According to this information, buyers can infer the quality of products to avoid wasting time and reduce the risk of purchase.…”

Section: Introductionmentioning

confidence: 99%

Learning Personalized Risk Preferences for Recommendation

Liu

et al. 2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

The rapid growth of e-commerce has made people accustomed to shopping online. Before making purchases on e-commerce websites, most consumers tend to rely on rating scores and review information to make purchase decisions. With this information, they can infer the quality of products to reduce the risk of purchase. Specifically, items with high rating scores and good reviews tend to be less risky, while items with low rating scores and bad reviews might be risky to purchase. On the other hand, the purchase behaviors will also be influenced by consumers' tolerance of risks, known as the risk attitudes. Economists have studied risk attitudes for decades. These studies reveal that people are not always rational enough when making decisions, and their risk attitudes may vary in different circumstances. Most existing works over recommendation systems do not consider users' risk attitudes in modeling, which may lead to inappropriate recommendations to users. For example, suggesting a risky item to a risk-averse person or a conservative item to a risk-seeking person may result in the reduction of user experience. In this paper, we propose a novel risk-aware recommendation framework that integrates machine learning and behavioral economics to uncover the risk mechanism behind users' purchasing behaviors. Concretely, we first develop statistical methods to estimate the risk distribution of each item and then draw the Nobel-award winning Prospect Theory into our model to learn how users choose from probabilistic alternatives that involve risks, where the probabilities of the outcomes are uncertain. Experiments on several e-commerce datasets demonstrate that by taking user risk preferences into consideration, our approach can achieve better performance than many classical recommendation approaches, and further analyses also verify the advantages of risk-aware recommendation beyond accuracy. CCS CONCEPTS • Information systems → Recommender systems; • Applied computing → Economics; • Computing methodologies → Intelligent agents.

show abstract

“…Recommender systems, which predict user preferences from historical records, play a crucial role in helping customers with their decision-making process [1,44,60]. Recently, a variety of Review-Based Recommender Systems (RBRS) have been proposed to incorporate textual reviews from users for user modeling and recommendation processes [5,12,32,35,45,56,61], and have been applied to real-world e-commerce systems [25]. For instance, Zheng et al [61] is the first work that uses convolutional neural networks (CNNs) to encode user and item review information, while subsequent works further leverage advanced techniques such as attention mechanisms [49] to encode review information [5,12,35] or construct a graph structure for modeling user-item interactions [45,56].…”

Section: Introductionmentioning

confidence: 99%

Shilling Black-box Review-based Recommender Systems through Fake Review Generation

Chiang

Chen

Song

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Review-Based Recommender Systems (RBRS) have attracted increasing research interest due to their ability to alleviate wellknown cold-start problems. RBRS utilizes reviews to construct the user and items representations. However, in this paper, we argue that such a reliance on reviews may instead expose systems to the risk of being shilled. To explore this possibility, in this paper, we propose the first generation-based model for shilling attacks against RBRSs. Specifically, we learn a fake review generator through reinforcement learning, which maliciously promotes items by forcing prediction shifts after adding generated reviews to the system. By introducing the auxiliary rewards to increase text fluency and diversity with the aid of pre-trained language models and aspect predictors, the generated reviews can be effective for shilling with high fidelity. Experimental results demonstrate that the proposed framework can successfully attack three different kinds of RBRSs on the Amazon corpus with three domains and Yelp corpus. Furthermore, human studies also show that the generated reviews are fluent and informative. Finally, equipped with Attack Review Generators (ARGs), RBRSs with adversarial training are much more robust to malicious reviews. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Case amazon

Cited by 30 publications

References 5 publications

Active Learning in Recommender Systems

Active Learning in Recommender Systems

Learning Personalized Risk Preferences for Recommendation

Shilling Black-box Review-based Recommender Systems through Fake Review Generation

Contact Info

Product

Resources

About