A Study of Context Dependencies in Multi-page Product Search

Bi, Keping; Teo, Choon Hui; Dattatreya, Yesh; Mohan, Vijai; Croft, W. Bruce

doi:10.1145/3357384.3358095

Cited by 9 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates that incorporating aspect-value information into search optimizations is generally beneficial for the performance of product search systems. 4 After a 5-round iterative feedback process, we observe different results for different feedback models. For term-based negative feedback models such as Rocchios, SingleNeg, and MultiNeg, we observe little performance improvement during the feedback process.…”

Section: Overall Retrieval Performancementioning

confidence: 96%

See 1 more Smart Citation

Conversational Product Search Based on Negative Feedback

Zhang

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

Intelligent assistants change the way people interact with computers and make it possible for people to search for products through conversations when they have purchase needs. During the interactions, the system could ask questions on certain aspects of the ideal products to clarify the users' needs. For example, previous work proposed to ask users the exact characteristics of their ideal items [27,37] before showing results. However, users may not have clear ideas about what an ideal item looks like, especially when they have not seen any item. So it is more feasible to facilitate the conversational search by showing example items and asking for feedback instead. In addition, when the users provide negative feedback for the presented items, it is easier to collect their detailed feedback on certain properties (aspect-value pairs) of the non-relevant items. By breaking down the item-level negative feedback to fine-grained feedback on aspect-value pairs, more information is available to help clarify users' intents. So in this paper, we propose a conversational paradigm for product search driven by non-relevant items, based on which fine-grained feedback is collected and utilized to show better results in the next iteration. We then propose an aspectvalue likelihood model to incorporate both positive and negative feedback on fine-grained aspect-value pairs of the non-relevant items. Experimental results show that our model is significantly better than state-of-the-art product search baselines without using feedback and those baselines using item-level negative feedback.

show abstract

Section: Overall Retrieval Performancementioning

confidence: 96%

“…Later, Ai et al [1] noticed that product search can be personalized and proposed a hierarchical embedding model based on product reviews for personalized product search. Recently, Bi et al [4] studied different context dependencies in multi-page product search.…”

Section: Related Workmentioning

confidence: 99%

Conversational Product Search Based on Negative Feedback

Zhang

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

show abstract

“…The primary reason is that such datasets contain confidential or proprietary information, and e-commerce platforms do not wish to take this risk. To cite an example, [49][50][51]worked on LTR with Walmart and Amazon datasets, but the datasets are not published. There are a few datasets for clustering, or recommendation systems, but as the number of features are very less (e.g.…”

Section: Dataset Availabilitymentioning

confidence: 99%

A Survey on E-Commerce Learning to Rank

Kabir

Hasan

Mandal³

et al. 2023

Preprint

View full text Add to dashboard Cite

In e-commerce, ranking the search results based on users’ preference is the most important task. Commercial e-commerce platforms, such as, Amazon, Alibaba, eBay, Walmart, etc. perform extensive and relentless research to perfect their search result ranking algorithms because the quality of ranking drives a user’s decision to purchase or not to purchase a product, directly affecting the profitability of the e-commerce platform. In such a commercial platforms, for optimizing search result ranking numerous features are considered, which emerge from relevance, personalization, seller’s reputation and paid promotion. To maintain their competitive advantage in the market, the platforms do no publish their core ranking algorithms, so it is difficult to know which of the algorithms or which of the features are the most effective for finding the most optimal search result ranking in e-commerce. No extensive surveys of learning to rank (LTR) in the e-commerce domain as such is not yet published. In this work, we survey the existing e-commerce learning to rank algorithms. Besides, we also compare these algorithms based on query relevance criterion on a large real-life e-commerce dataset and provide a quantitative comparison. To the best of our knowledge this is the first such survey which include an experimental comparison among various learning to rank algorithms.

show abstract

“…Early studies on product search focus on retrieving products based on structured product facets such as brands and categories [17,18,35]. However, as there exists a significant vocabulary gap between user queries and product descriptions [46,60], state-of-the-art approaches usually conduct product search in latent space with deep learning techniques [8,25,67]. For example, Bi et al [7? ] extract fine-grained review information with embedding networks; Guo et al [24] model long/short term user preferences with attention networks over user query history.…”

Section: Related Workmentioning

confidence: 99%

Model-agnostic vs. Model-intrinsic Interpretability for Explainable Product Search

Narayanan.R

2021

Proceedings of the 30th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Product retrieval systems have served as the main entry for customers to discover and purchase products online. With increasing concerns on the transparency and accountability of AI systems, studies on explainable information retrieval has received more and more attention in the research community. Interestingly, in the domain of e-commerce, despite the extensive studies on explainable product recommendation, the studies of explainable product search is still in an early stage. In this paper, we study how to construct effective explainable product search by comparing model-agnostic explanation paradigms with model-intrinsic paradigms and analyzing the important factors that determine the performance of product search explanations. We propose an explainable product search model with model-intrinsic interpretability and conduct crowdsourcing to compare it with the state-of-the-art explainable product search model with model-agnostic interpretability. We observe that both paradigms have their own advantages and the effectiveness of search explanations on different properties are affected by different factors. For example, explanation fidelity is more important for user's overall satisfaction on the system while explanation novelty may be more useful in attracting user purchases. These findings could have important implications for the future studies and design of explainable product search engines. CCS CONCEPTS• Information systems → Retrieval models and ranking; Retrieval tasks and goals; Evaluation of retrieval results.

show abstract

A Study of Context Dependencies in Multi-page Product Search

Cited by 9 publications

References 19 publications

Conversational Product Search Based on Negative Feedback

Conversational Product Search Based on Negative Feedback

A Survey on E-Commerce Learning to Rank

Model-agnostic vs. Model-intrinsic Interpretability for Explainable Product Search

Contact Info

Product

Resources

About