The Experts below are selected from a list of 10899 Experts worldwide ranked by ideXlab platform

Eugene Agichtein - One of the best experts on this subject based on the ideXlab platform.

  • de biased modeling of search Click Behavior with reinforcement learning
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021
    Co-Authors: Jianghong Zhou, Sayyed M Zahiri, Simon Hughes, Khalifeh Al Jadda, Surya Kallumadi, Eugene Agichtein
    Abstract:

    Users' Clicks on Web search results are one of the key signals for evaluating and improving web search quality and have been widely used as part of current state-of-the-art Learning-To-Rank(LTR) models. With a large volume of search logs available for major search engines, effective models of searcher Click Behavior have emerged to evaluate and train LTR models. However, when modeling the users' Click Behavior, considering the bias of the Behavior is imperative. In particular, when a search result is not Clicked, it is not necessarily chosen as not relevant by the user, but instead could have been simply missed, especially for lower-ranked results. These kinds of biases in the Click log data can be incorporated into the Click models, propagating the errors to the resulting LTR ranking models or evaluation metrics. In this paper, we propose the De-biased Reinforcement Learning Click model (DRLC). The DRLC model relaxes previously made assumptions about the users' examination Behavior and resulting latent states. To implement the DRLC model, convolutional neural networks are used as the value networks for reinforcement learning, trained to learn a policy to reduce bias in the Click logs. To demonstrate the effectiveness of the DRLC model, we first compare performance with the previous state-of-art approaches using established Click prediction metrics, including log-likelihood and perplexity. We further show that DRLC also leads to improvements in ranking performance. Our experiments demonstrate the effectiveness of the DRLC model in learning to reduce bias in Click logs, leading to improved modeling performance and showing the potential for using DRLC for improving Web search quality.

  • deepcat deep category representation for query understanding in e commerce search
    arXiv: Information Retrieval, 2021
    Co-Authors: Ali Ahmadvand, Surya Kallumadi, Faizan Javed, Eugene Agichtein
    Abstract:

    Mapping a search query to a set of relevant categories in the product taxonomy is a significant challenge in e-commerce search for two reasons: 1) Training data exhibits severe class imbalance problem due to biased Click Behavior, and 2) queries with little customer feedback (e.g., \textit{tail} queries) are not well-represented in the training set, and cause difficulties for query understanding. To address these problems, we propose a deep learning model, DeepCAT, which learns joint word-category representations to enhance the query understanding process. We believe learning category interactions helps to improve the performance of category mapping on \textit{minority} classes, \textit{tail} and \textit{torso} queries. DeepCAT contains a novel word-category representation model that trains the category representations based on word-category co-occurrences in the training set. The category representation is then leveraged to introduce a new loss function to estimate the category-category co-occurrences for refining joint word-category embeddings. To demonstrate our model's effectiveness on {\em minority} categories and {\em tail} queries, we conduct two sets of experiments. The results show that DeepCAT reaches a 10\% improvement on {\em minority} classes and a 7.1\% improvement on {\em tail} queries over a state-of-the-art label embedding model. Our findings suggest a promising direction for improving e-commerce search by semantic modeling of taxonomy hierarchies.

  • deepcat deep category representation for query understanding in e commerce search
    arXiv: Information Retrieval, 2021
    Co-Authors: Ali Ahmadvand, Surya Kallumadi, Faizan Javed, Eugene Agichtein
    Abstract:

    Mapping a search query to a set of relevant categories in the product taxonomy is a significant challenge in e-commerce search for two reasons: 1) Training data exhibits severe class imbalance problem due to biased Click Behavior, and 2) queries with little customer feedback (e.g., tail queries) are not well-represented in the training set, and cause difficulties for query understanding. To address these problems, we propose a deep learning model, DeepCAT, which learns joint word-category representations to enhance the query understanding process. We believe learning category interactions helps to improve the performance of category mapping on minority classes, tail and torso queries. DeepCAT contains a novel word-category representation model that trains the category representations based on word-category co-occurrences in the training set. The category representation is then leveraged to introduce a new loss function to estimate the category-category co-occurrences for refining joint word-category embeddings. To demonstrate our model's effectiveness on minority categories and tail queries, we conduct two sets of experiments. The results show that DeepCAT reaches a 10% improvement on minority classes and a 7.1% improvement on tail queries over a state-of-the-art label embedding model. Our findings suggest a promising direction for improving e-commerce search by semantic modeling of taxonomy hierarchies.

  • beyond dwell time estimating document relevance from cursor movements and other post Click searcher Behavior
    The Web Conference, 2012
    Co-Authors: Qi Guo, Eugene Agichtein
    Abstract:

    Result Clickthrough statistics and dwell time on Clicked results have been shown valuable for inferring search result relevance, but the interpretation of these signals can vary substantially for different tasks and users. This paper shows that that post-Click searcher Behavior, such as cursor movement and scrolling, provides additional clues for better estimating document relevance. To this end, we identify patterns of examination and interaction Behavior that correspond to viewing a relevant or non-relevant document, and design a new Post-Click Behavior (PCB) model to capture these patterns. To our knowledge, PCB is the first to successfully incorporate post-Click searcher interactions such as cursor movements and scrolling on a landing page for estimating document relevance. We evaluate PCB on a dataset collected from a controlled user study that contains interactions gathered from hundreds of unique queries, result Clicks, and page examinations. The experimental results show that PCB is significantly more effective than using page dwell time information alone, both for estimating the explicit judgments of each user, and for re-ranking the results using the estimated relevance.

Younghoon Park - One of the best experts on this subject based on the ideXlab platform.

  • consumer Click Behavior at a search engine the role of keyword popularity
    Journal of Marketing Research, 2014
    Co-Authors: Kinshuk Jerath, Younghoon Park
    Abstract:

    The authors study consumers' Click Behavior on organic and sponsored links after a keyword search on an Internet search engine. Using a data set of individual-level Click activity after keyword searches from a leading search engine in Korea, the authors find that consumers' Click activity after a keyword search is low and heavily concentrated on the organic list. However, searches of less popular keywords (i.e., keywords with lower search volume) are associated with more Clicks per search and a larger fraction of sponsored Clicks. This indicates that, compared with more popular keywords, consumers who search for less popular keywords expend more effort in their search for information and are closer to a purchase, which makes them more targetable for sponsored search advertising.

  • consumer Click Behavior at a search engine the role of keyword popularity
    Social Science Research Network, 2013
    Co-Authors: Kinshuk Jerath, Younghoon Park
    Abstract:

    The authors study users’ Click Behavior on organic and sponsored links after a keyword search at a search engine. Using a dataset obtained from a search engine, they analyze over 1.5 million user searches for multiple keywords over the span of one month. They find that consumers’ Click activity after a keyword search is quite low and is heavily concentrated on the organic list. Interestingly, however, there is significant variation in Click Behavior across keywords, driven by the fact that the composition of consumers searching different keywords is different. Specifically, keyword popularity, as determined by search volumes for the keywords, is an important indicator of searchers’ Click tendencies — as keyword popularity decreases, keywords are searched by consumers who generate more Clicks per search and Click more sponsored links. This indicates that, as compared to more popular keywords, less popular keywords are searched by consumers who expend more effort in their search for information and are closer to a purchase, which makes them more targetable for sponsored search advertising.

Yiqun Liu - One of the best experts on this subject based on the ideXlab platform.

  • incorporating non sequential Behavior into Click models
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2015
    Co-Authors: Chao Wang, Yiqun Liu, Meng Wang, Ke Zhou, Jianyun Nie
    Abstract:

    Click-through information is considered as a valuable source of users' implicit relevance feedback. As user Behavior is usually influenced by a number of factors such as position, presentation style and site reputation, researchers have proposed a variety of assumptions (i.e.~Click models) to generate a reasonable estimation of result relevance. The construction of Click models usually follow some hypotheses. For example, most existing Click models follow the sequential examination hypothesis in which users examine results from top to bottom in a linear fashion. While these Click models have been successful, many recent studies showed that there is a large proportion of non-sequential browsing (both examination and Click) Behaviors in Web search, which the previous models fail to cope with. In this paper, we investigate the problem of properly incorporating non-sequential Behavior into Click models. We firstly carry out a laboratory eye-tracking study to analyze user's non-sequential examination Behavior and then propose a novel Click model named Partially Sequential Click Model (PSCM) that captures the practical Behavior of users. We compare PSCM with a number of existing Click models using two real-world search engine logs. Experimental results show that PSCM outperforms other Click models in terms of both predicting Click Behavior (perplexity) and estimating result relevance (NDCG and user preference test). We also publicize the implementations of PSCM and related datasets for possible future comparison studies.

  • how do users describe their information need query recommendation based on snippet Click model
    Expert Systems With Applications, 2011
    Co-Authors: Yiqun Liu, Junwei Miao, Min Zhang
    Abstract:

    Query recommendation helps users to describe their information needs more clearly so that search engines can return appropriate answers and meet their needs. State-of-the-art researches prove that the use of users' Behavior information helps to improve query recommendation performance. Instead of finding the most similar terms previous users queried, we focus on how to detect users' actual infor- mation need based on their search Behaviors. The key idea of this paper is that although the Clicked documents are not always relevant to users' queries, the snippets which lead them to the Click most prob- ably meet their information needs. Based on analysis into large-scale practical search Behavior log data, two snippet Click Behavior models are constructed and corresponding query recommendation algorithms are proposed. Experimental results based on two widely-used commercial search engines' Click-through data prove that the proposed algorithms outperform practical recommendation methods of these two search engines. To the best of our knowledge, this is the first time that snippet Click models are proposed for query recommendation task.

  • investigating characteristics of non Click Behavior using query logs
    Asia Information Retrieval Symposium, 2010
    Co-Authors: Ting Yao, Min Zhang, Yiqun Liu, Yongfeng Zhang
    Abstract:

    Users’ query and Click Behavior information has been widely used in relevance feedback techniques to improve search engine performance. However, there is a special kind of user Behavior that submitting a query but not Clicking any result returned by search engines. Queries ending with non-Click make up a large fraction of user search activities, but few studies on them have been done in user Behavior analysis. In this paper we investigate non-Click Behavior using large scale search logs from a commercial search engine. We analyze query and non-Click Behavior characteristics on three levels, i.e., query, session and user level. Query frequency, search engine returned results and category of information need are observed to be relative to non-Click Behavior. There are significant differences between post-query actions of Clicked and non-Clicked queries. Users’ personal preference can also results in non-Click Behavior. Our findings have implications for separating queries which are handled well or not by search engines and are useful in user Behavior reliability study.

Tieyan Liu - One of the best experts on this subject based on the ideXlab platform.

  • advertiser centric approach to understand user Click Behavior in sponsored search
    Information Sciences, 2014
    Co-Authors: Sungchul Kim, Tao Qin, Tieyan Liu
    Abstract:

    Sponsored search is the major business model of commercial search engines. The number of Clicks on ads is a key indicator of success for both advertisers and search engines, and therefore increasing ad Clicks is a goal of both of them. Many existing works stand on the view of search engines concerning how to help search engines to earn more revenue by accurately predicting ad Clicks. Unlike these works, this paper aims at understanding user Clicks on ads from "the view of advertisers", in order to help advertisers to improve their ad quality and therefore advertising effectiveness. To do this, a factor graph model is proposed, which considers two advertiser-controllable factors to understand user Click Behaviors: (1) the relevance between a query and an ad, which has been well studied in the literature, and (2) the "attractiveness" of the ad, which is a newly-proposed concept. The proposed model can be used to predict user Clicks and also to mine a set of attractive words that could be leveraged to improve the quality of the ads. We have verified the effectiveness of the proposed approach using real world datasets, through quantitative evaluations and informative case studies.

  • advertiser centric approach to understand user Click Behavior in sponsored search
    Conference on Information and Knowledge Management, 2011
    Co-Authors: Sungchul Kim, Tao Qin, Tieyan Liu
    Abstract:

    Sponsored search is the major business model of commercial search engines. The number of Clicks on ads is a key indicator of success for both advertisers and search engines, and increasing ad Clicks is a goal of both of them. Many existing works stand on the view of search engines concerning how to help search engines to earn more revenue by accurately predicting ad Clicks. Unlike the existing works, this paper aims at understanding user Clicks on ads from "the view of advertisers", in order to help advertisers to improve their ad quality and therefore advertising effectiveness. To do this, a factor graph model is proposed, which considers two advertiser-controllable factors to understand user Click Behaviors: the relevance between a query and an ad, which has been well studied in previous literatures, and the "attractiveness" of the ad, which is a newly-proposed concept. The proposed model can be used to predict user Clicks and also to mine a set of attractive words that could be leveraged to improve the quality of the ads. We have verified the effectiveness of the proposed approach using real-world datasets, through quantitative evaluations and informative case studies.

Min Zhang - One of the best experts on this subject based on the ideXlab platform.

  • how do users describe their information need query recommendation based on snippet Click model
    Expert Systems With Applications, 2011
    Co-Authors: Yiqun Liu, Junwei Miao, Min Zhang
    Abstract:

    Query recommendation helps users to describe their information needs more clearly so that search engines can return appropriate answers and meet their needs. State-of-the-art researches prove that the use of users' Behavior information helps to improve query recommendation performance. Instead of finding the most similar terms previous users queried, we focus on how to detect users' actual infor- mation need based on their search Behaviors. The key idea of this paper is that although the Clicked documents are not always relevant to users' queries, the snippets which lead them to the Click most prob- ably meet their information needs. Based on analysis into large-scale practical search Behavior log data, two snippet Click Behavior models are constructed and corresponding query recommendation algorithms are proposed. Experimental results based on two widely-used commercial search engines' Click-through data prove that the proposed algorithms outperform practical recommendation methods of these two search engines. To the best of our knowledge, this is the first time that snippet Click models are proposed for query recommendation task.

  • investigating characteristics of non Click Behavior using query logs
    Asia Information Retrieval Symposium, 2010
    Co-Authors: Ting Yao, Min Zhang, Yiqun Liu, Yongfeng Zhang
    Abstract:

    Users’ query and Click Behavior information has been widely used in relevance feedback techniques to improve search engine performance. However, there is a special kind of user Behavior that submitting a query but not Clicking any result returned by search engines. Queries ending with non-Click make up a large fraction of user search activities, but few studies on them have been done in user Behavior analysis. In this paper we investigate non-Click Behavior using large scale search logs from a commercial search engine. We analyze query and non-Click Behavior characteristics on three levels, i.e., query, session and user level. Query frequency, search engine returned results and category of information need are observed to be relative to non-Click Behavior. There are significant differences between post-query actions of Clicked and non-Clicked queries. Users’ personal preference can also results in non-Click Behavior. Our findings have implications for separating queries which are handled well or not by search engines and are useful in user Behavior reliability study.