Interaction Behavior

14,000,000 Leading Edge Experts on the ideXlab platform

Scan Science and Technology

Contact Leading Edge Experts & Companies

Scan Science and Technology

Contact Leading Edge Experts & Companies

The Experts below are selected from a list of 381966 Experts worldwide ranked by ideXlab platform

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

  • constructing an Interaction Behavior model for web image search
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2018
    Co-Authors: Xiaohui Xie, Jiaxin Mao, Maarten De Rijke, Ruizhe Zhang, Min Zhang
    Abstract:

    User Interaction Behavior is a valuable source of implicit relevance feedback. In Web image search a different type of search result presentation is used than in general Web search, which leads to different Interaction mechanisms and user Behavior. For example, image search results are self-contained, so that users do not need to click the results to view the landing page as in general Web search, which generates sparse click data. Also, two-dimensional result placement instead of a linear result list makes browsing Behaviors more complex. Thus, it is hard to apply standard user Behavior models (e.g., click models) developed for general Web search to Web image search. In this paper, we conduct a comprehensive image search user Behavior analysis using data from a lab-based user study as well as data from a commercial search log. We then propose a novel Interaction Behavior model, called grid-based user browsing model (GUBM), whose design is motivated by observations from our data analysis. GUBM can both capture users' Interaction Behavior, including cursor hovering, and alleviate position bias. The advantages of GUBM are two-fold: (1) It is based on an unsupervised learning method and does not need manually annotated data for training. (2) It is based on user Interaction features on search engine result pages (SERPs) and is easily transferable to other scenarios that have a grid-based interface such as video search engines. We conduct extensive experiments to test the performance of our model using a large-scale commercial image search log. Experimental results show that in terms of Behavior prediction (perplexity), and topical relevance and image quality (normalized discounted cumulative gain (NDCG)), GUBM outperforms state-of-the-art baseline models as well as the original ranking. We make the implementation of GUBM and related datasets publicly available for future studies.

Xiaohui Xie - One of the best experts on this subject based on the ideXlab platform.

  • constructing an Interaction Behavior model for web image search
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2018
    Co-Authors: Xiaohui Xie, Jiaxin Mao, Maarten De Rijke, Ruizhe Zhang, Min Zhang
    Abstract:

    User Interaction Behavior is a valuable source of implicit relevance feedback. In Web image search a different type of search result presentation is used than in general Web search, which leads to different Interaction mechanisms and user Behavior. For example, image search results are self-contained, so that users do not need to click the results to view the landing page as in general Web search, which generates sparse click data. Also, two-dimensional result placement instead of a linear result list makes browsing Behaviors more complex. Thus, it is hard to apply standard user Behavior models (e.g., click models) developed for general Web search to Web image search. In this paper, we conduct a comprehensive image search user Behavior analysis using data from a lab-based user study as well as data from a commercial search log. We then propose a novel Interaction Behavior model, called grid-based user browsing model (GUBM), whose design is motivated by observations from our data analysis. GUBM can both capture users' Interaction Behavior, including cursor hovering, and alleviate position bias. The advantages of GUBM are two-fold: (1) It is based on an unsupervised learning method and does not need manually annotated data for training. (2) It is based on user Interaction features on search engine result pages (SERPs) and is easily transferable to other scenarios that have a grid-based interface such as video search engines. We conduct extensive experiments to test the performance of our model using a large-scale commercial image search log. Experimental results show that in terms of Behavior prediction (perplexity), and topical relevance and image quality (normalized discounted cumulative gain (NDCG)), GUBM outperforms state-of-the-art baseline models as well as the original ranking. We make the implementation of GUBM and related datasets publicly available for future studies.

Lunjin Lu - One of the best experts on this subject based on the ideXlab platform.

Katie K Crean - One of the best experts on this subject based on the ideXlab platform.

  • sex differences in social Interaction Behavior following social defeat stress in the monogamous california mouse peromyscus californicus
    PLOS ONE, 2011
    Co-Authors: Brian C Trainor, Michael C Pride, Rosalina Villalon Landeros, Nicholas W Knoblauch, Elizabeth Y Takahashi, Andrea L Silva, Katie K Crean
    Abstract:

    Stressful life experiences are known to be a precipitating factor for many mental disorders. The social defeat model induces Behavioral responses in rodents (e.g. reduced social Interaction) that are similar to Behavioral patterns associated with mood disorders. The model has contributed to the discovery of novel mechanisms regulating Behavioral responses to stress, but its utility has been largely limited to males. This is disadvantageous because most mood disorders have a higher incidence in women versus men. Male and female California mice (Peromyscus californicus) aggressively defend territories, which allowed us to observe the effects of social defeat in both sexes. In two experiments, mice were exposed to three social defeat or control episodes. Mice were then Behaviorally phenotyped, and indirect markers of brain activity and corticosterone responses to a novel social stimulus were assessed. Sex differences in Behavioral responses to social stress were long lasting (4 wks). Social defeat reduced social Interaction responses in females but not males. In females, social defeat induced an increase in the number of phosphorylated CREB positive cells in the nucleus accumbens shell after exposure to a novel social stimulus. This effect of defeat was not observed in males. The effects of defeat in females were limited to social contexts, as there were no differences in exploratory Behavior in the open field or light-dark box test. These data suggest that California mice could be a useful model for studying sex differences in Behavioral responses to stress, particularly in neurobiological mechanisms that are involved with the regulation of social Behavior.

Han Ji-sheng - One of the best experts on this subject based on the ideXlab platform.

  • Electro-acupuncture improves the social Interaction Behavior of rats
    PHYSIOLOGY & BEHAVIOR, 2015
    Co-Authors: Zhang Hong-feng, Li Han-xia, Dai Yu-chuan, Xu Xin-jie, Han Song-ping, Zhang Rong, Han Ji-sheng
    Abstract:

    Oxytocin (OXT) and arginine-vasopressin (AVP) are two closely related neuropeptides and implicated in the regulation of mammalian social Behaviors. A prior clinical study in our laboratory suggested that electroacupuncture (EA) alleviated social impairment in autistic children accompanied by changes of peripheral levels of OXT and AVP. However, it remains unclear whether EA stimulation had an impact on central OXT and AVP levels. In the present study, rats were subjected to a single session of EA (sEA) or repeated sessions of EA (rEA). Following the stimulation, mRNA levels and peptide levels of OXT/AVP systems were determined. The results showed that sEA led to region-specific up-regulation of OXT and AVP mRNA levels in the hypothalamus where the peptides were produced, without affecting the content of OXT and AVP in the hypothalamus and peripheral blood. The rEA of 5 sessions in 9 days was given to the low socially interacting (LSI) rats. LSI rats that underwent rEA showed significant improvement of social Behavior characterized by spending more time investigating the strange rats in the three-chamber sociability test. The improved sociability was accompanied by an up-regulation of mRNA and the peptide levels of OXT or AVP in SON of the hypothalamus as well as a significant increase of the serum level of AVP. It is concluded that activation of OXT/AVP systems may be associated with the pro-social effect caused by EA stimulation. (C) 2015 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).National Natural Science Foundation of China [81271507]; Research Special Fund for Public Welfare Industry of Health of China [201302002-11]SCI(E)PubMedSSCIARTICLEzhangrong@bjmu.edu.cn; hanjisheng@bjmu.edu.cn485-49315

Interaction Behavior - 15 days free trial to Access Experts & Abstracts