Online commercial intention detection framework based on web pages

Online commercial intention detection framework based on web pages
复制标题

基于网页的在线商业意图检测框架

DOI:
10.1504/ijcse.2016.076220
复制
发表时间:
2016-05
期刊:
Int. J. Computational Science and Engineering
影响因子:
--
通讯作者:
Longbin Lai et al.
Longbin Lai et al.
中科院分区:
其他
文献类型:
--
作者:
Huakang Li;Huakang Li;Xiaofeng Xu;Xiaofeng Xu;Longbin Lai et al.;Longbin Lai et al.

文献摘要

参考文献

相似文献

中国互联网络信息中心发布的数据显示,全球网民每周上网时间大多为10-16个小时。为了在互联网上有效地发布广告和社会信息,与传统的推荐系统相比,如何从用户的在线行为中挖掘商业价值成为一个新的挑战。在本文中,我们提出了一个新的系统,名为‘在线商业意图(OCI)检测系统’,利用用户的全球网络浏览历史来预测在线购物平台上的潜在购买产品。通过分析购物平台上十亿条查询的点击量分布,首次建立了一个揭示用户查询与产品类别之间关系的商业关键词词典。收集数百万互联网用户的足迹,并对原始页面内容进行爬行。使用N-gram算法提取页面中的关键词,并使用查询频率(QF)、逆类别频率(ICF)等来估计商业概率,通过合并其商业关键词的KD矩阵来估计页面OCI。为了提高类别的连贯性和准确性,我们提出了一个类别相似度模型来观察前N个类别之间的距离。实验结果表明,人工评估的类别预测准确率达到86%。
The China Internet Network Information Centre (CNNIC) published that internet users around the world mostly spent 10-16 hours per week online. For effective advertising and social information publishing on the internet, how to dig out the commercial value from users' online behaviour becomes a new challenge compared with the traditional recommendation system. In this paper, we propose a novel system named 'online commercial intention (OCI) detection system' using users' global web browsing history to predict potential purchasing products on an online shopping platform. A 'commercial keyword dictionary (KD)' that reveals the relationship between user queries and product categories is firstly set up by analysing the click distribution of billion queries on the shopping platform. Footprints of millions of internet users are gathered and the raw page contents are crawled. Keywords in these pages are extracted using N-gram algorithm and commercial probabilities are estimated with query frequency (QF), inverse category frequency (ICF), etc. The page OCI is estimated by merging the KD matrices of its commercial keywords. In order to increase categories' coherence and accuracy, we provide a category similarity model to observe the distance between top N categories. The experiment results show that category prediction accuracy reaches 86% with manual evaluation.
DOI: 10.21236/ada640219
发表时间: 1995-02
期刊: --
影响因子: --
作者:
R. Armstrong;Dayne Freitag;T. Joachims;Tom Michael Mitchell
通讯作者: R. Armstrong;Dayne Freitag;T. Joachims;Tom Michael Mitchell
DOI: 10.1145/1871437.1871565
发表时间: 2010-10
期刊: Proceedings of the 19th ACM international conference on Information and knowledge management
影响因子: --
作者:
Ryen W. White;Paul N. Bennett;S. Dumais
通讯作者: Ryen W. White;Paul N. Bennett;S. Dumais
DOI: 10.1007/s005300050098
发表时间: 1998-09
期刊: Multimedia Systems
影响因子: 3.9
作者:
K. Bharat;T. Kamba;Michael C. Albers
通讯作者: K. Bharat;T. Kamba;Michael C. Albers
初始配置对基于网络的推荐的影响
DOI: 10.1209/0295-5075/81/58004
发表时间: 2008-03-01
期刊: EPL
影响因子: 1.8
作者:
Zhou, T.;Jiang, L. -L.;Zhang, Y. -C.
通讯作者: Zhang, Y. -C.
DOI: 10.1007/s10489-011-0301-4
发表时间: 2012-06
影响因子: 5.3
作者:
Victoria Eyharabide;A. Amandi
通讯作者: Victoria Eyharabide;A. Amandi