Exploiting User Preference for Online Learning in Web Content Optimization Systems
Exploiting User Preference for Online Learning in Web Content Optimization Systems
复制标题
DOI：
10.1145/2493259
复制
发表时间：
2014-04
期刊：
影响因子：
--
通讯作者：
Jiang Bian;Bo Long;Lihong Li;Taesup Moon;Anlei Dong;Yi Chang
中科院分区：
文献类型：
--
作者：
Jiang Bian;Bo Long;Lihong Li;Taesup Moon;Anlei Dong;Yi Chang
门户网站服务已成为向网络用户及时提供数字内容（例如新闻、广告等）的重要媒介。为了吸引更多的用户访问Web门户上的各种内容模块，需要设计一个推荐系统，通过自动估计内容项的吸引力以及与用户兴趣的相关性，有效地实现Web门户内容的优化。最先进的在线学习方法采用专用的逐点模型来独立估计每个候选内容项目的吸引力得分。尽管这种逐点模型可以很容易地适应在线推荐，但仍然存在一些关键问题。首先，这种逐点方法无法利用内容项之间宝贵的用户偏好。此外，当面临学习样本稀疏的问题时，点模型的性能会急剧下降。为了解决这些问题，我们建议探索一种新的用于门户网站内容优化的动态成对学习方法，其中我们利用根据用户在门户服务上的操作提取的动态用户偏好来计算内容项的吸引力分数。在本文中，我们介绍两种特定的成对学习算法，一种简单的基于图的算法和一种形式化的贝叶斯建模算法。对来自商业门户网站的大规模数据进行的实验表明，成对方法相对于基线逐点模型有显着改进。进一步的分析表明，我们新的成对学习方法比逐点模型更有利于个性化推荐，因为数据稀疏性对于个性化内容优化更为关键。
Web portal services have become an important medium to deliver digital content (e.g. news, advertisements, etc.) to Web users in a timely fashion. To attract more users to various content modules on the Web portal, it is necessary to design a recommender system that can effectively achieve Web portal content optimization by automatically estimating content item attractiveness and relevance to user interests. The state-of-the-art online learning methodology adapts dedicated pointwise models to independently estimate the attractiveness score for each candidate content item. Although such pointwise models can be easily adapted for online recommendation, there still remain a few critical problems. First, this pointwise methodology fails to use invaluable user preferences between content items. Moreover, the performance of pointwise models decreases drastically when facing the problem of sparse learning samples. To address these problems, we propose exploring a new dynamic pairwise learning methodology for Web portal content optimization in which we exploit dynamic user preferences extracted based on users' actions on portal services to compute the attractiveness scores of content items. In this article, we introduce two specific pairwise learning algorithms, a straightforward graph-based algorithm and a formalized Bayesian modeling one. Experiments on large-scale data from a commercial Web portal demonstrate the significant improvement of pairwise methodologies over the baseline pointwise models. Further analysis illustrates that our new pairwise learning approaches can benefit personalized recommendation more than pointwise models, since the data sparsity is more critical for personalized content optimization.