Tapping on the potential of q community by recommending answer providers
Tapping on the potential of q community by recommending answer providers
复制标题
DOI：
10.1145/1458082.1458204
复制
发表时间：
2008-10
期刊：
影响因子：
--
通讯作者：
Jinwen Guo;Shengliang Xu;Shenghua Bao;Yong Yu
中科院分区：
文献类型：
--
作者：
Jinwen Guo;Shengliang Xu;Shenghua Bao;Yong Yu
基于社区的问答（cQA）服务的迅速普及，例如Yahoo！答非所问、百度有道等引起了学术界和产业界的高度关注。除了问题搜索和答案发现等基本问题外，用户参与率低是限制cQA服务发展潜力的关键问题。在本文中，我们专注于解决这个问题，推荐答案提供商，其中一个问题是作为一个查询和排名的用户列表根据回答问题的可能性返回。基于这种直观的推荐思想，我们尝试引入主题级模型来改进启发式的术语级方法，并将其作为基线。该方法包括两个步骤：（1）发现问答内容中的潜在主题和用户的潜在兴趣，建立用户档案;（2）基于潜在主题和术语级模型，为新到的问题推荐问题回答者。具体来说，我们开发了一个通用的生成模型的问题和答案在cQA，然后改变，以获得一个新的计算易处理的贝叶斯网络模型。实验进行了一个现实世界的数据从雅虎抓取！2007年6月12日至2007年8月4日期间的回答，其中包括118510个问题，772962个答案和150324个用户。实验结果表明，基线方法的显着改善，并验证了主题级信息的积极影响。
The rapidly increasing popularity of community-based Question Answering (cQA) services, e.g. Yahoo! Answers, Baidu Zhidao, etc. have attracted great attention from both academia and industry. Besides the basic problems, like question searching and answer finding, it should be noted that the low participation rate of users in cQA service is the crucial problem which limits its development potential. In this paper, we focus on addressing this problem by recommending answer providers, in which a question is given as a query and a ranked list of users is returned according to the likelihood of answering the question. Based on the intuitive idea for recommendation, we try to introduce topic-level model to improve heuristic term-level methods, which are treated as the baselines. The proposed approach consists of two steps: (1) discovering latent topics in the content of questions and answers as well as latent interests of users to build user profiles; (2) recommending question answerers for new arrival questions based on latent topics and term-level model. Specifically, we develop a general generative model for questions and answers in cQA, which is then altered to obtain a novel computationally tractable Bayesian network model. Experiments are carried out on a real-world data crawled from Yahoo! Answers during Jun 12 2007 to Aug 04 2007, which consists of 118510 questions, 772962 answers and 150324 users. The experimental results reveal significant improvements over the baseline methods and validate the positive influence of topic-level information.