图书情报工作 ›› 2019, Vol. 63 ›› Issue (10): 97-105.DOI: 10.13266/j.issn.0252-3116.2019.10.011

• 情报研究 • 上一篇    下一篇

社会化问答平台提问回复率的预测研究——以“百度知道”为例

邓胜利, 付少雄, 刘瑾   

  1. 武汉大学信息资源研究中心 武汉 430072
  • 收稿日期:2018-11-02 修回日期:2019-01-21 出版日期:2019-05-20 发布日期:2019-05-20
  • 通讯作者: 付少雄(ORCID:0000-0002-5166-3141),博士研究生,通讯作者,E-mail:fu_shaoxiong@163.com
  • 作者简介:邓胜利(ORCID:0000-0001-7489-4439),教授,博士,博士生导师;刘瑾(ORCID:0000-0003-4345-2157),硕士研究生。

The Prediction Research of Response Rate in Social Q&A Communities: A Case Study of Baidu Knows

Deng Shengli, Fu Shaoxiong, Liu Jin   

  1. Center for Studies of Information Resources, Wuhan University, Wuhan 430072
  • Received:2018-11-02 Revised:2019-01-21 Online:2019-05-20 Published:2019-05-20

摘要: [目的/意义] 基于社会化问答平台提问回复率较低的现状,通过预测提问回复率,能够为社会化问答平台提升用户活跃度与留存率,改善用户体验提供参考。[方法/过程] 以"百度知道"为研究平台,抓取平台设置的14个话题下共10 640条提问记录,从提问特征与提问者特征角度,构建提问回复率影响因素的研究框架。采用二元Logistic回归对影响因素进行数据验证,构建提问回复率的预测模型,对模型准确率进行验证。[结果/结论] 社会化问答平台提问回复率研究可改善平台信息服务质量与促进用户知识贡献行为,实验结果验证了研究模型在社会化问答平台提问回复率预测中的有效性。

关键词: 社会化问答平台, 知识贡献行为, 回复率, Logistic回归, 预测

Abstract: [Purpose/significance] Based on the current situation of low response rate of social Q&A communities, the research can provide references for social Q&A communities to improve user activation, retention rate and user experience by predicting the response rate of questions.[Method/process] The paper took "Baidu Know" as the research platform, and grabbed 10 640 question records under 14 topics set by the platform. From the perspective of question and questioner characteristics, the paper constructed the research framework of the factors affecting the question response rate. The binary logistic regression was used to verify the influencing factors, and then the prediction model of the question response rate was constructed.[Result/conclusion] The prediction research of response rate in social Q&A communities can improve the quality of platform information services and promote user knowledge contribution behavior. The experimental results have verified the validity of the model in the prediction of question response rate of the social Q&A communities.

Key words: social Q&A community, knowledge contribution behavior, response rate, logistic regression, prediction

中图分类号: