图书情报工作 ›› 2019, Vol. 63 ›› Issue (17): 137-144.DOI: 10.13266/j.issn.0252-3116.2019.17.016

• 情报研究 • 上一篇    下一篇

基于在线评论的网络社区信息可信度评价方法研究

国佳, 郭勇, 沈旺, 潘梦雅   

  1. 吉林大学管理学院 长春 130025
  • 收稿日期:2019-01-08 修回日期:2019-04-01 出版日期:2019-09-05 发布日期:2019-09-05
  • 作者简介:国佳(ORCID:0000-0002-1758-1345),讲师,E-mail:guojiajlu1982@163.com;郭勇(ORCID:0000-0001-7888-3294),本科生;沈旺(ORCID:0000-0002-8933-5653),副教授;潘梦雅(ORCID:0000-0002-0319-626X),硕士研究生。

Credibility Evaluating Method of Online Community Information Based on Online Reviews

Guo Jia, Guo Yong, Shen Wang, Pan Mengya   

  1. School of Management, Jilin University, Changchun 130025
  • Received:2019-01-08 Revised:2019-04-01 Online:2019-09-05 Published:2019-09-05

摘要: [目的/意义]提出基于在线评论的网络社区信息可信度评价方法,为信息治理提供有效依据。[方法/过程]构建基于在线评论的网络社区信息可信度评价指标体系,利用改进AHP理论确定指标权重;利用LSTM模型对评论情感分类,采用改进的D-S证据理论模型融合情感分类数据作为指标量化计算方法。以知乎网络社区为例,从3个角度计算网络信息内容的可信度:经过筛选的具有可信观点评价的在线评论、所有在线评论、调查问卷。[结果/结论]实验结果表明,基于可信观点评论的可信度排序与基于调查问卷的可信度排序基本一致,说明利用在线评论对网络信息可信度进行评价具有一定的可行性。

关键词: 在线评论, 信息可信度, 改进D-S证据理论模型, 网络社区

Abstract: [Purpose/significance] A social Q&A community information credibility evaluation method based on online reviews was proposed, aiming to provid an effective methods for information governing.[Method/process] The paper constructed the evaluation system of online community information reliability based on online reviews, and the indicator weight was determined by improved AHP theory. The LSTM model was used to classify the reviews emotion, and the improved D-S evidence theory model was used to fuse the emotion classification data. Taking ZhiHu Community as an example, the credibility of network information content was calculated from three perspectives:screened online reviews with credible opinion evaluation, all online reviews and questionnaires.[Result/conclusion] The experimental results showed that the ranking of the credibility value of this method was basically the same as that of the ranking obtained by the questionnaire. It showed that it is feasible to evaluate the credibility of the network information by online review.

Key words: online reviews, information credibility, modified D-S evidential theory, online community

中图分类号: