基于元分析的网络用户评论表达真实性研究

张鑫众; 徐健; 张雯昕; 王玥瑄; 李文睿; 盛清泉

doi:10.13266/j.issn.2095-5472.2025.021

PDF(1976 KB)

知识管理论坛 ›› 2025, Vol. 10 ›› Issue (4) : 321-334. DOI: 10.13266/j.issn.2095-5472.2025.021 CSTR: 32306.14.CN11-6036.2025.021

研究论文

基于元分析的网络用户评论表达真实性研究

作者信息 +

Research on the Authenticity of Online User Comment Expression Based on Meta Analysis

Author information +

文章历史 +

摘要

【目的/意义】 随着网络用户数量快速增长，网络评论对用户的影响越来越大并在一定程度上影响人们在网络上的选择和行为。针对当前网络评论研究中真实性评估不足的问题，通过元分析量化评估网络评论真实性，揭示不真实评论的分布规律，为相关研究的数据可靠性判断提供依据。 【方法/过程】 在相关领域对于评论真实性相关因素研究较少的客观情况下，创新性地提出利用不真实评论比例这一差异类变量进行元分析。采用异质性检验、发表偏倚检验和随机效应模型进行元分析，结合可视化工具解析不同平台、不同类型评论的不真实情况。 【结果/结论】 各类网络评论平台普遍存在超过15%的不真实评论且占比持续上升，结果根据平台类型、国内外环境等因素产生一定的差异性。学界较多选取的评论平台中，独立于商家、客户的第三方评论平台（如大众点评、Yelp等）中不真实评论最少存在15%左右；独立于用户的卖家平台（如京东、亚马逊等）中不真实评论较多，占比达到20%左右；而不具备商业属性的用户自建平台（如微博、博客等）中不真实评论数量最多，占比超过25%以上，其中大多数为谣言和垃圾评论。

Abstract

[Purpose/Significance] With the rapid growth of online users, online comments increasingly influence users’ choices and behaviors on the internet. To address the insufficient assessment of authenticity in current online comment research, this study employs meta-analysis to quantitatively evaluate the authenticity of online comments, revealing the distribution patterns of online comments, revealing the distribution patterns of inauthentic comments, and providing a reference for data reliability judgment in related studies. [Method/Process] Given the limited research on factors related to comment authenticity, this study innovatively proposed to use the proportion of inauthentic comments as a differential variable for meta-analysis. Heterogeneity tests, publication bias tests, and random-effects models were applied, combined with visualization tools to analyze inauthenticity across different platforms and comment types. [Result/Conclusion] There are generally over 15% of untrue comments, and the proportion continues to rise. The results vary depending on factors such as platform type and domestic and international environment. Among the review platforms widely selected by academia, there are at least 15% of untrue reviews on third-party review platforms (such as Dianping, Yelp, etc.) that are independent of merchants and customers; There are many untrue reviews on seller platforms independent of users (such as JD.com, Amazon, etc.), accounting for about 20%; In user built platforms without commercial attributes (such as Weibo, blogs, etc.), the number of untrue comments is the highest, accounting for more than 25%, most of which are rumors and junk comments.

导出引用

张鑫众 , 徐健 , 张雯昕 , 等. 基于元分析的网络用户评论表达真实性研究[J]. 知识管理论坛. 2025, 10(4): 321-334 https://doi.org/10.13266/j.issn.2095-5472.2025.021

Zhang Xinzhong , Xu Jian , Zhang Wenxin , et al. Research on the Authenticity of Online User Comment Expression Based on Meta Analysis[J]. Knowledge Management Forum. 2025, 10(4): 321-334 https://doi.org/10.13266/j.issn.2095-5472.2025.021

中图分类号： G252

参考文献

列表( 原文顺序 | 文献年度倒序 | 文中引用次数倒序 ) 可视化分析

[1]	LUCA M, ZERVAS G. Fake it until you make it：reputation, competition, and Yelp review fraud[J]. Management science, 2016, 62(12): 3412-3427. 本文引用 [2]

[2]	CROCKETT Z. 5-star phonies: inside the fake Amazon review complex[EB/OL]. [2025-07-20]. https://thehustle.co/amazon-fake-reviews/. https://thehustle.co/amazon-fake-reviews/ 本文引用 [1]

[3]	JIN Z, CAO J, GUO H, et al. Detection and analysis of 2016 us presidential election related rumors on Twitter[C]//Social, cultural, and behavioral modeling: 10th international conference. Cham: Springer Inter-national Publishing, 2017: 14-24. 本文引用 [1]

[4]	JINDAL N, LIU B. Review spam detection[C]//Proceedings of the 16th international conference on World Wide Web. Banff: ACM Press; 2007: 1189-1190. 本文引用 [1]

[5]	武雅利, 徐勇, 焦梦蕾, 等. 基于在线交易的虚假评论与网络水军研究综述[J]. 现代计算机, 2019(21): 37-40. WU, Y L, XU Y, JIAO M L, et al. A review of fake reviews and internet water army in online transactions[J]. Modern computer, 2019(21): 37-40. 本文引用 [2]

[6]	王宁, 宋嘉莹, 杨学成. C2C电商平台中在线评论偏离真实性的诱因及应对策略[J]. 软科学, 2017, 31(4): 100-103. WANG N, SONG J, YANG X. Incentives and countermeasures for deviation from authenticity of online reviews in C2C e-commerce platforms[J]. Soft science, 2017, 31(4): 100-103. 本文引用 [1]

[7]	李璐旸, 秦兵, 刘挺. 虚假评论检测研究综述[J]. 计算机学报, 2018, 41(4): 946-968. LI L, QIN B, LIU T. A survey on fake review detection research[J]. Chinese journal of computers, 2018, 41(4): 946-968. 本文引用 [1]

[8]	魏瑾瑞, 徐晓晴. 虚假评论、消费决策与产品绩效——虚假评论能产生真实的绩效吗[J]. 南开管理评论, 2020, 23(1): 189-199. WEI J, XU X. Fake reviews, consumer decision-making and product performance: can fake reviews generate real performance?[J] Nankai business review, 2020, 23(1): 189-199. 本文引用 [1]

[9]	陈燕方, 娄策群. 在线商品虚假评论形成路径研究[J]. 现代情报, 2015, 35(1): 49-53. CHEN Y, LOU C. Research on the formation paths of fake online product reviews[J]. Modern information, 2015, 35(1): 49-53. 本文引用 [2]

[10]	KAPFERER J N. Rumors: uses, interpretations, and images[M]. Piscataway: transaction publishers, 1990. 本文引用 [1]

[11]	刘建明. 舆论传播[M]. 北京: 清华大学出版社, 2000. LIU J. Public opinion communication [M]. Beijing: Tsinghua University Press, 2000. 本文引用 [1]

[12]	DUAN W, GU B, WHINSTON A B. Do online reviews matter?—an empirical investigation of panel data[J]. Decision support systems, 2008, 45(4): 1007-1016. 本文引用 [1]

[13]	王永贵, 张言彩.元分析方法在国内外经济管理研究中的应用比较[J]. 经济管理, 2012, 34(4): 182-190. WANG Y, ZHANG Y. Comparative analysis of meta-analysis applications in domestic and international economic management research[J]. Economic management journal, 2012, 34(4): 182-190. 本文引用 [1]

[14]	彭国超, 程晓, 刘彩华. 基于元分析的网络用户个人信息披露意愿影响因素研究[J]. 现代情报, 2022, 42(11): 111-120. PENG G, CHENG X, LIU C. Research on influencing factors of online users' personal information disclosure intention based on meta-analysis[J]. Journal of modern information, 2022, 42(11): 111-120. 本文引用 [1]

[15]	杨笑. 基于元分析的电子商务平台评论有用性影响因素研究[D]. 北京: 北京外国语大学, 2022. YANG X. Research on influencing factors of online review helpfulness in e-commerce platforms based on meta-analysis[D]. Beijing: Beijing Foreign Studies University, 2022. 本文引用 [1]

[16]	LIPSEY M W, WILSON D B. Practical meta-analysis[M]. Thousand Oaks: Sage Publications, 2001. 本文引用 [1]

[17]	万晨. 不同平台在线评论消费者感知差异研究——产品类型的调节作用[J]. 现代情报, 2014, 34(12): 154-158, 167. WAN C. Research on consumer perception differences of online reviews across platforms: the moderating role of product type[J]. Journal of Modern Information, 2014, 34(12): 154-158, 167. 本文引用 [1]

[18]	STROUD N J. Polarization and partisan selective exposure[J]. Journal of communication, 2010, 60(3), 556-576. 本文引用 [1]

[19]	LIPSEY M W, WILSON D B. Guidance on the application of meta analysis method[M]. Thousand Oaks: SAGE Publication, 2001. 本文引用 [1]

[20]

曾昭炳, 姚继军. 寻找“最佳证据”：如何运用元分析进行文献综述——以STEM教育对学生成绩的影响研究为例[J]. 华东师范大学学报(教育科学版), 2020, 38(6): 70-85.

ZENG

, YAO

. Finding the "best evidence": how to conduct literature review using meta-analysis—taking the impact of STEM education on student achievement as an example[J]. Journal of East China Normal University (educational sciences), 2020, 38(6): 70-85.

本文引用 [1]

[21]	严炜炜, 陈若瑜, 张敏. 基于元分析的在线知识付费意愿影响因素研究[J]. 情报学报, 2021, 40(2): 204-212. YAN W W, CHEN R Y, ZHANG M. Research on influencing factors of online knowledge payment intention based on meta-analysis[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(2): 204-212. 本文引用 [1]

[22]	韩继峰. 基于元分析的用户标注动机影响因素研究[J]. 情报探索, 2019(3): 6-10. HAN J F. Research on influencing factors of user tagging motivation based on meta-analysis[J]. Information research, 2019(3): 6-10. 本文引用 [1]

[23]	夏凌翔. 元分析及其在社会科学研究中的应用[J]. 西北师大学报(社会科学版), 2005, 42(5): 55-58. XIA L X. Meta-analysis and its application in social science research[J]. Journal of Northwest Normal University (social sciences), 2005, 42(5): 55-58. 本文引用 [1]

[24]	HIGGINS J P T, THOMPSON S G, DEEKS J J, et al. Measuring inconsistency in meta-analyses[J]. British medical journal, 2003, 327(7414): 557-560. 本文引用 [1]

[25]	MUKHERJEE A. Spotting fake reviewer groups in consumer markets[C]//Proceedings of the 19th ACM SIGKDD international conference on knowledge discovery and data mining. New York: Association for Computing Machinery, 2013: 985-993. 本文引用 [1]

[26]	任亚峰, 姬东鸿, 张红斌, 等. 基于PU学习算法的虚假评论识别研究[J]. 计算机研究与发展, 2015, 52(3): 639-648. REN Y F, JI D H, ZHANG H B, et al. Deceptive reviews detection based on positive and unlabeled learning[J]. Journal of computer research and development, 2015, 52(3): 639-648. 本文引用 [1]

[27]	DUAN W, GU B, WHINSTON A B. Do online reviews matter? an empirical investigation of panel data[J]. Decision support systems, 2008, 45(4): 1007-1016. 本文引用 [1]

[28]	LUCA M, ZERVAS G. Fake it till you make it: reputation, competition, and Yelp review fraud[J]. Management science, 2016, 62(12): 3412-3427. 本文引用 [1]