基于知识采纳模型和多层感知机神经网络的评论有用性识别研究

doi:10.16381/j.cnki.issn1003-207x.2020.2215

摘要/Abstract

摘要： 移动互联网、社交媒体平台及电子商务的迅速发展，产生了大量的用户评论，其商业价值凸显，如何有效识别用户评论的有用性成为重要研究主题。本文提出基于知识采纳模型(Knowledge Adoption Model，KAM)理论和多层感知机(Multilayer Perceptron, MLP)神经网络的分类算法对评论文本进行有用性识别。该算法根据知识采纳模型理论从评论质量和评论来源可信度两方面进行评论有用性识别的特征提取：利用先验领域知识词典构造领域词占比、停用词占比等评论质量方面的特征,有效解决了特定领域评论存在的领域知识壁垒问题；根据评论作者的粉丝数、作者获赞数等信息构建评论来源可信度方面的特征。为了验证本文所提方法的识别效果，本文采用知乎论坛中医相关评论数据进行实验；实验结果表明，本文提出的方法能有效提高在线评论有用性的分类效果，提高了可解释性。

关键词: 在线评论；评论信息有用性；知识采纳模型；多层感知机神经网络

Abstract: With the rapid development of the mobile Internet, social media platforms and electronic commerce, a large amount of online reviews with user comments have been generated and show great business value. The recognition of usefulness of user comments provides an important guarantee for mining valuable information in comments. To this end, a classification algorithm is proposed based on the Knowledge Adoption Model (KAM) theory and Multilayer Perceptron (MLP) neural networks to identify the usefulness of online reviews in social media platforms. According to the knowledge adoption model theory, the algorithm extracts the featuresfor identifying usefulness of comments from two aspects: review quality and review source credibility.Specifically, to represent the review quality by constructing featuresusing the proportion of domain words and the proportion of stop words via a dictionary containing prior domain knowledge, which effectively alleviates the problem of domain knowledge barriers in cross-domain reviews; to represent the review source credibility by constructing the features based on the number of fans of the author and the number of likes the author has already received so far. In order to verify the recognition effect of the method proposed, traditional Chinese medicine related comments are crawled from Zhihu.com as the experimental data set. The experimental results show that the feature construction method, which integrates domain knowledge into text feature representation by calculating the proportion of domain words, can effectively alleviates the problems of knowledge barriers in specific fields; and the proposed method provides important information of review quality for the identification of the usefulness of online reviews, and thus has improved the identifying effect of usefulness of online comments and increasedthe interpretability to some extent.

Key words: online reviews; usefulness of online reviews; knowledge adoption model; multilayer perceptron neural network

中图分类号:

TP391.1

张婧, 周怡欣, 胡涵, 卞亦文. 基于知识采纳模型和多层感知机神经网络的评论有用性识别研究[J]. 中国管理科学, 2022, 30(4): 264-274.

ZHANG Jing, ZHOU Yi-xin, HU Han, BIAN Yi-wen. Identification of Usefulness for Online Reviews Based on Knowledge Adoption Model and Multilayer Perceptron Neural Network[J]. Chinese Journal of Management Science, 2022, 30(4): 264-274.

参考文献

［1］姜巍, 张莉, 戴翼,等. 面向用户需求获取的在线评论有用性分析［J］. 计算机学报, 2013, 36(1):119-131.Jiang Wei, Zhang Li, Dai Yi, et al. Analyzing helpfulness of online reviews for user requirements elicitation［J］. Chinese Journal of Computers, 2013, 36(1):119-131.
［2］ Shin S, Chung N, Xiang Z, et al. Assessing the impact of textual content concreteness on helpfulness in online travel reviews［J］. Journal of Travel Research, 2019, 58(4):579-593.
［3］ Liu Xiaomo, Wang G A, Fan Weiguo, et al. Finding useful solutions in online knowledge communities: A theory-driven design and multilevel analysis［J］. Information Systems Research, 2020, 31(3):731-752.
［4］郝媛媛, 叶强, 李一军. 基于影评数据的在线评论有用性影响因素研究［J］. 管理科学学报, 2010, 13(8):78-88.Hao Yuanyuan, Ye Qiang, Li Yijun. Research on online impact factors of customer reviews usefulness based on movie reviews data［J］. Journal of Management Sciences in China, 2010, 13(8):78-88.
［5］ Mudambi S M, Schuff D. Research note: What makes a helpful online review? A study of customer reviews on Amazon. com［J］. MIS Quarterly, 2010, 34(1):185-200.
［6］ Baek H, Ahn J, Choi Y. Helpfulness of online consumer reviews: Readers’ objectives and review cues［J］. International Journal of Electronic Commerce, 2012, 17(2): 99-126.
［7］ Chen Yubo, Xie Jinhong. Online consumer review: Word-of-mouth as a new element of marketing communication mix［J］. Management Science, 2008, 54(3):477-491.
［8］刘伟, 徐鹏涛. O2O电商平台在线点评有用性影响因素的识别研究——以餐饮行业O2O模式为例［J］. 中国管理科学, 2016, 24(5):168-176.Liu Wei, Xu Pengtao. A study on influencing factors of the helpfulness of online reviews in O2O of restaurant industry-based on tobit model［J］. Chinese Journal of Management Science, 2016, 24(5):168-176.
［9］张艳辉, 李宗伟, 赵诣成. 基于淘宝网评论数据的信息质量对在线评论有用性的影响［J］. 管理学报, 2017, 14(1):77-85.Zhang Yanhui, Li Zongwei, Zhao Yicheng. How the information quality affects the online reviews usefulness?-An empirical analysis based on Taobao review data［J］. Chinese Journal of Management, 2017, 14(1):77-85.
［10］苗蕊, 徐健. 评分不一致性对在线评论有用性的影响—归因理论的视角［J］. 中国管理科学, 2018, 26(5):178-186.Miao Rui, Xu Jian. The impact of rating inconsistency on online reviews helpfulness: A perspective on attribution theory［J］. Chinese Journal of Management Science, 2018, 26(5):178-186.
［11］ Liu Zhiwei, Park S. What makes a useful online review? Implication for travel product websites［J］. Tourism Management,2015, 47:140-151.
［12］ Albert H, Chen Kuanchin, David C, et al. A study of factors that contribute to online review helpfulness［J］. Computers in Human Behavior, 2015, 48:17-27.
［13］殷国鹏. 消费者认为怎样的在线评论更有用?—社会性因素的影响效应［J］. 管理世界, 2012,28(12):115-124.Yin Guopeng. What online comments do customers think are more useful-Influence effect of social factors［J］. Management World, 2012,28(12):115-124.
［14］朱丽叶, 袁登华, 张静宜. 在线用户评论质量与评论者等级对消费者购买意愿的影响——产品卷入度的调节作用［J］. 管理评论, 2017, 29(2):87-96.Zhu Liye, Yuan Denghua, Zhang Jingyi. The impact of online user reviews quality and commentators rank on consumer purchasing intention-The moderating role of product involvement［J］. Management Review, 2017, 29(2):87-96.
［15］ Ghose A, Ipeirotis P G. Estimating the helpfulness and economic impact of product reviews: Mining text and reviewer characteristics［J］. IEEE Transactions on Knowledge and Data Engineering, 2011, 23(10), 1498-1512.
［16］蔡淑琴, 秦志勇, 李翠萍,等. 面向负面在线评论的情感强度对有用性的影响研究［J］. 管理评论, 2017, 29(2):79-86.Cai Shuqin, Qin Zhiyong, Li Cuiping, et al. Study on the usefulness of online reviews at different emotional intensity［J］. Management Review, 2017, 29(2):79-86.
［17］ Fang Bin, Ye Qiang, Kucukusta D, et al. Analysis of the perceived value of online tourism reviews: Inuence of readability and reviewer characteristics［J］. Tourism Management, 2016, 52:498-506.
［18］严建援, 李扬, 冯淼, 等. 用户问答与在线评论对消费者产品态度的交互影响［J］. 管理科学, 2020, 33(2):102-113.Yan Jianyuan, Li Yang, Feng Miao, et al. Interaction effects of customer Q&As and online reviews on consumer product attitudes［J］. Journal of Management Science, 2020, 33(2):102-113.
［19］陈文亮,朱靖波,朱慕华,等.基于领域词典的文本特征表示［J］.计算机研究与发展,2005,42(12):2155-2160.Chen Wenliang, Zhu Jingbo, Zhu Muhua, et al. Text representation using domain dictionary［J］. Journal of Computer Research and Development, 2005, 42(12):2155-2160.
［20］ Sussman S W, Siegal W S. Informational influence in organizations: An integrated approach to knowledge adoption［J］. Information Systems Research, 2003, 14(1):47-65.
［21］ Cheung C, Lee M, Rabjohn N. The impact of electronic word-of-mouth-The adoption of online opinions in online customer communities［J］. Internet Research, 2008, 18(3):229-247.
［22］ Erkan I, Evans C. The influence of eWOM in social media on consumers’ purchase intentions: An extended approach to information adoption［J］. Computers in Human Behavior, 2016, 61:47-55.
［23］琚春华, 郭飞鹏. 基于支持向量机的分布数据挖掘模型DSVM［J］. 系统工程理论与实践, 2010, 30(10):1855-1863.Ju Chunhua, Guo Feipeng. Distributed data mining model based on support vector machines［J］. Systems Engineering-Theory & Practice, 2010, 30(10):1855-1863.
［24］肖斌卿, 杨旸, 李心丹, 等. 基于模糊神经网络的小微企业信用评级研究［J］. 管理科学学报,2016, 19(11):114-126.Xiao Binqing, Yang Yang, Li Xindan, et al. Research on credit rating of small and micro enterprises based on fuzzy neural network［J］. Journal of Management Sciences in China, 2016, 19(11):114-126.
［25］杨建武. 基于核方法的XML文档自动分类［J］. 计算机学报, 2011, 34(2):353-359.Yang Jianwu. XML document classification based on kernel method［J］. Chinese Journal of Computers, 2011, 34(2):353-359.
［26］于浩, 步丰林, 高剑峰. 感知器在语言模型训练中的应用［J］. 计算机研究与发展, 2006(2):260-267.Yu Hao, Bu Fenglin, Gao Jianfeng. Perceptron for language modeling［J］. Journal of Computer Research and Development, 2006(2):260-267.
［27］ Hu Hao, Li Ping, Chen Yan. Biterm-based multilayer perceptron network for tagging short text［C］//Proceedings of 2015 IEEE 7th International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM), Angkor Wat, Cambodia, 2015, IEEE, 2015:212-217.
［28］ Qader W A, Ameen M M, Ahmed B I. An overview of bag of words; Importance, implementation, applications, and challenges［C］//Proceedings of 2019 International Engineering Conference (IEC), Erbil, Iraq, 2019, IEEE, 2020:200-204.
［29］ Ngo-Ye T L, Sinha A P. The influence of reviewer engagement characteristics on online review helpfulness: A text regression model［J］. Decision Support Systems, 2014,61:47-58.
［30］ Joulin A, Grave E, Bojanowski P, et al. Bag of tricks for efficient text classification［C］//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, April 3-7, 2017.
［31］王伟, 王洪伟. 特征观点对购买意愿的影响:在线评论的情感分析方法［J］. 系统工程理论与实践, 2016, 36(1):63-76.Wang Wei, Wang Hongwei. The influence of aspect-based opinions on user’s purchase intention using sentiment analysis of online reviews［J］. Systems Engineering-Theory & Practice, 2016, 36(1):63-76.
［32］ Yang Zhilin, Cai Shaohan, Zhou Zheng, et al. Development and validation of an instrument to measure user perceived service quality of information presenting Web portals［J］. Information & Management, 2005, 42(4):575-589.
［33］欧阳红兵,黄亢,闫洪举.基于LSTM神经网络的金融时间序列预测［J］.中国管理科学,2020,28(4):27-35.Ouyang Hongbing, Huang Kang, Yan hongju. Prediction of financial time series based on LSTM neural network［J］. Chinese Journal of Management Science, 2020, 28(4):27-35.