针对论坛数据特点的汽车质量问题挖掘

doi:10.16381/j.cnki.issn1003-207x.2019.0233

摘要/Abstract

摘要： 汽车质量是汽车生产商在市场中立足的根本和发展的保证，了解并掌握用户反馈的汽车质量问题是其维护品牌声誉、提升市场竞争力且最贴近用户的重要途径。本文基于网络论坛数据，对用户的用车体验中隐含的汽车质量问题进行挖掘。针对论坛数据和用户体验的特点，首先选取文本特征，识别出用户体验中涉及汽车质量问题的文本；然后依据质量问题对应汽车部件与问题类型间的关系，提出了一种汽车质量问题的提取方法；最后，利用某实际论坛数据验证了本文方法的可行性与有效性。本文提出的针对论坛数据特点的汽车质量问题挖掘方法，可以帮助汽车生产商及时获取可能存在的汽车质量问题，在质量管理过程中具有重要意义。

关键词: 论坛数据, 用户生成内容, 汽车质量, 质量问题挖掘, 文本挖掘

Abstract: As the embodiment of the core competitiveness of automobile manufacturers, automobile quality is the basis and guarantee for the development of automobile manufacturers in the market. Understanding and mastering the automobile quality problems from user feedback is an important means to maintain brand reputation, enhance market competitiveness, and be close to users.Based on the data of online forums, the car quality problems found by the users when using or driving the cars are excavated. According to the characteristics of the forum data and user experience,firstly, the text features are selected to identify the texts related to automobile quality problems in the user experience. Then, according to the relationship between automobile units corresponding to quality problems and the types of problems,a method is proposed to extract automobile quality problems.The Apriori algorithm is used to extract the automobile units, and the semantic K-means clustering and hierarchical clustering algorithm are used to extract the corresponding problem types. The combination of automobile units and the types of problems leads to the quality problems of automobiles.Finally, the feasibility and effectiveness of this method are verified by actual forum data. The proposed method to mine automobile quality problems based on the characteristics of forum datacan help automobile manufacturers obtain and analyze potential automobile quality problems in time and assist companiesin making management decisions, which is of great significance in the process of quality management.

Key words: forum data, user-generated content, automobile quality, quality problems mining, text mining

中图分类号:

F253.3

王余行, 党延忠, 徐照光. 针对论坛数据特点的汽车质量问题挖掘[J]. 中国管理科学, 2021, 29(9): 201-212.

WANG Yu-hang, DANG Yan-zhong, XU Zhao-guang. Mining Automobile Quality Problems Based on the Characteristics of Forum Data[J]. Chinese Journal of Management Science, 2021, 29(9): 201-212.

参考文献

[1] 王宗水, 赵红, 秦绪中. 我国家用汽车顾客感知价值及提升策略研究[J]. 中国管理科学, 2016, 24(2):125-133. Wang Zongshui, Zhao Hong, Qing Xuzhong.Research on customer perceived value of family using car and promoted strategies in China[J].Chinese Journal of Management Science, 2016, 24(2):125-133.
[2] Xu Z, Dang Y, Munro P. Knowledge-driven intelligent quality problem-solving system in the automotive industry[J]. Advanced Engineering Informatics, 2018, 38:441-457.
[3] Jang S, Prasad A, Ratchford B T. Consumer search of multiple information sources and its impact on consumer price satisfaction[J]. Journal of Interactive Marketing, 2017, 40:24-40.
[4] 闫强, 孟跃. 在线评论的感知有用性影响因素——基于在线影评的实证研究[J]. 中国管理科学, 2013,21(S1):126-131. Yan Qiang, Meng Yue.Factors affecting the perceived usefulness of online reviews——An empirical study based on online film reviews[J]. Chinese Journal of Management Science, 2013,21(S1):126-131.
[5] Li Y M, Chen H M, Liou J H, et al. Creating social intelligence for product portfolio design[J]. Decision Support Systems, 2014, 66(C):123-134.
[6] Lee-Kelley L, Turner N. PMO managers' self-determined participation in a purposeful virtual community-of-practice[J]. International Journal of Project Management, 2017, 35(1):64-77.
[7] 刘宇, 梁循, 杨小平. 基于Petri网的微博网络信息传播模型[J]. 中国管理科学, 2018, 26(12):161-170. Liu Yu, Yang Xun, Yang Xiaoping.Information propagation model of microblog network based on petri net[J]. Chinese Journal of Management Science,2018, 26(12):161-170.
[8] Raji R A, Mohd Rashid S, Mohd Ishak S, et al. Do firm-created contents on social media enhance brand equity and consumer response among consumers of automotive brands?[J]. Journal of Promotion Management, 2020, 26(1):19-49.
[9] Hammond M. Users of the world, unite! The challenges and opportunities of Social Media[J]. Business Horizons, 2010, 53(1):59-68.
[10] 冯娇, 姚忠. 基于社会学习理论的在线评论信息对购买决策的影响研究[J]. 中国管理科学, 2016, 24(9):106-114. Feng Jiao, Yao Zhong.Consumer-generated views base on social learning theory:Implications for purchase decision[J]. Chinese Journal of Management Science,2016, 24(9):106-114.
[11] 施晓菁, 梁循, 孙晓蕾. 基于在线评级和评论的评价者效用机制研究[J]. 中国管理科学, 2016, 24(5):149-157. Shi Xiaojing, Liang Xun, Sun Xiaolei.Rater utility mechanism research based on online rating and comment[J]. Chinese Journal of Management Science,2016, 24(5):149-157.
[12] Zhang Wenhao, Xu Hua, Wan Wei. Weakness finder:Find product weakness from Chinese reviews by using aspects based sentiment analysis[J]. Expert Systems with Applications, 2012, 39(11):10283-10291.
[13] Abbasi A, Chen H, Salem A. Sentiment analysis in multiple languages:Feature selection for opinion classification in Web forums[J]. Acm Transactions on Information Systems, 2008, 26(3):1-34.
[14] Loughran T, McDonald B. When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks[J]. The Journal of Finance, 2011, 66(1):35-65.
[15] Abrahams A S, Jiao J, Wang G A, et al. Vehicle defect discovery from social media[J]. Decision Support Systems, 2012, 54(1):87-97.
[16] Jiang Cuiqing, Liu Yao, Ding Yong, et al. Capturing helpful reviews from social media for product quality improvement:A multi-class classification approach[J]. International Journal of Production Research, 2017, 55(12):3528-3541.
[17] Abrahams A S, Fan W, Wang G A, et al. An integrated text analytic framework for product defect discovery[J]. Production & Operations Management, 2015, 24(6):975-990.
[18] 蒋翠清,王齐林,刘士喜,等.中文社会媒体环境下半监督学习的汽车缺陷识别方法[J].中国管理科学, 2014(s1), 677-685. Jiang Cuiqing, Wang Qilin, Liu Shixi, et al.Semi-supervised learning for automobile defect identification in the context of Chinese social media[J]. Chinese Journal of Management Science,2014(s1), 677-685.
[19] Liu Yao, Jiang Cuiqing, Ding Yong, et al. Identifying helpful quality-related reviews from social media based on attractive quality theory[J]. Total Quality Management & Business Excellence, 2017(1):1-20.
[20] 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.
[21] Min H J, Park J C. Identifying helpful reviews based on customer's mentions about experiences[J]. Expert Systems with Applications, 2012, 39(15):11830-11838.
[22] Xu Z, Dang Y, Munro P, et al. A data-driven approach for constructing the component-failure mode matrix for FMEA[J]. Journal of Intelligent Manufacturing, 2020, 31(1):249-265.
[23] Hu M, Liu B. Mining and summarizing customer reviews[C]//Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, 2004:168-177.
[24] 李实, 叶强, 李一军,等. 中文网络客户评论的产品特征挖掘方法研究[J]. 管理科学学报, 2009(2):142-152. Li Shi, Ye Qiang, Li Yijun, et al.Mining features of products from Chinese customer online reviews[J]. Journal of Management Sciences in China, 2009(2):142-152.
[25] Guo Honglei, Zhu Huijia, Guo Zhili, et al. Product feature categorization with multilevel latent semantic association[C]//Proceedings of the 18th ACM conference on Information and knowledge management, ACM, 2009:1087-1096.
[26] Jo Y, Oh A H. Aspect and sentiment unification model for online review analysis[C]//ACM International Conference on Web Search and Data Mining, ACM, 2011:815-824.
[27] 邱云飞, 赵彬, 林明明,等. 结合语义改进的K-means短文本聚类算法[J]. 计算机工程与应用, 2016, 52(19):78-83. Qiu Yunfei, Zhao Bin, Lin Mingming et al.Improved K-means clustering algorithm combined semantic similarityof short text[J]. Computer Engineering and Applications, 2016, 52(19):78-83.
[28] Kodinariya T M, Makwana P R. Review on determining number of Cluster in K-Means Clustering[J]. International Journal, 2013, 1(6):90-95.