Understanding the formation process of negative customer engagement behaviours: a quantitative and qualitative interpretation

AbstractThe development of mobile internet has made it easier for negative emotions, cognitions and behaviours expressed by customers to be spread, and the damage caused by negative customer engagement behaviours (NCEBs) to the company's brand value and reputation has gradually been amplified. Therefore, this study aims to explore the formation process of NCEBs in online brand community by combining qualitative method with quantitative method. Xiaomi Community was selected as the data source platform, using Python programming language to crawl users’ comments in ‘11Ultra circle’ and machine learning methods to obtain negative emotional polarity comments. The text coding and classification of negative emotion polarity comments are mainly based on manual coding and supplemented by machine learning. Perform binary logistic regression on the classified data to obtain the impact of various factors on NCEBs. The results showed that there were differences in the impact of different factors on NCEBs. This article obtains a different result from existing literature, that is, cognition and emotion are no longer necessary factors for the generation of NCEBs. Company managers should start with pricing, users’ cognition mining, and identifying and solving key issues reported by users to suppress the occurrence of NCEBs.Keywords: Consumer behaviour; negative customer engagementonline communityquality management Disclosure statementNo potential conflict of interest was reported by the author(s).Notes1 https://weibo.com/u/36341487602 https://mp.weixin.qq.com/s/lS9-kBoVAqf3GhQMKD83Zg3 https://chejiahao.m.autohome.com.cn/info/82701024 https://auto.ifeng.com/qichezixun/20200928/1483345.shtml5 https://www.xiaomi.cn/6 https://www.xiaomi.cn/board/25686841Additional informationFundingThis work was supported by National Natural Science Foundation of China [grant number 72072104]; National Office of Philosophy and Social Sciences [grant number 18ZDA079].