Instruments of corporate risk and reputation assessment tools are quintessentially developed on structured quantitative data linked to financial ratios and macroeconomics. An emerging stream of studies has challenged this norm by demonstrating improved risk assessment and model prediction capabilities through unstructured textual corporate data. Fake online consumer reviews pose serious threats to a business’ competitiveness and sales performance, directly impacting revenue, market share, brand reputation and even survivability. Research has shown that as little as three negative reviews can lead to a potential loss of 59.2 % of customers. Amazon, as the largest e-commerce retail platform, hosts over 85,000 small-to-medium-size (SME) retailers (UK), selling over fifty percent of Amazon products worldwide. Despite Amazon's best efforts, fake reviews are a growing problem causing financial and reputational damage at a scale never seen before. While large corporations are better equipped to handle these problems more efficiently, SMEs become the biggest victims of these scam tactics. Following the principles of attribute (AA) and responsible (RA) analytics, we present a novel hybrid method for indexing enterprise risk that we call the Fake Review Index (). The proposed modular approach benefits from a combination of structured review metadata and semantic topic index derived from unstructured product reviews. We further apply LIME to develop a Confidence Score, demonstrating the importance of explainability and openness in contemporary analytics within the OR domain. Transparency, explainability and simplicity of our roadmap to a hybrid modular approach offers an attractive entry platform for practitioners and managers from the industry.

中文翻译：

---

开发可解释的电子商务虚假评论指数：属性分析方法

企业风险和声誉评估工具本质上是根据与财务比率和宏观经济学相关的结构化定量数据开发的。一系列新兴研究通过非结构化文本公司数据展示了改进的风险评估和模型预测能力，对这一规范提出了挑战。虚假的在线消费者评论对企业的竞争力和销售业绩构成严重威胁，直接影响收入、市场份额、品牌声誉甚至生存能力。研究表明，只要 3 条负面评论就可能导致 59.2% 的客户流失。亚马逊作为最大的电子商务零售平台，拥有超过 85,000 家中小型 (SME) 零售商（英国），销售全球 50% 以上的亚马逊产品。尽管亚马逊尽了最大努力，但虚假评论问题日益严重，造成了前所未有的财务和声誉损失。虽然大公司更有能力更有效地处理这些问题，但中小企业却成为这些诈骗策略的最大受害者。遵循属性（AA）和责任（RA）分析的原则，我们提出了一种新颖的混合方法来索引企业风险，我们称之为虚假评论索引（Fake Review Index）。所提出的模块化方法受益于结构化评论元数据和源自非结构化产品评论的语义主题索引的组合。我们进一步应用 LIME 来开发置信度分数，证明可解释性和开放性在 OR 领域内的当代分析中的重要性。我们的混合模块化方法路线图的透明度、可解释性和简单性为行业从业者和管理者提供了一个有吸引力的入门平台。