User reviews are now an essential source of information for consumers, exerting strong influence on purchase decisions. Broadly speaking, reviews rated by consumers as more helpful exert a greater influence downstream. The current research examines how the linguistic characteristics of a review affect its helpfulness score. Using a convolutional neural network (CNN), this research analyzes the linguistic subjectivity and objectivity of over 2 million reviews on Amazon. The results show that, ceteris paribus, both linguistic subjectivity and objectivity have a positive impact on review helpfulness. However, contrary to consumers' intuition, when subjectivity and objectivity are combined in the same review, review helpfulness increases less than their respective separate effects would predict, especially for hedonic products. We conceptualize that this results from the increased complexity of messages mixing subjective and objective sentences, which requires more effortful processing. The findings extend the literature on online reviews, word-of-mouth, and text analysis in marketing, and offer practical implications for marketing communication and facilitation of reviews.

中文翻译：

---

在线评论中主观性和客观性的影响：卷积神经网络方法

用户评论现在已成为消费者重要的信息来源，对购买决策产生重大影响。一般来说，消费者认为更有帮助的评论会对下游产生更大的影响。当前的研究探讨了评论的语言特征如何影响其有用性得分。这项研究使用卷积神经网络 (CNN) 分析了亚马逊上超过 200 万条评论的语言主观性和客观性。结果表明，在其他条件不变的情况下，语言的主观性和客观性都对复习有用性产生积极影响。然而，与消费者的直觉相反，当主观性和客观性结合在同一篇评论中时，评论有用性的增加小于其各自单独效果所预测的，特别是对于享乐产品而言。我们认为这是由于混合主观和客观句子的消息复杂性增加而导致的，这需要更努力的处理。这些发现扩展了营销中在线评论、口碑和文本分析的文献，并为营销传播和促进评论提供了实际意义。