2026年1月团队成果被ABS 4期刊IJRM录用；

点击次数：

基础信息

• 标题：Unveiling consumer preferences: a theory-based multimodal deep learning architecture for explainable recommendation

• 作者：刘心语，钱洋*（共同一作），刘业政，Jennifer Shang，姜元春，柴一栋

• 发表期刊/来源：International Journal of Research in Marketing

• 链接：https://www.sciencedirect.com/science/article/abs/pii/S0167811626000078

摘要

This study constructs an explainable recommendation via combining product images, textual descriptions, user reviews, and user-item interactions. We propose a theory-based multimodal deep learning architecture. Specifically, we first extract the element-level features from product display information, including region-level visual and word-level textual features. To measure the impacts of these element-level features on user preferences, we introduce attention mechanisms. In addition, we inject the user reviews to disentangle the effects of visual and textual features on user preferences. Finally, we introduce a stick-breaking method to measure the asymmetrical influence of images and textual descriptions at the holistic level. To evaluate our model’s utility, we conduct experiments from four perspectives: recommendation performance, explanatory analysis, mechanism, and robustness. Experimental results show that our model can improve recommendation performance and give explanations. Our findings provide valuable insights for recommendation system design and offer guidance to marketers for optimizing product display pages.

中文翻译：本研究通过融合产品图像、文本描述、用户评论以及用户-物品交互数据，构建了一种可解释的推荐方法。我们提出了一种基于理论的多模态深度学习架构。具体而言，我们首先从产品展示信息中提取元素级特征，包括区域级视觉特征和词级文本特征。为了衡量这些元素级特征对用户偏好的影响，我们引入了注意力机制。此外，我们融入用户评论，以解耦视觉特征与文本特征对用户偏好的各自影响。最后，我们采用一种“折棒”（stick-breaking）方法，在整体层面上度量图像与文本描述对用户偏好的非对称性影响。为评估所提模型的有效性，我们从四个角度开展了实验：推荐性能、可解释性分析、机制验证和鲁棒性测试。实验结果表明，我们的模型不仅能提升推荐性能，还能提供可解释的推荐理由。本研究的发现为推荐系统的设计提供了有价值的见解，并为营销人员优化产品展示页面提供了实践指导。