面向带有非随机多模态评论反馈的序列推荐的双边状态空间模型
Two-Sided State-Space Models for Sequential Recommendation with Non-Random Multimodal Review Feedback
- Emory University（埃默里大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对双边平台序列推荐中评论反馈的非随机性与溢出效应问题，提出TS-SSM模型，经多数据集实验较现有基准模型在Recall@20上有显著提升。
AI中文摘要：
双边数字平台本质上是动态的：用户偏好会发生变化，项目（item）的流行度会演变，而评论既反映又驱动这些变化。然而，大多数序列推荐系统将评论视为更新用户状态的被动信号，存在两个未充分探索的方面：其一，评论的生成并非随机，而是取决于用户和项目不断演变的潜在状态；其二，评论可以重塑项目状态，在相关项目间引发溢出效应，并影响用户未来的决策。为解决这些差距，我们提出了一种用于事件条件序列推荐的双边状态空间模型（TS-SSM）。TS-SSM由三个组件构成：（1）模态非缺失随机融合模块，用于编码评论内容和信息观测模式；（2）结合时间变化与局部图消息传递的用户状态演化，利用相关项目状态优化用户偏好；（3）具有正负评论反馈非对称留存的项目状态演化。在六个亚马逊类别上的实验显示，TS-SSM较BSARec的Recall@20提升了14.8%至18.8%，平均超过HM4SR达11.7%；在Goodreads Fantasy数据集上，其将Recall@20从HM4SR的0.5191提升至0.5847； ablation实验凸显了观测模式、局部传播和项目动态的不同贡献。
英文摘要：
Two-sided digital platforms are inherently dynamic: user preferences shift, item popularity evolves, and reviews both reflect and drive these changes. Yet most sequential recommendation systems treat reviews as passive signals for updating user states, leaving two aspects underexplored. First, review generation is nonrandom, depending on evolving latent states of both users and items. Second, reviews can reshape item states, induce spillover across related items, and influence future user decisions. To address these gaps, we propose a two-sided state-space model (TS-SSM) for event-conditioned sequential recommendation. TS-SSM consists of three components: (1) a modality-missing-not-at-random fusion module that encodes review content and informative observation patterns; (2) user-state evolution with temporal variation and local graph message passing that uses related item states to refine user preferences; and (3) item-state evolution with asymmetric carryover of positive and negative review feedback. In experiments across six Amazon categories, TS-SSM increases Recall@20 over BSARec by 14.8%--18.8% and exceeds HM4SR by 11.7% on average. On Goodreads Fantasy, Recall@20 improves HM4SR from .5191 to .5847. Ablations highlight distinct contributions of observation patterns, local propagation, and item dynamics.
