Quality of Experience (QoE) multidimensional concept is the key for successful delivery of multimedia services. Higher user requirements for new experiences such as augmented reality, virtual reality, and future 6G services set higher requirements for QoE. A more complex QoE space requires the use of data mining methods in order to process the data for better QoE prediction. The increased dimensionality of the QoE space becomes a limiting factor for achieving the desired QoE prediction accuracy. Existing studies considering the QoE multidimensional concept with approaches that overcome the challenge of increased QoE space dimensionality are of great importance for future research. Accordingly, this article aims to review the applications of Feature Selection (FS) methods in video QoE modeling. It provides a comprehensive overview of the existing studies with the categorization and review of applied FS methods with reference to the data collection and data modeling steps. The analysis included 71 studies which provides overview of the FS methods applications in video QoE modeling depending on the input Influence Factor (IF) dimension sizes, type of IFs, QoE prediction methods used and QoE evaluation type. Our review revealed the advantages of using FS methods in video QoE modeling, frequency of application of FS methods with potential of applying more FS methods in a series or a parallel, gives an overview of the achieved dimensionality reduction degree for different methods, and provides insights in opportunities for researchers for applying FS methods on complex multidimensional QoE space.

中文翻译：

---

视频体验质量建模的特征选择：系统的文献综述

体验质量 (QoE) 多维概念是成功交付多媒体服务的关键。用户对增强现实、虚拟现实、未来6G业务等新体验的更高要求对QoE提出了更高的要求。更复杂的 QoE 空间需要使用数据挖掘方法来处理数据以获得更好的 QoE 预测。QoE 空间维度的增加成为实现所需 QoE 预测精度的限制因素。考虑 QoE 多维概念的现有研究以及克服 QoE 空间维数增加挑战的方法对未来的研究非常重要。因此，本文旨在回顾特征选择 (FS) 方法在视频 QoE 建模中的应用。它提供了对现有研究的全面概述，并参考数据收集和数据建模步骤对应用的 FS 方法进行了分类和审查。该分析包括 71 项研究，根据输入影响因子 (IF) 维度大小、IF 类型、使用的 QoE 预测方法和 QoE 评估类型，概述了 FS 方法在视频 QoE 建模中的应用。我们的评论揭示了在视频 QoE 建模中使用 FS 方法的优势，FS 方法的应用频率以及串联或并行应用更多 FS 方法的潜力，概述了不同方法实现的降维程度，并提供了见解研究人员有机会在复杂的多维 QoE 空间上应用 FS 方法。