A systematic review of data-driven approaches in player modeling of educational games
A systematic review of data-driven approaches in player modeling of educational games
复制标题
教育游戏玩家建模中数据驱动方法的系统回顾
DOI：
--
复制
发表时间：
2017
影响因子：
12
通讯作者：
Heuiseok Lim
中科院分区：
文献类型：
--
作者：
Danial Hooshyar;M. Yousefi;Heuiseok Lim
近年来，人们对开放式互动教育工具（如游戏）的兴趣越来越大。开发游戏最重要的方面之一在于建模和预测个人行为，即研究游戏中玩家的计算模型。虽然基于模型的方法被认为是标准的，但由于教育游戏可以创建巨大的动作空间，它们的应用往往非常困难。出于这个原因，数据驱动的方法已经显示出希望，部分原因是它们不完全依赖于专家知识。本研究旨在系统地回顾现有的研究使用数据驱动的方法在教育游戏的玩家建模。本研究的主要目标是识别、分类和汇集相关方法。我们仔细调查了10年（2008-2017年）的研究样本，这些研究是关于教育游戏玩家建模的数据驱动方法，因此发现了67项重要的研究工作。然而，我们的入选标准将样本减少到21项研究，这些研究涉及四个主要研究问题，因此我们对这些已发表作品的问题，方法和发现进行了分析和分类，我们对这些作品进行了评估，并根据非统计方法得出结论。我们发现，数据驱动方法在教育游戏研究中的研究主要有三个沿着方向：第一，数据驱动方法在教育游戏玩家建模中的目标，即行为建模、目标识别和过程内容生成;最后，在教育游戏的玩家建模中使用数据驱动方法的当前挑战，即游戏数据，玩家模型中的时间预测，统计技术，算法效率，知识工程，泛化问题和数据稀疏问题。最后，我们解决了该领域未来的四个关键挑战，即缺乏适当的和丰富的数据公开提供给研究人员，缺乏一个数据驱动的方法来识别概念特征的日志数据，混合球员建模方法，和数据挖掘技术的个人预测。
Recent years have seen growing interest in open-ended interactive educational tools such as games. One of the most crucial aspects of developing games lies in modeling and predicting individual behavior, the study of computational models of players in games. Although model-based approaches have been considered standard for this purpose, their application is often extremely difficult due to the huge space of actions that can be created by educational games. For this reason, data-driven approaches have shown promise, in part because they are not completely reliant on expert knowledge. This study seeks to systematically review the existing research on the use of data-driven approaches in player modeling of educational games. The primary objectives of this study are to identify, classify, and bring together the relevant approaches. We have carefully surveyed a 10-year sample (2008–2017) of research studies conducted on data-driven approaches in player modeling of educational games, and thereby found 67 significant research works. However, our criteria for inclusion reduced the sample to 21 studies that addressed four primary research questions, and so we analyzed and classified the questions, methods, and findings of these published works, which we evaluated and from which we drew conclusions based on non-statistical methods. We found that there are three primary avenues along which data-driven approaches have been studied in educational games research: first, the objective of data-driven approaches in player modeling of educational games, namely behavior modeling, goal recognition, and procedural content generation; second, approaches employed in such modeling; finally, current challenges of using data-driven approaches in player modeling of educational games, namely game data, temporal forecasting in player models, statistical techniques, algorithmic efficiency, knowledge engineering, problem of generalizability, and data sparsity problem. In conclusion we addressed four critical future challenges in the area, namely, the lack of proper and rich data publicly available to the researchers, the lack of a data-driven method to identify conceptual features from log data, hybrid player modeling approaches, and data mining techniques for individual prediction.