教育数据挖掘工具综述

斯特凡•斯莱特¹，斯万克•约克西莫维奇²，维特梅•科万诺维奇²，莱恩•贝克¹，德拉甘•加斯维奇²

（1.宾夕法尼亚大学,美国 费城 PA 19104；2.爱丁堡大学, 英国 爱丁堡 EH8 9AB）

崔鑫 王靖 译

【摘 要】数据挖掘拥有悠久的历史，它可以追溯到探索性数据分析(Tukey, 1977)，且目前已经形成了有效的、可推广的方法。本文将讨论教育数据挖掘研究与实践中逐渐兴起的一些工具，以及在更广泛的层面上数据挖掘和数据科学研究者所使用的相关工具，近40种教育领域数据挖掘与分析的常用工具，包括数据处理与特征工程工具、算法分析工具、可视化效果工具，以及EDM和LA的特殊应用，如贝叶斯知识跟踪工具、文本挖掘、社会网络分析、过程与序列挖掘、PSLC服务站等。本文将为初次接触这一领域的研究者提供有用的信息，以帮助他们找到有用的工具。

【关键词】数据挖掘工具；特征工程；算法分析；可视化

Tools for Educational Data Mining

Stefan Slater¹, Srecko Joksimovic², Vitomir Kovanović², Ryan Baker¹ and Dragan Gašević²

（1. University of Pennsylvania， Philadelphia, PA 19104, USA；2. The University of Edinburgh, Edinburgh EH8 9AB,UK）

Abstract: Data mining as an area of methods has an extended history going back to exploratory data analysis and has established methods for determining validity and generalizability. This paper will discuss some of the tools that have emerged for research and practice in educational data mining, discussing the research fields where relevant tools also used by the broader data mining and data science communities. Then this paper will reviewe nearly 40 tools frequently used for data mining/analytics in the area of education, including data manipulation and feature engineering tools, algorithmic analysis tools, visualizations and special application of EDM and LA, such as Bias tracking tools, text mining, knowledge of social network analysis, process and sequence mining, PSLC service station etc. It is expected that this review will provide useful information to researchers new to this area of methods on what tools they may find useful.

Keywords: data mining tools; feature engineering; algorithm analysis; visualization

下载：        教育数据挖掘工具综述.pdf