Data Mining and Learning Analytics

CHAPTER 10 INVESTIGATING CO‐OCCURRENCE PATTERNS OF LEARNERS’ GRAMMATICAL ERRORS ACROSS PROFICIENCY LEVELS AND ESSAY TOPICS BASED ON ASSOCIATION ANALYSIS

Yutaka Ishii

Center for Higher Education Studies, Waseda University, Tokyo, Japan

10.1 INTRODUCTION

10.1.1 The Relationship between Data Mining and Educational Research

Investigating learners’ grammatical errors is a very important area in language teaching. In the past, this research was conducted only in the area of language teaching. However, in recent years, it has been conducted in the field of natural language processing such as the research on automated scoring of learners’ writing or speaking and automated grammatical error detection. The reason is that with the advancement of computer technologies, the technique of machine learning and data mining has been developed quite extensively. As a result, the research of educational application to natural language processing has been popular. For example, at the conference of “Helping Our Own” (HOO) 2011 and 2012, shared task for grammatical error correction was conducted. Moreover, in Japan, Error Detection and Correction Workshop (EDCW) 2012 was also conducted. This workshop aims at detecting learners’ grammatical errors using shared language resources.

Data mining is an automatic approach to extract patterns of regularity or relationship from massive data (Adriaans & Zantinge, 1998). In the past, data analysis had been conducted only with statistical methods. However, ...