Diego Buenaño-Fernández, Sergio Luján-Mora, William Villegas-Ch. 5th International Conference on Technological Ecosystems for Enhancing Multiculturality (TEEM 2017), p. 1-7, Cadiz (Spain), October 18-20 2017. ISBN: 978-1-4503-5386-1.
In recent years, the constant increase in the number of online courses has led to radical changes in the education sector. These new online learning environments present a series of challenges that are difficult to manage using traditional methods. The challenges relate to the level of commitment and motivation shown by students on this type of course. Several articles have been identified from the analysed literature related to the application of text or opinion mining techniques for the analysis of comments made in social networks. In the educational field, articles related to the topic that focus on the analysis of opinion have been identified based on entries included in discussion forums for online courses. Many publications are geared towards solutions in the English language, and the nature of linguistic analysis of this type of study makes it necessary to adapt them for languages other than English. In this paper, we explore the opinion mining through text mining in emails from Massive Open Online Courses (MOOC). The opinion mining expressed in emails is a complex task due to the thematic disparity of emails, their size and the depth of linguistic analysis required. The purpose of this study is to analyse students opinions about their courses, their instructors, and the main tools used on the course. The research focus on the calculation and analysis of the frequency of terms, the analysis of concordances, groupings and n-grams. The case study used in this paper is a MOOC on the topic of web development with more than 40,000 enrolled students.
Keywords: Opinion mining, Massive Open Online Course, MOOC, Supervised learning, Text mining
More information: Improvement of massive open online courses by text mining of students' emails: a case study