Advantages and Limits of Text Mining Software for Analysis of Students' Satisfaction in Online Education (case study)
Abstract
The article deals with the analysis of students' feedback while studying at different online learning environments. Information about satisfaction is often available in the form of textual (frequently multilingual) information, hidden in users' reviews, chat rooms, tea rooms and other unspecified and unstructured ways of feedback.
To read such materials is often time-consuming and according to the quantity almost impossible. Text mining helps us 1/ to classify and to categorize the type of responses (complaints positive, negative, irrelevant, disease, etc.), usually on the base of sentiment analysis, 2/ to reveal the most frequent problems, 3/ to discover similarities and patterns and/or 4/ to identify similar text records (clusters).
Authors do not present the "big data" approach, based on powerful (and expensive) software. They focus just on part of the whole large scale of users' reflection to present the basic problems educational researchers might meet while working with available software tools (Statistica, Semantria) The unstructured text they processed (9 870 students' reviews/chats/remarks within 32 online courses) was created and published in 12 languages.
Authors describe the problems they met, especially in the area of multilingual information processing. Despite all effort, nearly half of languages failed to process