University of Twente Student Theses

Login

Dropout prediction in MOOCs : using sentiment analysis of users' comments to predict engagement.

Dmoshinskaia, Nataliia (2016) Dropout prediction in MOOCs : using sentiment analysis of users' comments to predict engagement.

[img] PDF
1MB
Abstract:Massive open online course attract a huge and diverse audience, however, the dropout rate in MOOCs is very high, which concerns educationalists and course developers. This study employs sentiment analysis to assess and predict learners engagement into MOOC forums for courses with digital badges which stimulate users to participate in discussions. Analysis of the tonality of participants' comments of two courses is used to predict learners' engagement in discussion forums. The data were operationalized with the help of R packages. Descriptive statistics was used to study correlation between sentiment characteristics and engagement and conditional inference trees were applied to build a more complex model with several variables. Unlike in some previous research no proof of lower sentiment level leading to higher dropout was found. Moreover, some critical involvement was discovered to be crucial for the course completion.
Item Type:Essay (Master)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:81 education, teaching
Programme:Educational Science and Technology MSc (60023)
Link to this item:https://purl.utwente.nl/essays/70461
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page