Analyzing Behavioral Patterns in an Introductory Programming MOOC at University Level

Massive open online courses (MOOCs) are an indispensable component in university education today. In large introductory courses especially, MOOCs can promote the efficiency of online teaching tremendously, since a large and heterogeneous group of students can be prepared for further courses and learn self-paced and self-directed. However, MOOCs are also characterized by high dropout rates and with a small group of people only completing the course. In this paper, we analyzed the Learning Object Oriented Programming MOOC from Technical University of Munich, an edX course that is dedicated to first-year students in different fields. The course run of 2019 with 2,489 enrolled users is analyzed for this purpose. The dropouts (89 %) were analyzed to better understand future course design. Interaction in the MOOC was considered in this context as a means of detecting behavioral patterns and predicting early dropouts. We found that the interaction with certain MOOC elements such as videos or the problem tool had a major impact on course success. These results may be useful for earlier dropout predictions and the design of future courses to provide an engaging environment with fewer students quitting the course.

[1]  S. Baldassarri.  2022 EDUCAUSE Horizont Report. Teaching and Learning Edition , 2022, Revista Iberoamericana de Tecnología en Educación y Educación en Tecnología.

[2]  Ø. Røynesdal,et al.  Pedagogical Approaches and Learning Activities, Content, and Resources Used in the Design of Massive Open Online Courses (MOOCs) in the Health Sciences: Protocol for a Scoping Review , 2022, JMIR research protocols.

[3]  P. Luik,et al.  Learners’ Performance in a MOOC on Programming , 2021, Education Sciences.

[4]  Georgios Kostopoulos,et al.  Early Dropout Prediction in MOOCs through Supervised Learning and Hyperparameter Optimization , 2021, Electronics.

[5]  Christian M. Stracke,et al.  A Systematic Literature Review on the Quality of MOOCs , 2021, Sustainability.

[6]  S. Kannadhasan,et al.  The Role of Future E-Learning System and Higher Education , 2020, International Journal of Advanced Research in Science, Communication and Technology.

[7]  Shampa Chakraverty,et al.  Tools and Techniques for Teaching Computer Programming: A Review , 2020 .

[8]  P. Sadler,et al.  Going over the cliff: MOOC dropout behavior at chapter transition , 2020 .

[9]  Zenun Kastrati,et al.  MOOC dropout prediction using machine learning techniques: Review and research challenges , 2018, 2018 IEEE Global Engineering Education Conference (EDUCON).

[10]  Marco Kalz,et al.  Refining success and dropout in massive open online courses based on the intention–behavior gap , 2017 .

[11]  An Yan,et al.  Predicting abandonment in online coding tutorials , 2017, 2017 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC).

[12]  Nitesh V. Chawla,et al.  MOOC Dropout Prediction: Lessons Learned from Making Pipelines Interpretable , 2017, WWW.

[13]  Peter Hubwieser,et al.  Computational thinking as springboard for learning object-oriented programming in an interactive MOOC , 2017, 2017 IEEE Global Engineering Education Conference (EDUCON).

[14]  Martin Ebner,et al.  A case study on narrative structures in instructional MOOC designs , 2017 .

[15]  Jaakko Kurhila,et al.  Multi-faceted support for MOOC in programming , 2012, SIGITE '12.

[16]  Peter Hubwieser,et al.  Web-Based Learning in Computer Science: Insights into Progress and Problems of Learners in MOOCs , 2020 .

[17]  Peter Hubwieser,et al.  Strictly Objects First: A Multipurpose Course on Computational Thinking , 2018 .

[18]  Christian Gütl,et al.  User Behavioral Patterns and Early Dropouts Detection: Improved Users Profiling through Analysis of Successive Offering of MOOC , 2018, J. Univers. Comput. Sci..

[19]  Shinichi Oeda,et al.  Log-Data Clustering Analysis for Dropout Prediction in Beginner Programming Classes , 2017, KES.

[20]  Achilles Kameas,et al.  Developing a Computer Programming MOOC , 2015 .

[21]  Jane Sinclair,et al.  Dropout rates of massive open online courses : behavioural patterns , 2014 .

[22]  Christian Gütl,et al.  MOOC in Latin America: Implementation and Lessons Learned , 2013, LTEC.

[23]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..