Marco Furini
ABSTRACT
Technologies have changed many different aspects of people's life and the recent CoVid-19 pandemic proved that education is not an exception. But technologies in education go beyond the simple use of video lectures: technologies might be exploited to improve personal learning. In this paper, we focus on the dropout of studies, a global phenomenon that artificial intelligence techniques are trying to ameliorate. Here, we investigate whether data related to the consumption of video lectures might improve the students' dropout prediction. We consider first-year students enrolled in our Department and we characterize them with personal, scholastic, academic and technological features. Then, we measure the performance of three machine learning algorithms in terms of accuracy and sensitivity. The experimental evaluation shows that Random Forest and KNN perform better that Decision Tree and also shows that data related to the use of video lectures improves the prediction performance for some degree programs (reaching 73% in terms of accuracy and sensitivity). These preliminary results show that the approach is promising and worth exploring in future studies.
- 2010. Next Generation Learning. White Paper. Bill and Melinda Gates Foundation (2010).Google Scholar
- C. Aina. 2013. Parental background and university dropout in Italy. Higher Education (2013). https://doi.org/10.1007/s10734-012-9554-zGoogle Scholar
- Sattar Ameri, Mahtab J. Fard, Ratna B. Chinnam, and Chandan K. Reddy. 2016. Survival Analysis Based Framework for Early Prediction of Student Dropouts. In Conference on Information and Knowledge Management. 903--912. https://doi.org/10.1145/2983323.2983351Google Scholar
- G. Biau and E. Scornet. 2016. A random forest guided tour. TEST (2016), 197--227. https://doi.org/10.1007/s11749-016-0481-7Google Scholar
- L. Breiman. 2001. Random Forest. Machine Learning 45 (2001), 5--32. https://doi.org/10.1023/A:1010933404324Google ScholarDigital Library
- J. Casanova and R. Mauricio. 2018. Factors that determine the persistence and dropout of university students. Psicothema (2018).Google Scholar
- Francesca Del Bonifro, Maurizio Gabbrielli, Giuseppe Lisanti, and Stefano Pio Zingaro. 2020. Student Dropout Prediction. In Artificial Intelligence in Education. Springer International Publishing, 129--140.Google Scholar
- Maria Federico and Marco Furini. 2014. An automatic caption alignment mechanism for off-the-shelf speech recognition technologies. Multimedia Tools and Applications 72, 1 (2014), 21--40. https://doi.org/10.1007/s11042-012-1318-3Google ScholarDigital Library
- Marco Furini. 2016. On gamifying the transcription of digital video lectures. Entertainment Computing 14 (2016), 23--31. https://doi.org/10.1016/j.entcom.2015.08.002Google ScholarCross Ref
- Marco Furini. 2018. On introducing timed tag-clouds in video lectures indexing. Multimedia Tools and Applications 77, 1 (01 Jan 2018), 967--984. https://doi.org/10.1007/s11042-016-4282-5Google ScholarDigital Library
- Marco Furini, Giovanna Galli, and Maria Cristiana Martini. 2020. An Online Education System to Produce and Distribute Video Lectures. Mobile Networks and Applications (2020). https://doi.org/10.1007/s11036-019-01236-4Google Scholar
- M. Furini, S. Mirri, and M. Montangero. 2018. Topic-based playlist to improve video lecture accessibility. In 2018 15th IEEE Annual Consumer Communications Networking Conference (CCNC). 1--5. https://doi.org/10.1109/CCNC.2018.8319246Google ScholarDigital Library
- Ombretta Gaggi, Claudio Enrico Palazzi, Matteo Ciman, Giorgia Galiazzo, Sandro Franceschini, Milena Ruffino, Simone Gori, and Andrea Facoetti. 2017. Serious Games for Early Identification of Developmental Dyslexia. Comput. Entertain. 15, 2, Article 4 (April 2017), 24 pages. https://doi.org/10.1145/2629558Google ScholarDigital Library
- Gongde Guo, Hui Wang, David Bell, Yaxin Bi, and Kieran Greer. 2003. KNN Model-Based Approach in Classification. In On The Move to Meaningful Internet Systems 2003. Springer Berlin Heidelberg, Berlin, Heidelberg, 986--996.Google ScholarCross Ref
- Tomas Hasbun, Alexandra Araya, and Jorge Villalon. 2016. Extracurricular Activities as Dropout Prediction Factors in Higher Education Using Decision Trees. In Conference on Advanced Learning Technologies. 242--244. https://doi.org/10.1109/ICALT.2016.66Google ScholarCross Ref
- Hengxuan Li, Collin F. Lynch, and Tiffany Barnes. 2018. Early Prediction of Course Grades: Models and Feature Selection. 492--495.Google Scholar
- Ioanna Lykourentzou, Ioannis Giannoukos, Vassilis Nikolopoulos, George Mpardis, and Vassili Loumos. 2009. Dropout prediction in e-learning courses through the combination of machine learning techniques. Computers & Education 53, 3 (2009), 950--965. https://doi.org/10.1016/j.compedu.2009.05.010Google ScholarDigital Library
- Anthony J. Myles, Robert N. Feudale, Yang Liu, Nathaniel A. Woody, and Steven D. Brown. 2004. An introduction to decision tree modeling. Journal of Chemometrics 18, 6 (2004), 275--285. https://doi.org/10.1002/cem.873Google ScholarCross Ref
- Boris Perez, Camilo Castellanos, and Dario Correal. 2018. Applying Data Mining Techniques to Predict Student Dropout: A Case Study. In Conference on Applications in Computational Intelligence. https://doi.org/10.1109/ColCACI.2018.8484847Google ScholarCross Ref
- Martin Solis, Tania Moreira, Roberto Gonzalez, Tatiana Fernandez, and Maria Hernandez. 2018. Perspectives to Predict Dropout in University Students with Machine Learning. In Conference on Bioinspired Intelligence. 1--6. https://doi.org/10.1109/IWOBI.2018.8464191Google ScholarCross Ref
- Di Sun, Yueheng Mao, Junlei Du, Pengfei Xu, Qinhua Zheng, and Hongtao Sun. 2019. Deep Learning for Dropout Prediction in MOOCs. In Conference on Educational Innovation through Technology. https://doi.org/10.1109/EITT.2019.00025Google Scholar
- Amelec Viloria, Jholman Garcia Padilla, Carlos Vargas-Mercado, Hugo Hernandez-Palma, Nataly Orellano Llinas, and Monica Arrozola David. 2019. Integration of Data Technology for Analyzing University Dropout. Procedia Computer Science 155 (2019), 569--574.Google ScholarCross Ref
- Jacob Whitehill, Kiran Mohan, Daniel Seaton, Yigal Rosen, and Dustin Tingley. 2017. MOOC Dropout Prediction: How to Measure Accuracy?. In ACM Conference on Learning @ Scale. 161--164. https://doi.org/10.1145/3051457.3053974Google ScholarDigital Library
- Zhuoyuan Zheng, Yunpeng Cai, and Ye Li. 2015. Oversampling method for imbalanced classification. Computing and Informatics 34 (01 2015), 1017--1037.Google Scholar
Index Terms
- On Using Video Lectures Data Usage to Predict University Students Dropout
Recommendations
Predicting MOOCs Dropout Using Only Two Easily Obtainable Features from the First Week’s Activities
Intelligent Tutoring SystemsAbstractWhile Massive Open Online Course (MOOCs) platforms provide knowledge in a new and unique way, the very high number of dropouts is a significant drawback. Several features are considered to contribute towards learner attrition or lack of interest, ...
Log-Data Clustering Analysis for Dropout Prediction in Beginner Programming Classes
Educational data mining (EDM) involves the application of data mining, machine learning, and statistics to information generated from an educational setting. In most school education, one teacher teaches many students. A periodic examination is used as ...
MOOC Dropout Prediction: How to Measure Accuracy?
L@S '17: Proceedings of the Fourth (2017) ACM Conference on Learning @ ScaleIn order to obtain reliable accuracy estimates for automatic MOOC dropout predictors, it is important to train and test them in a manner consistent with how they will be used in practice. Yet most prior research on MOOC dropout prediction has measured ...
Comments