TY - GEN
T1 - Predicting abandonment in online coding tutorials
AU - Yan, An
AU - Lee, Michael J.
AU - Ko, Andrew J.
N1 - Funding Information:
This work was supported in part by the National Science Foundation (NSF) under grants IIS-1657160, CNS-1240786, CNS-1240957, CNS-1339131, CCF-0952733, CCF-1339131, IIS-1314399, and IIS-1314384.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/11/9
Y1 - 2017/11/9
N2 - Learners regularly abandon online coding tutorials when they get bored or frustrated, but there are few techniques for anticipating this abandonment to intervene. In this paper, we examine the feasibility of predicting abandonment with machine-learned classifiers. Using interaction logs from an online programming game, we extracted a collection of features that are potentially related to learner abandonment and engagement, then developed classifiers for each level. Across the first five levels of the game, our classifiers successfully predicted 61% to 76% of learners who did not complete the next level, achieving an average AUC of 0.68. In these classifiers, features negatively associated with abandonment included account activation and help-seeking behaviors, whereas features positively associated with abandonment included features indicating difficulty and dis-engagement. These findings highlight the feasibility of providing timely intervention to learners likely to quit.
AB - Learners regularly abandon online coding tutorials when they get bored or frustrated, but there are few techniques for anticipating this abandonment to intervene. In this paper, we examine the feasibility of predicting abandonment with machine-learned classifiers. Using interaction logs from an online programming game, we extracted a collection of features that are potentially related to learner abandonment and engagement, then developed classifiers for each level. Across the first five levels of the game, our classifiers successfully predicted 61% to 76% of learners who did not complete the next level, achieving an average AUC of 0.68. In these classifiers, features negatively associated with abandonment included account activation and help-seeking behaviors, whereas features positively associated with abandonment included features indicating difficulty and dis-engagement. These findings highlight the feasibility of providing timely intervention to learners likely to quit.
UR - http://www.scopus.com/inward/record.url?scp=85041015390&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85041015390&partnerID=8YFLogxK
U2 - 10.1109/VLHCC.2017.8103467
DO - 10.1109/VLHCC.2017.8103467
M3 - Conference contribution
AN - SCOPUS:85041015390
T3 - Proceedings of IEEE Symposium on Visual Languages and Human-Centric Computing, VL/HCC
SP - 191
EP - 199
BT - Proceedings - 2017 IEEE Symposium on Visual Languages and Human-Centric Computing, VL/HCC 2017
A2 - Rodgers, Peter
A2 - Henley, Austin Z.
A2 - Sarma, Anita
PB - IEEE Computer Society
T2 - 2017 IEEE Symposium on Visual Languages and Human-Centric Computing, VL/HCC 2017
Y2 - 11 October 2017 through 14 October 2017
ER -