Jointly Modeling Heterogeneous Student Behaviors and Interactions among Multiple Prediction Tasks
- 20 July 2021
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 16 (1), 1-24
- https://doi.org/10.1145/3458023
Abstract
Prediction tasks about students have practical significance for both student and college. Making multiple predictions about students is an important part of a smart campus. For instance, predicting whether a student will fail to graduate can alert the student affairs office to take predictive measures to help the student improve his/her academic performance. With the development of information technology in colleges, we can collect digital footprints that encode heterogeneous behaviors continuously. In this article, we focus on modeling heterogeneous behaviors and making multiple predictions together, since some prediction tasks are related and learning the model for a specific task may have the data sparsity problem. To this end, we propose a variant of Long-Short Term Memory (LSTM) and a soft-attention mechanism. The proposed LSTM is able to learn the student profile-aware representation from heterogeneous behavior sequences. The proposed soft-attention mechanism can dynamically learn different importance degrees of different days for every student. In this way, heterogeneous behaviors can be well modeled. In order to model interactions among multiple prediction tasks, we propose a co-attention mechanism based unit. With the help of the stacked units, we can explicitly control the knowledge transfer among multiple tasks. We design three motivating behavior prediction tasks based on a real-world dataset collected from a college. Qualitative and quantitative experiments on the three prediction tasks have demonstrated the effectiveness of our model.Keywords
Funding Information
- National Key AI Program of China (2018AAA0100503 and 2018AAA0100500)
- National Science Foundation of China (62072304, 61772341, 61472254, and 61770238)
- Shanghai Municipal Science and Technology Commission (18511103002, 19510760500, and 19511101500)
- Program for Changjiang Young Scholars in University of China, the Program for China Top Young Talents, the Program for Shanghai Top Young Talents, SJTU Global Strategic (2019 SJTU-HKUST)
- Oceanic Interdisciplinary Program of Shanghai Jiao Tong University (SL2020MS032)
- Scientific Research Fund of Second Institute of Oceanography (SL2020MS032)
This publication has 28 references indexed in Scilit:
- Discovery of College Students in Financial HardshipPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Next-term student grade predictionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- A Review on Predicting Student's Performance Using Data Mining TechniquesProcedia Computer Science, 2015
- Predicting students' final performance from participation in on-line discussion forumsComputers & Education, 2013
- Data mining for adaptive learning in a TESL-based e-learning systemExpert Systems with Applications, 2011
- Predicting and preventing student failure – using the k-nearest neighbour method to predict student performance in an online course environmentInternational Journal of Learning Technology, 2010
- Addressing the assessment challenge with an online system that tutors as it assessesUser Modelling and User-Adapted Interaction, 2009
- A comparative analysis of techniques for predicting academic performance2007 37th annual frontiers in education conference - global engineering: knowledge without borders, opportunities without passports, 2007
- Framewise phoneme classification with bidirectional LSTM networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Long Short-Term MemoryNeural Computation, 1997