• Corpus ID: 219177253

Analyzing Student Strategies In Blended Courses Using Clickstream Data

@article{Akpinar2020AnalyzingSS,
  title={Analyzing Student Strategies In Blended Courses Using Clickstream Data},
  author={Nil-Jana Akpinar and Aaditya Ramdas and Umut Acar},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.00421}
}
Educational software data promises unique insights into students' study behaviors and drivers of success. While much work has been dedicated to performance prediction in massive open online courses, it is unclear if the same methods can be applied to blended courses and a deeper understanding of student strategies is often missing. We use pattern mining and models borrowed from Natural Language Processing (NLP) to understand student interactions and extract frequent strategies from a blended… 

Figures and Tables from this paper

Gaining Insights on Student Course Selection in Higher Education with Community Detection

TLDR
It is found that course choices diversify as programs progress, meaning that attempting to understand course choices by identifying a ”typical” student gives less insight than understanding what characterizes course choice diversity.

Methods for Language Learning Assessment at Scale: Duolingo Case Study

Students using self-directed learning platforms, such as Duolingo, cannot be adequately assessed relying solely on responses to standard learning exercises due to a lack of control over learners’

Designing a Learning Analytics Dashboard to Provide Students with Actionable Feedback and Evaluating Its Impacts

: Various educational settings have begun to increasingly leverage the power of data analytics to optimize the learning environment and enhance the learning experience for students. However, despite

Mining Assignment Submission Time to Detect At-Risk Students with Peer Information

TLDR
A new method called Relative Assignment Submission Time (RAST) is proposed which uses the assignment submission information of peer students to improve the correlation with course grades and build a machine learning model using RAST as a feature to detect students who would suffer from poor grades.

Early Prediction of Conceptual Understanding in Interactive Simulations

Interactive simulations allow students to independently explore scientific phenomena and ideally infer the underlying principles through their exploration. Effectively using such environments is

Understanding Utility and Privacy of Demographic Data in Education Technology by Causal Analysis and Adversarial-Censoring

TLDR
It is shown that gender can be inferred from behavioral data; thus, simply leaving them out does not protect students’ privacy, and a novel approach is proposed to create a ‘private’ version of a dataset comprising of fewer features that predict the target without revealing the gender, and are interpretive.

References

SHOWING 1-10 OF 45 REFERENCES

A time series interaction analysis method for building predictive models of learners using log data

TLDR
A novel method for converting educational log data into features suitable for building predictive models of student success, an approach that requires no input from instructional or domain experts and can be applied across courses or learning environments.

Can Typical Behaviors Identified in MOOCs be Discovered in Other Courses?

TLDR
It turns out that the different characterizations of individual learning behaviors are consistent for the JavaFX course and uncover typical behaviors reminiscent of those found by others in MOOCs, while they aren’t as applicable to the AWT course.

Grade Prediction in MOOCs

  • Xiu LiLulu XieHuimin Wang
  • Computer Science
    2016 IEEE Intl Conference on Computational Science and Engineering (CSE) and IEEE Intl Conference on Embedded and Ubiquitous Computing (EUC) and 15th Intl Symposium on Distributed Computing and Applications for Business Engineering (DCABES)
  • 2016
TLDR
This paper proposed a grade prediction model to automatically predict students' grades based on students' previous performances, utilizing regression, back-propagation neural network methods based on feature selection comprehensively considering educational theories.

Understanding MOOC students: motivations and behaviours indicative of MOOC completion

TLDR
This research examined MOOC student demographic data, intended behaviours and course interactions to better understand variables that are indicative of MOOC completion and lead to ideas regarding how these variables can be used to support MOOC students through the application of learning analytics tools and systems.

Mining Login Data For Actionable Student Insight

TLDR
An exploratory data analysis of a large educational dataset consisting of 100 million instances of login data from 1.5 million unique students who attempted 783 thousand assignments provided a new hypothesis on student groupings, which was explored through a cluster analysis.

What will you do next? A sequence analysis on the student transitions between online platforms in blended courses

TLDR
This work studies sequences of student transitions between online tools in blended courses and identifies which habits make the most difference between the higher and lower performing groups.

MOOC student dropout: pattern and prevention

TLDR
A general system for predicting students' dropout is developed and can fit on different on-going courses, and some suggestions for instructing students on MOOC are given.

Exploring N-gram Features in Clickstream Data for MOOC Learning Achievement Prediction

TLDR
This paper explores the effectiveness of N-gram features in clickstream data and model the MOOC learning achievement prediction problem as a multiclass classification task which classifies learners into four achievement levels and demonstrates that the methods outperform the state-of-the-art methods significantly.