By Lavi Aulck https://orcid.org/0000-0001-6824-3875

Review Details

---

Reviewer has chosen not to be Anonymous

Summary of paper in a few sentences:

The paper examines the use of machine learning to predict student dropout. In its present form, the work stands as a combination of literature survey and a survey of machine learning techniques. The first half of the paper is dedicated to reviewing previous work and the latter half focuses on comparing the use of various machine learning approaches on a freely-available dataset. This work presents some novel insights with respect to dropout in developing countries.

Reasons to accept:

- The paper focuses on an interesting and unexplored space: the use of machine learning to predict dropout in developing countries.
- Additional conversation regarding the state of predicting dropout using machine learning is sorely needed. This paper does address some issues to consider for this space moving forward.

Reasons to reject:

- The writing for this work is in need of proofing. There are numerous grammatical errors as well as latex formatting errors. This often stands as an obstacle in understanding what the writers are presenting.
- The introduction section discusses numerous topics that are not discussed in greater detail later in the writing (namely, gender disparities with respect to dropout)
- The paper initially presents itself as a review/survey but does not present much more than a typical literature review. Furthermore, the authors seems caught between attempting to present a standalone review/survey of prior work and presenting their own machine learning experiment(s). I'd suggest the authors stick to one or the other.
- An additional discussion of the methods in the ML experiments is needed. What does the dataset look like? Which features are present? Why were those specific ML algorithms selected for use? What was the train/test split?
- The authors only glance over their findings/results from both their review and their experiments. I think an additional discussion of either/both is needed.

Nanopublication comments:

Further comments:

By Sattar Ameri https://orcid.org/0000-0002-7002-1259

Review Details

---

Reviewer has chosen not to be Anonymous

Summary of paper in a few sentences:

The paper is very well written. It is one of the few papers which are related to this problem domain. Authors broadly explained previous works and help the reader to get a deeper knowledge of the field.

Reasons to accept:

It is very Well written, relevant to the journal. The structure of the paper is fine tuned.Authors have a good knowledge about the domain and did a good job to represent their work.

Reasons to reject:

In my opinion paper is worthy and should be accepted.

Nanopublication comments:

Further comments:

Reviewer has chosen to be Anonymous

Summary of paper in a few sentences:

The paper discusses the state of student dropout in developing countries and several performance metrics used by researchers to evaluate machine learning techniques in the context of education with experimental examples

Reasons to accept:

In this article, a review of how machine-learning techniques have been used in the fight against dropouts is presented for the purpose of providing a stepping-stone for students, researchers and developers who aspire to apply the techniques

Reasons to reject:

The authors should make a better survey of Machine Learning Approaches for Student Dropout Prediction.
e.g. Carlos Márquez-Vera, Alberto Cano, Cristóbal Romero, Amin Y. Noaman, Habib M. Fardoun, Sebastián Ventura:
Early dropout prediction using data mining: a case study with high school students. Expert Systems 33(1): 107-124 (2016)

as well as about the procedure for handling imbalance datasets e.g
Krawczyk, B. (2016). Learning from imbalanced data: open challenges and future directions. Progress in Artificial Intelligence, 5(4), 221-232.

The experimental framework is not well designed. The results are based on only one dataset. Overfitting should be included.

Nanopublication comments:

Further comments:

Section 3.3 is not really useful.
The results are based on only one dataset.
If the authors want to propose an algorithm should present it with pseudocode.
A statistical test should be used for the comparison of the examined methods.
Some information about the time efficiency of the proposed method should be included.

By Mvurya Mgala https://orcid.org/0000-0002-8634-4968

Review Details

---

Reviewer has chosen not to be Anonymous

Summary of paper in a few sentences:

The paper has a addressed a real problem of student dropout. A significant work has been carried out in reading literature related to student dropout. The paper attempts to make some contribution in suggesting the superior classifiers that gave the best results and the metrics used to measure performance of the classifiers. The work raises interest for further work in the developing world by pointing out that few studies have been conducted. The authors also point out the lack of public databases which is a limitation that could attract investors or funding.

Reasons to accept:

The work is significant; an acceptable level of literature search has been conducted to make conclusions that motivate discussion and further research.

Reasons to reject:

No reason for rejection

Nanopublication comments:

Further comments:

Although the work is accepted, the authors need to eliminate all the typos and some grammatical mistakes in the write up.