A Chatbot Student Support System in Open and Distance Learning Institutions

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The paper is generally well written and structured.

Development work is well motivated (via the questionnaire) and much needed, but poorly described.

Main points missing:

- architecture of your NN (input, hidden layers, connetivity, output including functions, etc) and hyper parameters

- visualation of learning rate development, etc.

- details of the typically very important data engineering part

From presentation - make proper tables and not screenshots as well as diagramms that scale well with legends, etc.

If you provide code then it has to add value and described in great detail - maybe use it to seriously outline your approach, e.g. pyhton toolchain, etc.

In short, it is far too early to be published

Author Response

Please see uploaded file.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The disruptive technology of Chatbots in educational institutions has several offerings that need to be considered in higher educational institutions. For instance, the implementation in Open and Distance Learning (ODL) can help in fostering effective and interactive communication between the institutions and the learners. Isolation, lack of motivation, insufficient study time and delays in feedback are some of the challenges encountered by ODL learners and the consequences have led to the increase in attrition rate. The limitations of National Open University of Nigeria's existing e-ticketing support system were examined in this study, and an artificial intelligence (AI) chatbot was developed to solve these problems.

AUTHORS employed quantitative and qualitative methods through a survey of 579 students.

THEIR findings revealed significant delays in response times and inadequate resolutions as major barriers.

 

AUTHORS conclude that through response automation and delay reduction, the chatbot provides a scalable way to improve student happiness, lower attrition, and foster a more encouraging and supportive learning environment in ODL institutions.

 

This is an interesting study on an emerging topic, but the level of exposition is low and the study is difficult to follow

I have the following suggestions for the authors.

1) The abstract should be rewritten in a more structured way, mini-titles of background/purpose/methods/results etc. would help with this as a grid

2) The study from what I read does not follow the MDPI editorial standard

3) In the introduction, cluster citations that do not go into detail should be avoided. See for example “, according to many authors and attrition continues to be a significant concern for many educational institutions [25, 22] [26-28][15] [29-39]. ”

4) VERY IMPORTANT Structure the study according to an architecture that follows introduction, methods, results, discussion, conclusion

5) After the introduction there are three sections, then methodology, then method of data analysis, it is not clear why they are separated and also they are very generic and do not go into the details of the study.

6) There are two sections “finding and discussion” and “discussion” both written with a lot of approximation and with unclear figures and tables. Only one article is cited in the discussion which however seems more like an exposition of the results. Reorganize into two sections:

“results”, where you show the results with clear text, figures and tables

“discussion” where you compare your study with other studies and report the limitations

 

Author Response

Please see uploaded file.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

Overall, the article is quite interesting and makes a valuable contribution to AI in education. I have the following suggestions that can further enhance its quality and impact.

Comments for the Authors:

1. Clarity of Objectives: The paper's objectives are reducing student attrition rates in Open and Distance Learning (ODL) institutions through the development of a chatbot. However, please elaborate on the expected outcomes, such as measurable response times or user satisfaction improvements.
2. Literature Review: The authors have done a good job at literature review as it covers relevant studies on ODL challenges and chatbot applications. It is a good idea including a summary table of key studies is helpful, however, please add more discussion on how these studies directly influenced the chatbot's design and functionality.
3. Methodology: Please add more information on how the sample size was determined and why the specific ratio (70:30) for training/testing data was chosen. Also give the demographic breakdown and ensure that it is aligned with the objectives of the study.
4. Findings: The findings section provides valuable insights into the limitations of the current e-ticketing system and the proposed chatbot's potential. However, please include additional quantitative data, such as comparative response times before and after the chatbot's implementation to showcase stronger evidence of its effectiveness.
5. Figures and Tables: Please ensure that all figures are accompanied by detailed captions that explain their significance.
6. Discussion: Please write more about the potential limitations of the chatbot, such as scalability issues or challenges in understanding complex queries. Also, consider including a brief discussion on the ethical implications of using AI-powered chatbots, particularly concerning data privacy and bias.
7. Conclusion: The authors should reiterate the broader implications of the research for ODL institutions globally. Also consider highlighting specific next steps, such as pilot implementation and user feedback collection. That would enhance the conclusion's forward-looking perspective. Also address how this chatbot model could be adapted for use in other educational contexts or integrated with existing educational platforms. Also discuss how data security and user privacy are addressed, as these are critical in AI applications.
8. Future directions: Please propose a plan for assessing the chatbot's long-term impact on student retention and satisfaction.
9. References: Please ensure that all citations are formatted consistently according to the required style.

 

 

Author Response

Please see uploaded file.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Your methodology sections is still missing a lot of revelevant necessary details, e.g. corpus size of each data collection for your training and time needed, hyperparameters used, etc.

Fig 2 and Fig 3 are just bad quality - why not vector graphics!?

The provided new code is not properly formatted (use code environment!) nor does it have a label/Number

Fig 4 and 5 are useless as essentially not readable - why not provide the requested diagrams during model training?

Too much bullet points do not really improve readability - in this case still a lot of details are missing

 

Author Response

Author's responses are as contained in the attached document.

Author Response File: Author Response.docx

Reviewer 2 Report

Comments and Suggestions for Authors

I checked the previous version.

Now authors extensively answered to my questions.

There are no further comments

Author Response

The authors would want to record a note of thanks to the reviewer for this kind comment.

Reviewer 3 Report

Comments and Suggestions for Authors

The authors have done a good job at the revision. I have no further comments.

Author Response

The authors would want to record a note of thanks for this reviewer's comment.