Next Article in Journal
On the Use of the Multi-Agent Environment for Mobility Applications
Next Article in Special Issue
Tell Me More: Automating Emojis Classification for Better Accessibility and Emotional Context Recognition
Previous Article in Journal
Clinical Trial Classification of SNS24 Calls with Neural Networks
 
 
Article
Peer-Review Record

Measuring Ethical Values with AI for Better Teamwork

Future Internet 2022, 14(5), 133; https://doi.org/10.3390/fi14050133
by Erkin Altuntas 1, Peter A. Gloor 2,* and Pascal Budner 1
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Future Internet 2022, 14(5), 133; https://doi.org/10.3390/fi14050133
Submission received: 11 April 2022 / Revised: 26 April 2022 / Accepted: 26 April 2022 / Published: 27 April 2022
(This article belongs to the Special Issue Affective Computing and Sentiment Analysis)

Round 1

Reviewer 1 Report

This is a relatively broad research with demanding data collection and many calculations in various methods. I consider the discussion of results to be the most successful part of the paper, where all results are summarized, discussed and compared with studies by other authors, describes the practical consequences of research and also describes in detail the limits of research and proposals for future research. I have a few small remarks and minor corrections that could further improve the submitted, already relatively high-quality, paper:

  1. There is no part devoted to literature research. It would like to refer to other authors' research, compare the current state, methods used for your application, etc. Feel free to refer to the authors who are listed below. Alternatively, at least extend the introduction, which is disproportionately short to the other chapters of the paper.
  2. Why do you use data division splitting into 90% training and 10% test data? Most studies using AI use a ratio of 70% and 30%, or add a validation set. I'm not saying your relationship is bad, but I'd like to say why you chose this one.
  3. Part 4. Discussion should be formally called ideally 4. Discussion and conclusion, because it also contains information that is often given in the conclusion and this chapter is not added at all.
  4. What software did you use for the calculations?

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear Authors,

The content of your article fits perfectly within the scope of Future Internet journal's "Affective Computing and Sentiment Analysis" Special Issue. One of the reasons for this is that a key research topic involves issues of ethical and moral values of employees. This is very important for solutions to increase performance of their teams.

The authors proposed a new approach to measure personal values. It is relevant and interesting.

The above-mentioned goal was based on the 52 publications analysed in the article.

The results of the research, which was carried out with machine learning, are given and explained. The authors proved that the personal values obtained in the article can be useful for building better teams.

The paper contains some new data.

The paper is presented in logical way and overall written well.

The text is clear and easy to read.

The content of the final 4th section of the article is consistent with the evidence and arguments presented and addresses the main question asked. There is a reference to limitations in the article.

Comments and Suggestions for Authors

  1. It would be best to clearly identify which of the previous works by all Authors constitute the foundation of the work presented in this article.
  2. The study considered the use of a two-layered ML model. What other alternatives were there?
  3. The following typos are noticed in the article: please make the content of Tables 4, 5, A1 and B1 more readable.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Back to TopTop