All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
The authors have sincerely addressed the issues raised by the reviewers. I now recommend accepting the manuscript for publication.
[# PeerJ Staff Note - this decision was reviewed and approved by Jyotismita Chaki, a PeerJ Section Editor covering this Section #]
The paper first provides the motivations, for why they build the chatbot CuentosIE (contains from C1 to C6 contributions). Then, the paper provides a deeper background on dealing with emotions and how chatbots are used for emotion processing. Furthermore, the paper illustrates the design and implementation details of this proposed chatbot CuentosIE. The Experiment section shows how they set up the experiment and how the chatbot CuentosIE meets the contributions listed in C1 - C6. The paper offers a clear motivation and definitions of all terms and theorems.
The overall design of experiments is reasonable.
The experimental results are well-supported.
The revised version addressed all my concerns/questions in the first round of review.
While both reviewers' feedback are detailed, reviewer 2's feedback is slightly more complex. In the "Validity of the findings", Reviewer 2 raised the issue that it is written as a psychology paper and not enough details are provided to make it a computer science paper.
If the authors give a detailed explanation of its system architecture when revising it, this will make it more in scope for computer science, i.e. detail the architecture and the code you are using and place less emphasis on the psychology aspect. This solution is not immediately clear from Reviewer 2 but addressing it is necessary if the submission is to be considered suitable for PeerJ Computer Science.
Please address the issues raised by the reviewers and provide a revised manuscript.
**PeerJ Staff Note:** Please ensure that all review, editorial, and staff comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
The paper first provides the motivations, for why they build the chatbot CuentosIE (contains from C1 to C6 contributions). Then, the paper provides a deeper background on dealing with emotions and how chatbots are used for emotion processing. Furthermore, the paper illustrates the design and implementation details of this proposed chatbot CuentosIE. The Experiment section shows how they set up the experiment and how the chatbot CuentosIE meets the contributions listed in C1 - C6. The paper offers a clear motivation and definitions of all terms and theorems.
The overall design of experiments is reasonable. But it still needs some clarifications: 1) Why did the emotion classifier pick the Transformer model "tf_roberta_for_sequence_classification"? Did you cherry-pick the Transformer model here? 2) For Figures 4 and 5, are the 5,624 emotions enough to generate an accurate experimental result?
The experimental results are well-supported.
Please add more references to some parts in the paper, such as:
(line 196) "every day more companies include a chatbot on their websites or social networks to offer products and services to customers..." Please list one or two examples here.
(line 197) "Although most chatbots have been developed for commercial purposes, these machines are also very useful in other areas..." (such as the existing work "DroidPerf: Profiling Memory Objects on Android Devices" [MobiCom'23] develops a communicable bot to evaluate memory issues on smartphone terminal);
(line 280) "NLTK and the spaCy library"
(Figure 4 and 5) Please add the reference of the used in the caption.
The paper used clean and understandable English to present it's idea. It was nicely written.
All of the experiments seems to come from a psychological experimental perspective. The experiments are from human responses rather than on actual datasets. Also there should be a much more detailed explanation of the system structure.
The paper presents an E2E chatbot system using traditional NLP techniques (NLTK, etc) with newer ones (Falcon LLM) that chats with people, especially those with mental issues, about their feelings. However it lacks detailed explanation of it's system architecture. It feels more like a psychology paper not an computer science paper.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.