[REVIEW]: PySS3: A new interpretable and simple machine learning model for text classification

[whedon]

Submitting author: @sergioburdisso (Sergio Gastón Burdisso)
Repository: https://github.com/sergioburdisso/pyss3
Branch with paper.md (empty if default branch):
Version: v0.6.4
Editor: @bmcfee
Reviewers: @hbaniecki, @kmichael08
Archive: Pending

⚠️ JOSS reduced service mode ⚠️

Due to the challenges of the COVID-19 pandemic, JOSS is currently operating in a "reduced service mode". You can read more about what that means in our blog post.

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/872acc280f71e2a26e249d65dd399acd"><img src="https://joss.theoj.org/papers/872acc280f71e2a26e249d65dd399acd/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/872acc280f71e2a26e249d65dd399acd/status.svg)](https://joss.theoj.org/papers/872acc280f71e2a26e249d65dd399acd)

Reviewers and authors:

Please avoid lengthy details of difficulties in the review thread. Instead, please create a new issue in the target repository and link to those issues (especially acceptance-blockers) by leaving comments in the review thread below. (For completists: if the target issue tracker is also on GitHub, linking the review thread in the issue or vice versa will create corresponding breadcrumb trails in the link target.)

Reviewer instructions & questions

@hbaniecki & @kmichael08, please carry out your review in this issue by updating the checklist below. If you cannot edit the checklist please:

1. Make sure you're logged in to your GitHub account
2. Be sure to accept the invite at this URL: https://github.com/openjournals/joss-reviews/invitations

The reviewer guidelines are available here: https://joss.readthedocs.io/en/latest/reviewer_guidelines.html. Any questions/concerns please let @bmcfee know.

✨ Please start on your review when you are able, and be sure to complete your review in the next six weeks, at the very latest ✨

Review checklist for @hbaniecki

✨ Important: Please do not use the Convert to issue functionality when working through this checklist, instead, please open any new issues associated with your review in the software repository associated with the submission. ✨

Conflict of interest

• I confirm that I have read the JOSS conflict of interest (COI) policy and that: I have no COIs with reviewing this work or that any perceived COIs have been waived by JOSS for the purpose of this review.

Code of Conduct

• I confirm that I read and will adhere to the JOSS code of conduct.

General checks

• Repository: Is the source code for this software available at the repository url?
• License: Does the repository contain a plain-text LICENSE file with the contents of an OSI approved software license?
• Contribution and authorship: Has the submitting author (@sergioburdisso) made major contributions to the software? Does the full list of paper authors seem appropriate and complete?
• Substantial scholarly effort: Does this submission meet the scope eligibility described in the JOSS guidelines

Functionality

• Installation: Does installation proceed as outlined in the documentation?
• Functionality: Have the functional claims of the software been confirmed?
• Performance: If there are any performance claims of the software, have they been confirmed? (If there are no claims, please check off this item.)

Documentation

• A statement of need: Do the authors clearly state what problems the software is designed to solve and who the target audience is?
• Installation instructions: Is there a clearly-stated list of dependencies? Ideally these should be handled with an automated package management solution.
• Example usage: Do the authors include examples of how to use the software (ideally to solve real-world analysis problems).
• Functionality documentation: Is the core functionality of the software documented to a satisfactory level (e.g., API method documentation)?
• Automated tests: Are there automated tests or manual steps described so that the functionality of the software can be verified?
• Community guidelines: Are there clear guidelines for third parties wishing to 1) Contribute to the software 2) Report issues or problems with the software 3) Seek support

Software paper

• Summary: Has a clear description of the high-level functionality and purpose of the software for a diverse, non-specialist audience been provided?
• A statement of need: Does the paper have a section titled 'Statement of Need' that clearly states what problems the software is designed to solve and who the target audience is?
• State of the field: Do the authors describe how this software compares to other commonly-used packages?
• Quality of writing: Is the paper well written (i.e., it does not require editing for structure, language, or writing quality)?
• References: Is the list of references complete, and is everything cited appropriately that should be cited (e.g., papers, datasets, software)? Do references in the text use the proper citation syntax?

Review checklist for @kmichael08

✨ Important: Please do not use the Convert to issue functionality when working through this checklist, instead, please open any new issues associated with your review in the software repository associated with the submission. ✨

Conflict of interest

• I confirm that I have read the JOSS conflict of interest (COI) policy and that: I have no COIs with reviewing this work or that any perceived COIs have been waived by JOSS for the purpose of this review.

Code of Conduct

• I confirm that I read and will adhere to the JOSS code of conduct.

General checks

• Repository: Is the source code for this software available at the repository url?
• License: Does the repository contain a plain-text LICENSE file with the contents of an OSI approved software license?
• Contribution and authorship: Has the submitting author (@sergioburdisso) made major contributions to the software? Does the full list of paper authors seem appropriate and complete?
• Substantial scholarly effort: Does this submission meet the scope eligibility described in the JOSS guidelines

Functionality

• Installation: Does installation proceed as outlined in the documentation?
• Functionality: Have the functional claims of the software been confirmed?
• Performance: If there are any performance claims of the software, have they been confirmed? (If there are no claims, please check off this item.)

Documentation

• A statement of need: Do the authors clearly state what problems the software is designed to solve and who the target audience is?
• Installation instructions: Is there a clearly-stated list of dependencies? Ideally these should be handled with an automated package management solution.
• Example usage: Do the authors include examples of how to use the software (ideally to solve real-world analysis problems).
• Functionality documentation: Is the core functionality of the software documented to a satisfactory level (e.g., API method documentation)?
• Automated tests: Are there automated tests or manual steps described so that the functionality of the software can be verified?
• Community guidelines: Are there clear guidelines for third parties wishing to 1) Contribute to the software 2) Report issues or problems with the software 3) Seek support

Software paper

• Summary: Has a clear description of the high-level functionality and purpose of the software for a diverse, non-specialist audience been provided?
• A statement of need: Does the paper have a section titled 'Statement of Need' that clearly states what problems the software is designed to solve and who the target audience is?
• State of the field: Do the authors describe how this software compares to other commonly-used packages?
• Quality of writing: Is the paper well written (i.e., it does not require editing for structure, language, or writing quality)?
• References: Is the list of references complete, and is everything cited appropriately that should be cited (e.g., papers, datasets, software)? Do references in the text use the proper citation syntax?

[whedon]

Hello human, I'm @whedon, a robot that can help you with some common editorial tasks. @hbaniecki, @kmichael08 it looks like you're currently assigned to review this paper 🎉.

⚠️ JOSS reduced service mode ⚠️

Due to the challenges of the COVID-19 pandemic, JOSS is currently operating in a "reduced service mode". You can read more about what that means in our blog post.

⭐ Important ⭐

If you haven't already, you should seriously consider unsubscribing from GitHub notifications for this (https://github.com/openjournals/joss-reviews) repository. As a reviewer, you're probably currently watching this repository which means for GitHub's default behaviour you will receive notifications (emails) for all reviews 😿

To fix this do the following two things:

1. Set yourself as 'Not watching' https://github.com/openjournals/joss-reviews:

2. You may also like to change your default settings for this watching repositories in your GitHub profile here: https://github.com/settings/notifications

For a list of things I can do to help you, just type:

@whedon commands

For example, to regenerate the paper pdf after making changes in the paper's md or bib files, type:

@whedon generate pdf

[whedon]

Wordcount for paper.md is 1642

[whedon]

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

OK DOIs

- 10.1371/journal.pone.0168344 is OK
- 10.1016/j.eswa.2017.07.040 is OK
- 10.1007/978-3-319-44564-9_3 is OK
- 10.1007/978-3-319-65813-1_30 is OK
- 10.1016/j.eswa.2019.05.023 is OK
- 10.1016/j.patrec.2020.07.001 is OK

MISSING DOIs

- None

INVALID DOIs

- None

[whedon]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[whedon]

Software report (experimental):

github.com/AlDanial/cloc v 1.88  T=10.48 s (6.5 files/s, 3055.7 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
CSS                              6           1361            375           7369
Python                          10           1460           2144           5469
HTML                             5            429              6           4772
reStructuredText                20           1452           1207           1017
JavaScript                      10             85            193            897
Markdown                         6            208              0            392
Jupyter Notebook                 6              0           2668            276
TeX                              1             12              0            117
YAML                             2              8              5             46
DOS Batch                        1              8              1             26
make                             1              4              7              9
-------------------------------------------------------------------------------
SUM:                            68           5027           6606          20390
-------------------------------------------------------------------------------


Statistical information for the repository 'a31d62b5a31d0b1d086992e7' was
gathered on 2021/11/19.
The following historical commit information, by author, was found:

Author                     Commits    Insertions      Deletions    % of changes
Florian Angermeir                1            19             19            0.20
Sergio Burdisso                202         14552           4147           99.80

Below are the number of rows from each author that have survived and are still
intact in the current revision:

Author                     Rows      Stability          Age       % in comments
Florian Angermeir            18           94.7         16.4               22.22
Sergio Burdisso           10258           70.5         10.0                6.19

[whedon]

👋 @kmichael08, please update us on how your review is going (this is an automated reminder).

[whedon]

👋 @hbaniecki, please update us on how your review is going (this is an automated reminder).

[kmichael08]

wave @kmichael08, please update us on how your review is going (this is an automated reminder).

I'll get to it within a week, thanks for checking

[hbaniecki]

Overall, the PySS3 package is mature and of high quality. It comes with extensive documentation and easy-to-follow tutorials. Over two years of development, it steadily gathered a recognizable user-base (55k downloads, 200+ stars). The core functionalities are a valuable and needed contribution to interpretable machine learning, especially in the context of model monitoring and interactive analysis.

Comment on substantial scholarly effort:
As highlighted both in the software paper and documentation, two articles of the authors preceded this work:

"A text classification framework for simple and effective early depression detection over social media streams" (Expert Systems with Applications, 2019), https://doi.org/10.1016/j.eswa.2019.05.023,
"τ-SS3: A text classifier with dynamic n-grams for early risk detection over text streams" (Pattern Recognition Letters, 2020), https://doi.org/10.1016/j.patrec.2020.07.001.

These focus mainly on introducing, evaluating and applying novel algorithms. At the same time, the software (paper) implements a convenient API for the machine learning models and contributes interactive (server, visual) tools to work with them.

Comment on contribution and authorship:
From what I can tell looking at the GitHub repository, the submitting author made major contributions to the software, and is the only such in a strict sense of contributing code and documentation. Nevertheless, the full list of paper authors seems appropriate and complete, as the two other authors also contribute to this project, e.g. looking at the two preceding papers.

The authors addressed my issues on Functionality and Documentation. I will now proceed to review the paper contents.

[bmcfee]

Checking in on this as there hasn't been much action in the past week. @hbaniecki and @kmichael08 . Any updates here?

I know we're going into holidays and it's a busy time of year, but I'd like to know where this one stands and whether we should expect to pause until the new year.

[hbaniecki]

Hi, I have posted comments to the paper in the above issue and the initiative is on the authors' side to respond/address them.
Edit. Then I could mark the missing checks on my list.

[kmichael08]

I will do it the first week of January. Unfortunately, can't do it any faster

[bmcfee]

Happy new year everyone! I hope everyone's doing alright.

@kmichael08 have you had a chance to get started on this one yet?

@sergioburdisso have you been able to address @hbaniecki 's comments?

[kmichael08]

I started with the section related to the software paper. My comments are in the issue linked above.
Just a quick check. This paper is a shorter version of an arXiv preprint from 2019, and this preprint is referenced in this work. @bmcfee is this all good with the JOSS guidelines?

[bmcfee]

@kmichael08 yes, that should be fine. The JOSS preprint policy is listed here: https://joss.readthedocs.io/en/latest/submitting.html#preprint-policy

Authors are welcome to submit their papers to a preprint server (arXiv, bioRxiv, SocArXiv, PsyArXiv etc.) at any point before, during, or after the submission and review process.

Submission to a preprint server is not considered a previous publication.

[bmcfee]

@sergioburdisso checking in again - can you give us a quick update on progress in response to @hbaniecki 's comments?

[sergioburdisso]

Hi @bmcfee, @hbaniecki @kmichael08 ! First of all, thanks for taking the time to review our paper! I'm having a pretty rough "new year" so far, and couldn't manage to take care of the JOSS issues, but I'll try to do it this weekend, would it be OK if that's the case?

[bmcfee]

Sure, that's fine. Thanks for the update, and I hope your new year smooths out soon!

[bmcfee]

👋 @sergioburdisso no pressure, just checking in again to see how things are going.

[sergioburdisso]

@bmcfee Last weekend couldn't make it, but I think that tomorrow I'll be finally able to do it! 💪 (and thanks for checking in again 😎)

[bmcfee]

Great, thanks for the quick response!

[bmcfee]

Just checking in again - how are things going here?

[bmcfee]

@sergioburdisso checking in again. It's been over a month since we've heard from you.

[bmcfee]

Thanks @sergioburdisso for keeping this moving forward - how are things now regarding reviewer comments?

sergioburdisso/pyss3#21
sergioburdisso/pyss3#24

[bmcfee]

It looks like there's been no movement here since early April. Is there anything we can help with to keep this moving?

[bmcfee]

👋 @sergioburdisso how is this one doing?

[kyleniemeyer]

Hi @sergioburdisso, it's been a while since we have heard from you. Are you still planning on working on this submission? If we do not hear from you in the next few days, either here or via email, we will have to withdraw this submission.

[arfon]

@editorialbot reject

@bmcfee – this submission seems to be abandoned. As such, I'm proceeding to reject. Thanks for your work here @bmcfee and reviewers @hbaniecki & @kmichael08. Sorry this submission didn't work out.

[editorialbot]

Paper rejected.