search

nokaut / wsknn

Session-weighted recommendation system in Python
BSD 3-Clause "New" or "Revised" License
6 stars 0 forks source link

JOSS editor paper comments #54

Closed AoifeHughes closed 1 year ago

AoifeHughes commented 1 year ago

with respect to https://github.com/openjournals/joss-reviews/issues/5639 I have some general thoughts, but these are NOT required, please only use as guidance.

  1. Summary

    • Change "The users of e-commerce systems generate" to "Users of e-commerce systems generate".
    • Change "Based on this behavior, we can recommend the sequence of products the user may be interested in." to "Based on this behavior, we can recommend the sequence of products that the user may be interested in."

  2. Statement of need

    • Replace "WSKNN is an abbreviation from" with "WSKNN stands for".
    • Change "the k-NN model's performance is close to or exceeds the performance of neural networks algorithms" to "the performance of the k-NN model is comparable to, if not better than, that of neural network algorithms".
    • Change "It makes WSKNN a great benchmarking tool" to "This makes WSKNN a valuable benchmarking tool".

  3. Package structure

    • After "It has two main functions:", consider using a colon to lead into the bullet points.
    • Use bullet points for the list of parameters under "Those parameters are:".
    • Change "The YAML file with documented options is provided" to "A YAML file documenting options is provided".

  4. Data Formats

    • Change "The basic data type required by the algorithm is an event. An event has" to "The basic data type required by the algorithm is an event, which consists of:".
    • Consider using bullet points for the components of an event.

  5. Experiments

    • Change "We see that performance on analytical metrics is close to that of RNN-based models, but the WSKNN model is worst regarding response times." to "While the performance of WSKNN on analytical metrics is comparable to RNN-based models, its response times are less optimal."

  6. Limitations

    • Change "As with every Machine Learning system, WSKNN has its limitations:" to "Like all machine learning systems, WSKNN has limitations:".
SimonMolinsky commented 1 year ago

@AoifeHughes Thank you very much! I'll go through your comments and update the paper accordingly!

SimonMolinsky commented 1 year ago

@AoifeHughes I've corrected all the stylistic issues pointed out by you. Additionally, you mentioned using bullet lists, and it was a surprise for me because I had used those in places marked by you! Something may have gone wrong with the rendering. I wasn't sure, so I've changed bullets from - to *, and now everything seems to render fine in the paper.