Task Recommender System using Semantic Clustering Task Recommender System using Semantic Clustering to Identify the Right Personnel

Tracking #: 530-1510

Responsible editor: 

Michael Maes

Submission Type: 

Research Paper


Productivity of any organization is enhanced by assigning task to employees with right set of skills. An efficient recruitment and task allocation can not only improve productivity but also cater to satisfying employee aspiration and identifying training requirements. An automated Task Recommendation System is proposed comprising of synset based feature extraction, iterative semantic clustering and mapping based on semantic similarity. The system takes documents like appraisal or resume as input and suggests not only the persons appropriate to complete a task and job position but also employees needing additional training.



  • Reviewed

Data repository URLs: 

Date of Submission: 

Wednesday, February 21, 2018

Date of Decision: 

Wednesday, April 25, 2018

Nanopublication URLs:



Solicited Reviews:

1 Comment

Meta-Review by Editor

Thank you for submitting your paper “Task Recommender System using Semantic Clustering to Identify the Right Personnel”, to Data Science. First of all, we would like to apologize for the long delay before we could make a decision. We invited nine reviewers but only two were able to provide a review in the limited time we request.

We have now received two reports. Unfortunately, both reviewers recommend rejecting your manuscript. Both reviewers identify a weak integration into the literature as the main weakness. Recruitment and job allocation are important research problems that have been studied in various fields, including economics and manag ement science. The reviewers argue that your manuscript does not identify your contribution to this literature. This involves comparing your approach to existing methods and demonstrating under which conditions your method is superior. In addition, both reviewers point to language style issues and problems with the graphical analyses that make the paper hard to digest.

Having read your paper and both reviews, our meta-reviewer agreed with the reviewer recommendations and decided to reject your paper. We are sorry not bringing you better news, but we hope that you continue to consider Data Science as a potential outlet for your work. We wish you good luck in publishing this paper in another journal.

Michael Maes (http://orcid.org/0000-0001-9416-3211)