2018
DOI: 10.1016/j.knosys.2018.04.007
|View full text |Cite
|
Sign up to set email alerts
|

Evaluating recommendation and search in the labor market

Abstract: This study evaluates the most popular recommender system algorithms for use on both sides of the labor market: job recommendation and job seeker recommendation. Recent research shows the drawbacks of focusing solely on predictive power when evaluating recommender systems, which become especially prominent in job-and job seeker recommendation, where aspects such as reciprocity and item spread are two other vital performance metrics for the quality of recommendations. Besides evaluating using these extra metrics… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
7
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 16 publications
(7 citation statements)
references
References 21 publications
0
7
0
Order By: Relevance
“…Meanwhile, in [135] it is revealed that implicit feedback is a more powerful indicator of users' broad interests. The same authors suggest in [136] that classical RS tend to predict better from the job seeker viewpoint, but more attention should be paid to reciprocity from the recruiter side.…”
Section: Content-basedmentioning
confidence: 93%
See 1 more Smart Citation
“…Meanwhile, in [135] it is revealed that implicit feedback is a more powerful indicator of users' broad interests. The same authors suggest in [136] that classical RS tend to predict better from the job seeker viewpoint, but more attention should be paid to reciprocity from the recruiter side.…”
Section: Content-basedmentioning
confidence: 93%
“…Reusens et al [135,136] Identifies best indicators of job seekers' preferences. Analyzes the impact of reciprocity versus non-reciprocity.…”
Section: Rs Family Authors Key Featuresmentioning
confidence: 99%
“…Reusens et al [103] compare several CF approaches with keyword search in terms of recall and reciprocity, both for job recommendation and job seeker recommendation. With respect to job recommendations, although traditional CF approaches performed acceptably in terms of recall, they were inferior to keyword search in terms of reciprocity.…”
Section: Knowledge-based Jrsmentioning
confidence: 99%
“…Although some contributions do take this reciprocal nature into account, and usually with success (e.g., [17,103,70]), most contributions consider the one-dimensional job seeker perspective, neglecting possible harm to the employer and/or job portal.…”
Section: On the Temporal And Reciprocal Nature Of Job Recommendationsmentioning
confidence: 99%
“…(3) The user's common scoring project is a very important factor. Let (1,2,2,1) and (5,5,4,4) be the rating vectors of two users. Calculating only the common scoring project will result in inaccurate similarity,for example, the Jaccard similarity calculation does not take into account the user's specific rating value, so that the similarity of the two is as high as 1, If you don't consider this factor at all, you will lose some important information, such as MSD.…”
Section: B the Precision Valuementioning
confidence: 99%