Description

Name: skills_occupation_ngrams
Number of observations: 791,222
Number of features: 4
Description: This dataset collects statistics derived from free-text analysis on the skill-related responses collected in the Europass Survey. It describes the frequency of two-word terms in the skill free-text responses with respect to the occupations done by the respective respondents.
Sources: Europass Survey: June - September 2019
Download

Feature	Name	Description	Form¹	Stat²	Text³
bigram	Bigram	Bigram of keywords in a free-text response.		●	●
job_isco	Job ISCO 3	ISCO level 3 classification for job.	●		●
locale	CV Language	Language used to write CV.	●
responses	Responses	Number of responses with a particular combination of values for the above variables.		●
¹ Variable derives directly from a Europass CV;
² Variable is a statistical transformation of one or more Europass CV variables;
³ Variable is a result of information retrieval using text mining

Summary Statistics

Feature	Result
Variable type	character (nominal)
Number of missing values*	0 ( 0.00% )
Number of unique values	70
^* Missing features required for estimation, or unidentifi ed from classification algorithm.

Feature	Result
Variable type	character (nominal)
Number of missing values*	0 ( 0.00% )
Number of unique values	20
^* SkillsPassport.Locale missing.