Wf at 09:07, 10 March 2023

2023-03-10T09:07:18Z

Tim Holzheim: /* Wikidata Reconciliation */

2023-03-09T09:47:53Z

Wikidata Reconciliation

Tim Holzheim: /* Wikidata Reconciliation */

2023-03-09T09:44:30Z

Wikidata Reconciliation

Tim Holzheim: /* Volume Editors of CEUR-WS in dblp */

2023-03-09T09:00:42Z

Volume Editors of CEUR-WS in dblp

Tim Holzheim: /* Comparing Extracted and dblp Editors */

2023-03-09T08:57:35Z

Comparing Extracted and dblp Editors

Tim Holzheim: Created page with "= Editor Extraction = * covered volumes 1-3354 ** optimized for volumes 600+ * 11764 Editor records * for 228 volumes no editors could be extracted File:volume_editor_distr..."

2023-03-09T08:49:22Z

Created page with "= Editor Extraction = * covered volumes 1-3354 ** optimized for volumes 600+ * 11764 Editor records * for 228 volumes no editors could be extracted File:volume_editor_distr..."

New page

= Editor Extraction =

* covered volumes 1-3354
** optimized for volumes 600+
* 11764 Editor records
* for 228 volumes no editors could be extracted
[[File:volume_editor_distribution.png|400px]]

= Reconciliation =
== dblp reconciliation ==

=== Volume Editors of CEUR-WS in dblp ===
<source lang="sparql">
PREFIX dblp: <https://dblp.org/rdf/schema#>
SELECT DISTINCT ?vol_number (GROUP_CONCAT(?name; separator="|") as ?names) (GROUP_CONCAT(?dblp_id; separator="|") as ?concat_dblp_id)
WHERE {
?volume dblp:publishedIn "CEUR Workshop Proceedings" ;
dblp:publishedInSeries "CEUR Workshop Proceedings" ;
dblp:publishedInSeriesVolume ?vol_number;
dblp:hasSignature ?editors.
?editors dblp:signatureDblpName ?name ;
dblp:signatureCreator ?dblp_id ;
dblp:signatureOrdinal ?editor_ordinal ;
dblp:signaturePublication ?dblp_publication_id ;
a dblp:EditorSignature.
}
GROUP BY ?vol_number
</source>

=== Volume Editors of CEUR-WS in dblp with identifiers ===
<source lang="sparql">
PREFIX datacite: <http://purl.org/spar/datacite/>
PREFIX dblp: <https://dblp.org/rdf/schema#>
PREFIX litre: <http://purl.org/spar/literal/>
SELECT DISTINCT
(group_concat(DISTINCT ?nameVar;separator='|') as ?name)
(group_concat(DISTINCT ?homepageVar;separator='|') as ?homepage)
(group_concat(DISTINCT ?affiliationVar;separator='|') as ?affiliation)
(group_concat(DISTINCT ?dblpVar;separator='|') as ?dblp)
(group_concat(DISTINCT ?wikidataVar;separator='|') as ?wikidata)
(group_concat(DISTINCT ?orcidVar;separator='|') as ?orcid)
(group_concat(DISTINCT ?googleScholarVar;separator='|') as ?googleScholar)
(group_concat(DISTINCT ?acmVar;separator='|') as ?acm)
(group_concat(DISTINCT ?twitterVar;separator='|') as ?twitter)
(group_concat(DISTINCT ?githubVar;separator='|') as ?github)
(group_concat(DISTINCT ?viafVar;separator='|') as ?viaf)
(group_concat(DISTINCT ?scigraphVar;separator='|') as ?scigraph)
(group_concat(DISTINCT ?zbmathVar;separator='|') as ?zbmath)
(group_concat(DISTINCT ?researchGateVar;separator='|') as ?researchGate)
(group_concat(DISTINCT ?mathGenealogyVar;separator='|') as ?mathGenealogy)
(group_concat(DISTINCT ?locVar;separator='|') as ?loc)
(group_concat(DISTINCT ?linkedinVar;separator='|') as ?linkedin)
(group_concat(DISTINCT ?lattesVar;separator='|') as ?lattes)
(group_concat(DISTINCT ?isniVar;separator='|') as ?isni)
(group_concat(DISTINCT ?ieeeVar;separator='|') as ?ieee)
(group_concat(DISTINCT ?geprisVar;separator='|') as ?gepris)
(group_concat(DISTINCT ?gndVar;separator='|') as ?gnd)
WHERE{
?proceeding dblp:publishedIn "CEUR Workshop Proceedings";
dblp:publishedInSeriesVolume ?volume;
dblp:editedBy ?editor.
?editor dblp:primaryCreatorName ?nameVar.
OPTIONAL{?editor dblp:primaryHomepage ?homepageVar.}
OPTIONAL{?editor dblp:primaryAffiliation ?affiliationVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?dblp_blank.
?dblp_blank datacite:usesIdentifierScheme datacite:dblp;
litre:hasLiteralValue ?dblpVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?wikidata_blank.
?wikidata_blank datacite:usesIdentifierScheme datacite:wikidata;
litre:hasLiteralValue ?wikidataVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?orcid_blank.
?orcid_blank datacite:usesIdentifierScheme datacite:orcid;
litre:hasLiteralValue ?orcidVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?googleScholar_blank.
?googleScholar_blank datacite:usesIdentifierScheme datacite:google-scholar;
litre:hasLiteralValue ?googleScholarVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?acm_blank.
?acm_blank datacite:usesIdentifierScheme datacite:acm;
litre:hasLiteralValue ?acmVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?twitter_blank.
?twitter_blank datacite:usesIdentifierScheme datacite:twitter;
litre:hasLiteralValue ?twitterVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?github_blank.
?github_blank datacite:usesIdentifierScheme datacite:github;
litre:hasLiteralValue ?githubVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?viaf_blank.
?viaf_blank datacite:usesIdentifierScheme datacite:viaf;
litre:hasLiteralValue ?viafVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?scigraph_blank.
?scigraph_blank datacite:usesIdentifierScheme datacite:scigraph;
litre:hasLiteralValue ?scigraphVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?zbmath_blank.
?zbmath_blank datacite:usesIdentifierScheme datacite:zbmath;
litre:hasLiteralValue ?zbmathVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?researchGate_blank.
?researchGate_blank datacite:usesIdentifierScheme datacite:research-gate;
litre:hasLiteralValue ?researchGateVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?mathGenealogy_blank.
?mathGenealogy_blank datacite:usesIdentifierScheme datacite:math-genealogy;
litre:hasLiteralValue ?mathGenealogyVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?loc_blank.
?loc_blank datacite:usesIdentifierScheme datacite:loc;
litre:hasLiteralValue ?locVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?linkedin_blank.
?linkedin_blank datacite:usesIdentifierScheme datacite:linkedin;
litre:hasLiteralValue ?linkedinVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?lattes_blank.
?lattes_blank datacite:usesIdentifierScheme datacite:lattes;
litre:hasLiteralValue ?lattesVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?isni_blank.
?isni_blank datacite:usesIdentifierScheme datacite:isni;
litre:hasLiteralValue ?isniVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?ieee_blank.
?ieee_blank datacite:usesIdentifierScheme datacite:ieee;
litre:hasLiteralValue ?ieeeVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?gepris_blank.
?gepris_blank datacite:usesIdentifierScheme datacite:gepris;
litre:hasLiteralValue ?geprisVar.}
OPTIONAL{
?editor datacite:hasIdentifier ?gnd_blank.
?gnd_blank datacite:usesIdentifierScheme datacite:gnd;
litre:hasLiteralValue ?gndVar.}
}
GROUP BY ?editor

</source>
=== Comparing Extracted and dblp Editors ===
* editor by volume comparison
** 2233 volume the extracted editors match the dblp editors
** 807 volumes are missing in dblp (editors extracted)
** 27 volumes more editors were extracted than in dblp
** 387 volumes dblp has more editors than we could extract

== Wikidata Reconciliation ==
Using the ids queried from dblp to find the corresponding wikidata entry.

Current strategy:
;Input: List of different identifiers that are known about a editor
;Output: SPARQL query

Example:
*Input:
** homepage: http://www.stefandecker.org
** gnd id: 173443443
** dblp author id: d/StefanDecker
* Output:
<source lang="sparql">
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT DISTINCT ?person ?personLabel
WHERE
{
{OPTIONAL{ ?person wdt:P856 <http://www.stefandecker.org>.} }
UNION
{OPTIONAL{ ?person wdt:P227 "173443443".} } # gnd
UNION
{OPTIONAL{ ?person wdt:P2456 "d/StefanDecker".} } # dblp
?person rdfs:label ?personLabel. FILTER(lang(?personLabel)="en")
}
</source>

Running these queries for all 4942 editors known by dblp we get:
* Queries currently running...[[User:Tim Holzheim|Tim Holzheim]] ([[User talk:Tim Holzheim|talk]]) 09:49, 9 March 2023 (CET)

← Older revision		Revision as of 09:07, 10 March 2023
Line 193:		Line 193:

	[[File:editors_wikidata_reconciliation.png\|800px]]		[[File:editors_wikidata_reconciliation.png\|800px]]
		+	[[Category:Text2KG]]

@@ Line 182: / Line 182: @@
+}
 </source>
 Running these queries for all 4942 editors known by dblp we get:
@@ Line 189: / Line 190: @@
 The figure below shows the distribution of the available identifiers depending of the three categories identified, conflict, unkown
 [[File:editors_wikidata_reconciliation.png|800px]]

← Older revision		Revision as of 09:44, 9 March 2023
Line 184:		Line 184:

	Running these queries for all 4942 editors known by dblp we get:		Running these queries for all 4942 editors known by dblp we get:
−	* ~~Queries currently running...~~[[~~User~~:~~Tim Holzheim\|Tim Holzheim]] ([[User talk:Tim Holzheim~~\|~~talk~~]]~~) 09:49, 9 March 2023 (CET)~~	+	* 1467 editors were found in wikidata
		+	* 62 editor records in dblp have a conflict with wikidata
		+	* 3413 dblp editor records were not found in wikidata
		+
		+	The figure below shows the distribution of the available identifiers depending of the three categories identified, conflict, unkown
		+	[[File:editors_wikidata_reconciliation.png\|800px]]

@@ Line 13: / Line 13: @@
 <source lang="sparql">
 PREFIX dblp: <https://dblp.org/rdf/schema#>
-SELECT DISTINCT ?vol_number (GROUP_CONCAT(?name; separator="|") as ?names) (GROUP_CONCAT(?dblp_id; separator="|") as ?concat_dblp_id)
+SELECT DISTINCT ?vol_number
 WHERE {
    ?volume dblp:publishedIn "CEUR Workshop Proceedings" ;

@@ Line 149: / Line 149: @@
 ** 27 volumes more editors were extracted than in dblp
 ** 387 volumes dblp has more editors than we could extract
+* 9321 out of 11764 editor records can be reconciled
 == Wikidata Reconciliation ==

Editor Extraction and Reconciliation - Revision history

Wf at 09:07, 10 March 2023

Tim Holzheim: /* Wikidata Reconciliation */

Tim Holzheim: /* Wikidata Reconciliation */

Tim Holzheim: /* Volume Editors of CEUR-WS in dblp */

Tim Holzheim: /* Comparing Extracted and dblp Editors */

Tim Holzheim: Created page with "= Editor Extraction = * covered volumes 1-3354 ** optimized for volumes 600+ * 11764 Editor records * for 228 volumes no editors could be extracted File:volume_editor_distr..."