{"id":"https://openalex.org/keywords/document-deduplication","display_name":"document deduplication","description":"The computational identification and removal or linking of duplicate documents in large collections, often using hashing or similarity estimation.","display_name_alternatives":["document de-duplication","document deduping","deduplication of documents","duplicate document removal","document dedup"],"ids":{"openalex":"https://openalex.org/keywords/document-deduplication","wikidata":null},"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.3342,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.3342,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1118,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"works_count":113,"cited_by_count":1821,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/document-deduplication","updated_date":"2026-11-22T04:06:09","created_date":"2026-09-30T00:00:00"}
