Molecular Connections’ Author & Affiliation Disambiguation service includes:

• Author & Co-author knit development

• RDF triple stores management and development 

• Name Entity Disambiguation
  

• Library Management

Molecular Connections uses a fuzzy logic based technology to disambiguate authors /institutions automatically and the “hybrid” workflow provides manual muscle to improve the accuracy of the disambiguation to more than 99%. The approach further utilizes the meta-data surrounding authors’ profile (First-, Middle- and Last- name) and institution/affiliations from various data sources.  Author record meta-data is further complemented with entities such as the institutions’ address, Digital Object Identifier (DOI), co-authors in the publications, public profile identifiers (ORCID, Publons, etc.) and funding history (grants) to create a comprehensive database around the author and also to increase the efficacy of disambiguation.

Molecular Connections has generated an in-house proprietary database, which now contains a master list of more than 50,000 institutions (Academic and Commercial) from over 100 countries, and over 1,00,000 aliases enriched across multiple domains.

Proprietary Author & Affiliation Disambiguation System – MC Identify™

MC Identify™ facilitates identification of various related components including co-author profiles, net output of a research organization of interest etc., and helps in referee searches.