Interfolio Faculty Web Profiles: Fingerprinting Overview
The Fingerprint Engine (available for premium web profiles) is a tool that automatically generates a ‘fingerprint’ of key concepts based on the titles and descriptions for scholarship, grant, and profile data in FAR. These concepts provide a quick snapshot of the key themes/topics covered by the content and can be used during search and filtering. The Faculty Web Profile can also be used for finding similar researcher profiles. Some of the fingerprints seen on Interfolio Faculty Web Profiles are aggregations, meaning they are recalculated and may change after a new piece of content is added.
Please note that we currently only fingerprint content in English (where the English-language description text is not available, no fingerprint will be generated)
Optimize Content for Fingerprinting
To generate the fingerprint, the content (scholarship, grants, and profile data fed from FAR) needs to have a title and a description providing an overview of the content piece.
At the moment, there is no restriction on the number of words that must be included, but our tests show that a title of 5-15 words and a description of 150–300 words would produce a good fingerprint. There is no need to shorten your description if it is longer and the system will take all of the available content into account (not just the first 300 words).
FAQs
How can a fingerprint change over time?
When new data for an aggregated fingerprint is added, the aggregation is recalculated. For example, the researcher’s fingerprint is an aggregation of the fingerprinting results for their research interests and all research outputs and prizes, linked to the person.
Major updates to the thesaurus are not frequent and are mainly focused on adding new terms or optimizing the existing vocabulary (removing the terms that are no longer used, can be replaced with a better alternative). An update to the thesaurus may lead to a change in the resulting fingerprint.
Why does Web Profiles display fingerprints that are not related to my area of expertise?
The Elsevier Fingerprint Engine utilizes advanced Natural Language Processing (NLP) techniques to analyze the text of scientific documents, including abstracts. During this process, key concepts are identified and indexed based on their significance within the content. The goal is to capture a wide range of relevant terms that reflect the main themes and ideas presented in the text. The Fingerprint Engine uses thesauri that span all major disciplines, which means that terms may be drawn from various contexts. This multidisciplinary approach can result in fingerprints that capture a broader array of concepts, which may occasionally include terms that seem less relevant or important from a particular viewpoint. Please find more details on the Elsevier Fingerprint Engine here.
Can the irrelevant fingerprints or subject areas be removed?
Yes, removing the fingerprints and subject areas is possible in the Web Profiles backend. Please contact the Interfolio support team to follow up.
What other options are available for displaying fingerprints in Web Profiles?
Currently, the number of concepts per thesauri in aggregated fingerprints for faculty is set to 50 by default. If the number of concepts is reduced, it could potentially eliminate less relevant terms. Please contact the Interfolio support team if you wish to make the change.