Wissenschaftliche Inhalte effektiv nutzen  – mithilfe von Semantik


graphic of people with computers and tablets

In einer zunehmend datengesteuerten Gesellschaft kann es überfordernd sein, Ihre Wissensdatenbank auf dem neuesten Stand zu halten und Daten effektiv zu nutzen. Das Ergebnis ist in vielen Organisationen eine unzureichende Nutzung der Ihnen zur Verfügung stehenden Daten und Inhalte. Dies ist besonders häufig in Disziplinen wie den Biowissenschaften der Fall, in denen Daten weitgehend unstrukturiert sind und in denen eine heterogene und sich schnell entwickelnde Terminologie vorherrscht. Das erschwert die Verarbeitung der Daten, was wiederum die Suche und die Extraktion wissenschaftlicher Erkenntnisse behindert. Diese Herausforderungen untermauern die zunehmende Akzeptanz der FAIR (Findable, Accessible, Interoperable and Reusable) Datenprinzipien.

Erfahren Sie mehr in dem nachfolgenden Beitrag aus dem Blog des Copyright Clearance Centers.

Increasingly, the content landscape is more complex; more content providers as well as a broader range of internal data management tools lead to further siloing of data and making it inaccessible to users within an organization. Data-driven organizations need to support both internal and external content, making it accessible to users and enabling them to realize the investment made in this content.

Access to data is one part of the problem; findability is a second challenge that data-driven organizations face. In this blog post, learn how Copyright Clearance Center (CCC) and SciBite have combined their expertise to deliver a FAIR data platform that offers full semantic search within RightFind Navigate. RightFind Navigate both streamlines the delivery and aggregation of content and leverages industry-leading named entity recognition to enable full semantic search over aggregated content sets.

Bringing Content Together to Break Down Silos

As leaders in providing access to content, CCC developed RightFind Navigate to break down data silos and to streamline the delivery of information to users, whether that is scientific literature, global life science patents, or the latest information on drugs or ongoing clinical trials. RightFind provides access to the most comprehensive collection of scientific, medical, and technical content, including over 5 million open access articles, in a copyright-compliant manner.

RightFind Navigate provides a unified view of both internal and external content sets, saves time and effort, and eliminates data silos that limit the accessibility and usability of this content by users. Through a machine learning (ML) backed search experience, users are able to personalize their search experience, helping them to find key insights quickly and efficiently and directly feeding into the development of the next generation of therapeutics. This search experience is further enhanced through the application of semantics, powered by the SciBite semantic platform.

Applying Semantics to Improve Findability and Usability of Content

SciBite is an industry leader in the enterprise-wide implementation of FAIR data principles. Through an award-winning semantic platform, SciBite uses hand-curated and optimized ontologies (VOCabs) that contextualize and align data to the broader scientific community. These ontologies cover a broad range of concepts within the life sciences such as drugs, genes, proteins, combination therapies, and medical devices. When combined with a named entity recognition and extraction tool (TERMite), these VOCabs are used to identify key concepts or entities within the data and assign an ID to these entities.

A key to this tagging process is the ability to leverage the broad synonyms or different naming conventions that the VOCabs support, e.g. breast cancer, cancer of the breast, mammary tumour, or breast tumour are all different names for the same thing. This means that independent of how the data was captured in the original text, it will be accurately identified. Once tagged as an entity and assigned an ID (for example MedDRA ID10006187 for breast cancer), users can leverage all of the synonyms associated with the ID for search and analytics. For the RightFind Navigate user, independent of which search term they use, they will always return robust and inclusive search results. For example, whether the user searches for breast cancer or cancer of the breast, RightFind Navigate will know that these are equivalent and will return the same results, something that wouldn’t necessarily be the case if relying on string matching (keyword search). This improves the user experience and ensures that relevant content and insights are not missed.

How Does RightFind Navigate with Semantics Improve User Experience?

Data silos hamper access to data and limit the utility of internal and external content sets, as does the procurement of commercial data sources. Through RightFind Navigate, CCC provides a solution to streamline the delivery of published content and presents this alongside internal content and datasets. Combined with industry-leading semantic search powered by the SciBite platform, RightFind Navigate enables this aggregated content to be effectively navigated and insights extracted. De-siloing this content not only saves time and improves user experience, it also maximizes ROI for organizations who invest heavily in both internal and external content. In addition, having a platform of organized and harmonized data unlocks a whole host of downstream applications that can take this ROI to another level, such as analytical dashboards and even predictive ML and AI models.

Keep Learning: In this white paper from CCC and SciBite, we highlight four practical applications for semantic enrichment across the drug development pipeline, enabling life sciences organizations to not only save time but increase the accuracy and efficiency of their processes.

Get in Touch: If you are interested in exploring how RightFind Navigate with semantic search, powered by SciBite, can support your internal and external content, then please reach out to us.

Author: CCC

A pioneer in voluntary collective licensing, CCC (Copyright Clearance Center) helps organizations integrate, access, and share information through licensing, content, software, and professional services. With expertise in copyright and information management, CCC and its subsidiary RightsDirect collaborate with stakeholders to design and deliver innovative information solutions that power decision-making by helping people integrate and navigate data sources and content assets.