graphic of lines and dots

In der gesamten Gesundheitsbranche müssen Forscher Entscheidungen auf der Grundlage der bestmöglichen Sicht auf Daten treffen. Auf der Verarbeitung natürlicher Sprache basierendes Text-Mining ermöglicht es Forschern, wichtige Erkenntnisse aus riesigen Mengen veröffentlichter Informationen zu gewinnen. Aber was genau ist der beste Weg beim Text Mining? Abstracts oder Volltextsuche?

Unsere Kollegin Molly Buccini hat einen Blick auf exakt diese Frage geworfen und dazu einen Blogbeitrag veröffentlicht, den wir nachfolgend im Original veröffentlichen.

Across the healthcare industry, researchers and clinicians need to base decisions on the best possible view of data. Natural language processing-based text mining enables researchers to gather important insights from vast amounts of published information. Use cases range from drug discovery, clinical trial development, drug safety monitoring, through to real world insights and competitive intelligence. 

To capture the landscape of information needed for a particular project, mining abstracts and full-text papers both bring benefits. Scientific abstracts tend to be short, concise summaries, but miss much of the richness, detail, and granularity available from the full-text papers, particularly in tables. 

“Using abstracts rather than full-text articles when text mining scientific articles may often be a false economy,” said Stephen Garfield in Text Mining Scientific Articles: Why You Need the Full Picture. “It may feel like the quick route to results, but, in reality, only a full-text version is comprehensive. Put simply, text mining on full-text offers more facts, more kinds of facts, and quicker paths to insights.” 

In 2021, CCC and Linguamatics discussed how natural-language processing assists researchers to get better value from abstracts and full-text literature, with example use cases in research and rare diseases. One major benefit is savings – both in cost and time. Jane Reed, the head of life science strategy at Linguamatics points out, “If you’re trying to find the right article, read through the whole of information, and extract the information, that is very time consuming [and] costly if done manually.” 

XML for Mining offers text mining capabilities from more than 8000 journals from 60+ publishers which translates into over 13 million full-text articles. Ray Gilmartin, director of corporate solutions at CCC, discussed some of the benefits of how NLP and XML for Mining work concurrently including copyright compliance, simplification of process, and ease of use. Gilmartin stated that the partnership of RightFind and Linguamatics provides a solution that, “reduces all the manual processes, saving time, money, headaches, and frustrations.” 

To learn about the benefits of natural language processing-based text mining and more you can watch the conversation.  

More information: 

Learn more about knowledge management solutions like RightFind Navigate and XML for Mining.  

Related content: 

Fünf Empfehlungen für smartes Text- und Data-Mining 

Darauf sollten Naturwissenschaftler achten, wenn sie eine Strategie zur Nutzung von Daten entwickeln 

Author: Molly Tainter

Molly Buccini is a marketing communications manager at CCC. Her background before CCC includes B2B content marketing and local news reporting. Outside of the office, she enjoys reading, traveling, and theater.