Knowledge Miner KnowledgeMiner, an online AI-based tool for systematic exploration of scientific literature

KnowledgeMiner is an online AI-based tool that assists experts in systematically finding evidence in scientific literature. It does so by facilitating the creation and expansion of dedicated ontologies and using them to mine substantial volumes of literature. Results are presented in heatmaps and datatables that can easily be used to further explore, analyze and filter relevant results.

KnowledgeMiner is a tool which uses AI-driven techniques to help experts in retrieving and exploring scientific literature.

KnowledgeMiner offers a two-stage pipeline for systematically exploring scientific literature. 

The first stage allows users to define their own ontologies. Users can upload already existing lists of search terms, but may also start by typing a research question for which OpenAI's GPT3.5 large-language model returns a list of possibly relevant search terms. Users can iteratively edit and expand their ontologies by requesting GPT to suggest related keywords and synonyms.

In the second stage, users select two ontologies to be used for mining all PubMed titles and abstracts published since 2010. Results are presented in a heatmap displaying the number of unique sentences containing a hit for any possible combination of single terms from both ontologies. By clicking on rows, columns or cells in the heatmap, users can navigate to the underlying textual data. Sentences containing the hits are shown in a table together with some accompanying metadata such as a link to the original paper and information about the document type. It is also possible to view the complete abstracts in which the relevant sentences were identified.

Results can be downloaded for further analysis.

Do you want to know more about KnowledgeMiner or AI/NLP-based tooling? 

If you are interested to know more about this tool, please contact: Gino.Kalkman@tno.nl and/or Eugene.vanSomeren@tno.nl