Search K
Appearance
The Explore tool allows you to discover hundreds of papers in a fraction of the time across different scientific fields. You can search for literature by giving the system a self-written text or a link to a research paper.
As a result, you will get a map of relevant papers including their relevance scores. The results will automatically create a new dataset in your dashboard. The Explore tool is a Content-Based Recommendation Engine and serves you best when:
The Explore tool is good when: You don’t exactly know what you are looking for, allowing you to do a broad search on a topic. If you are exploring interdisciplinary If you don’t know the right vocabulary
The Explore tool is a Content Based Search Engine - which means that the machine is not showing and recommending what other researchers have read, but only the documents that match the text you uploaded. The tool identifies the most meaning-bearing words in the text itself, enriches it with contextual synonyms and other words that scientists use within the same context. It also enriches the model by adding hypernyms or topic modeled words - creating a fingerprint. And then matching this fingerprint to documents in the database.
To start a search you need to select one or multiple datasets to search within, then you can find Explore on the right side panel. Here, you can start your search in two ways. First is to copy either the URL or DOI link and paste it in the field for the research question. The engine then will fetch the title and abstract of the paper and provide you relevant results. The second way is by writing your own problem statement description. All you need to do is to write the title of the research question and another text box will appear where you can write the problem statement. The absolute technical minimum is 100 words, but we recommend 300 to 500 words for the best results.
The documents are searched within your selected datasets. As a result, you will get a map of relevant papers including their relevance scores. The map is divided into topics and all the results are collected underneath these topics. Each of the papers has its relevance score - this indicates how similar the found paper is to your problem statement. You can navigate this map, exploring each topic and all relevant papers. The tool will automatically create a new dataset for you, from the documents in this map, that you can continue working with.