Literature Search: Semantic Scholar

Semantic Scholar is an artificial intelligence backed search engine for academic publications, developed at the Allen Institute for AI. In contrast with Google Scholar, Semantic Scholar is designed to highlight the most important and influential elements of a paper. The AI technology is designed to identify hidden connections and links between research topics.

The search engine does not do Boolean searches or use Boolean operators. Instead, it recognizes a topic based on context by examining the relationship between words in close proximity to each other. For instance, if you are interested in papers on the impact of free trade on economic growth you would simply enter these four terms: "free", "trade", "economic and "growth" in that order. The search engine uses AI to do a semantic search. The search engine employs an algorithm to retrieve papers that discuss the relationship of free trade and economic growth. It is also possible to use natural language when doing a search. Like Google Scholar, Semantic Scholar exploits graph structures, which include the Microsoft Academic Knowledge Graph, Springer Nature's SciGraph, and the Semantic Scholar Corpus.

Semantic Scholar is free to use and unlike similar search engines (i.e. Google Scholar) does not search for material that is behind a paywall. Users may search the database without creating an account, but by creating a free account, users can create alerts and save searches.  Results can be filtered by subject area, date range, author, publication name, and whether there is link to a PDF of the article. Results can be sorted by relevance, date and citation count.