JSTOR Labs have introduced a beta research search tool that is worth exploring.  You can upload or drag and drop a file into the search box and the Analyzer tool will analyze the keywords and then produce a list of JSTOR items that match those keywords.  You can even use your phone to photograph some text and upload that for analysis!.  This service is not perfect but you can improve its use as a bibliographic research tool by adding additional keywords, and ranking their importance.

You need a fairly significant piece of text to benefit from this tool, but you can drop in all sorts of files such as an assignment, work based report or journal article you are working on.  You will get mismatches and it will work better with some searches than other, but if you are struggling to retrieve content from your usual search strategies, why not see if this helps.

The University of Exeter has extensive subscriptions to the journal and book content on JSTOR, so not only will you get a list of results, you’ll be able to examine the full text of your matching documents in the majority of cases.

Find out more about this tool from JSTOR and read the announcement blog which outlines some search scenarios that the developers hope this research tool can assist with.  Alex Humphreys from JSTOR says

Thinking only of keyword search within an academic context: junior researchers sometimes flail and thrash as they figure out the right keywords for their search – they know what they want, but what set of jargon-y terms will help them find it? At the other end of the spectrum, more experienced researchers can find themselves caught in discipline- or citation-based siloes, unaware of what they are unaware of (until the peer review feedback comes in…). I think JSTOR Labs might have something to help with these problems.

I gave it a trial by uploading a recent Powerpoint file we used with law undergraduates during a session on planning and conducting legal research for dissertations and it did a pretty good job of extracting key concepts from the document and  finding related content.  I added some phrases to the prioritized terms and played with the weightings until I got the most useful sets of search results for my needs.  So, if you are going to explore, I recommend you use the tools to add and adjust the importance of your search terms.

This tool is in beta and the developers are keen to develop it, based on feedback from users so try it out and pass on any feedback to the