I've been doing some research into different types of tools that can be used to cluster ideas from the interviews:

RapidMiner - http://rapid-i.com/component/option,com_frontpage/Itemid,1/lang,en/
Open-source data and text mining software.

GATE (General Architecture for Text Engineering) - http://gate.ac.uk/
Open-source natural language processing and language engineering tool

OCLC Tag Cloud - http://tagcloud.oclc.org/tagcloud/TagCloudDemo
Ability to group like terms, use a stop list, and set a color theme.

TagCrowd - http://tagcrowd.com/
Allows for the creation of a stop list, ability to ignore common words, and ability to group similar worlds together (learning, learned, learns = learning).

ConceptNet - http://web.media.mit.edu/~hugo/conceptnet/
A freely available commonsense knowledgebase and natural-language-processing toolkit which supports many practical textual-reasoning tasks over real-world documents right out-of-the-box (without additional statistical training) including: topic-jisting (e.g. a news article containing the concepts, “gun,” “convenience store,” “demand money” and “make getaway” might suggest the topics “robbery” and “crime”); affect-sensing (e.g. this email is sad and angry); analogy-making (e.g. “scissors,” “razor,” “nail clipper,” and “sword” are perhaps like a “knife” because they are all “sharp,” and can be used to “cut something”); and others.

Good general overview of "data mining" and "concept mining" on wikipedia.

Other than using the OCLC Tag Cloud, I have no prior experience with these tools. Some seem more complicated than others. I suppose the group needs to decide on the level of sophistication needed.