Semantic, Adaptive Search – Now that’s a Mouthful
Artificial intelligence (AI) has become the holy grail that is touted as the solution to everything, from fixing leaky sinks to establishing a colony on Mars. Oh, did I mention improving poor old search?
The basic problem with AI is there are few vendors. So, we wait. Although, the legal industry is pursuing AI with great gusto, but not necessarily making great strides.
Depending on the technology design, AI software is predicted to ‘learn’ from user behavior. Since it adapts to user context, it is supposed to provide better search results than those typically delivered by traditional semantic search engines.
These solutions rely on a thesaurus or ontology to classify, and understand what people are searching for. Instead of just keywords, words in the context of how they are used are also stored. Semantic, adaptive search falls under the auspices of AI, and will additionally use advanced machine learning and neural networks.
All fine and dandy, right? This is the part I don’t seem to get straight. On average, an information seeker will provide 2.73 terms describing the information needed, and will only attempt a search twice in a given session. If the right information isn’t located in those two attempts, the user assumes it does not exist or that it is, at best, inaccessible. (Gartner)
I used to be organized, but somehow I lost that admirable trait. I blame it on information overload. Anyway, I now spend quite a bit of time searching for my blogs, white papers, and research, as I have no clue where I filed them. I have resorted to using multiple search criteria. Something I do, which is ridiculous, is repeat the same erroneous search request, because I know it’s there somewhere and the system must have misunderstood, right?
So does the system learn from my mistakes, or learn the mistakes? Does anyone know?