Where Don't Concept Topics Work Well?
Where Don't Concept Topics Work Well?Given the ease of defining concept topics and the high degree of accuracy in broad topic areas like Food and Travel and Business, it would be easy to jump to the assumption that Concept Topics are a magic bullet for any and all categorization problems. While they represent a huge advance in categorization technology, it’s not a magic bullet. If for example you were doing very detailed low level categorization of drug interaction reviews and wanted to bucket content by drugs for disease classes (for example Liver Cancer Drugs), then concept topics wouldn’t get you there. In these detailed cases a query based or training based model will be more effective and will require less effort than it would when trying to define a broad/general category. This is also new technology for us, with profound implications for how we approach categorization of content. We're still working to understand all the limitations and already have some improvements in mind. While not perfect for every situation, Concept Topics are a significant enhancement for general purpose categorization because it solves the very difficult problem of bucketing into generic high level categories that have always been very difficult to handle because of the breadth of things that fall into them. In other words, if you're doing any categorization, you're going to want to try Concept Topics. Node Weight:
0
|
|
