The score tells you how similar your writing is to the category you selected. Use it to check the draft's emphasis. It doesn't grade factual accuracy or predict a ranking or citation.
Here's how it works. Your text and the category are represented as sets of numbers called vectors. OppAlerts compares them using cosine similarity, then multiplies the result by 100 to show a percentage. For each taxonomy, you see the ten closest categories and, if your target falls outside that list, where it ranks. Read those matches against what the article is supposed to cover.
Use the category matches and missing phrases to find explanations you may have left out. For example, a phrase about emergency cover could prompt you to explain what a maintenance contract includes. Adding the phrase alone might change the score; explaining the terms gives the reader something useful.
You can submit up to 8,192 bytes at a time. Longer text is rejected, so check long drafts in sections. Those section scores can't be averaged into a score for the whole article. Read more about the calculation and how to use it when editing.
Browse all frequently asked questions.
See how OppAlerts fits your work.
Tell me what you are working on and what you need to find out. I can walk you through the relevant reports and explain what OppAlerts can help you do.
You can explore the demo first, or use this form to ask about a task or arrange a demonstration with me.