|"Needs more adjectives."|
More questions then occurred to me: Is 84% accuracy impressive? How does that compare to a human evaluator's predictive ability? And again, are the factors being used for evaluation inherently quantifiable or not? What the program did, apparently for 800 books in various genres, was "analyze text, comparing prediction results to actual historical information available regarding the success of the book."
What I found most fascinating, though, were the trends revealed by the research--the weird little commonalities that the computer program found in successful books.
Well, I suppose we've all been told to use fewer adverbs. But it's interesting to me that what we are often told in literary fiction is to be pithy, specific, vivid; to avoid filler verbiage and vague language; to not overuse adjectives; to imbue our work with action and emotion and select the right verbs. Plus, what the heck is up with that "and" and "but" business? What this tells me is that good writing, successful writing, goes so far beyond what you can deconstruct with an algorithm. You can't just insert random strings of adjectives and nouns and assume it will make you writing more popular. You can't just distill writing down to seemingly arbitrary rules of thumb.Heavy use of conjunctions like “and” and “but,” large numbers of nouns and adjectives, and the use of verbs describing thought processes such as “recognized” or “remembered” were found in successful books. Conversely, less successful work seemed to use explicitly described emotions and actions such as “wanted” or “promised,” and use more verbs and adverbs.
Or can you?