Can an algorithm assess the quality of a novel manuscript?

18 December 2022

It pays to follow Australian scientist and writer Dr Karl Kruszelnicki (aka Dr Karl) on Twitter (as long as Twitter continues to permit such behaviour), especially if you are writing a novel.

The other day he posted a link to an article published in 2014, about a literary algorithm that is apparently capable of quickly assessing the quality of an unpublished novel manuscript. The article expounds upon research conducted (PDF) by Stony Brook University into the matter:

Regarding lexical choices, less successful books rely on verbs that are explicitly descriptive of actions and emotions (e.g., “wanted”, “took”, “promised”, “cried”, “cheered”, etc.), while more successful books favor verbs that describe thought-processing (e.g., “recognized”, “remembered”), and verbs that serve the purpose of quotes and reports (e.g,. “say”). Also, more successful books use discourse connectives and prepositions more frequently, while less successful books rely more on topical words that could be almost cliche, e.g., “love”, typical locations, and involve more extreme (e.g., “breathless”) and negative words (e.g., “risk”).

Fascinating, no? Remember though, don’t let the algorithm write the book, let it guide you in writing the book. But if you wish to avoid algorithms all together, look at the way Irish author Sally Rooney — for one — does things.