To what extent are there differences between the debut works of acclaimed authors, published in their early years, and their later writings? What transformations occur in their style after decades spent in literary endeavors? How does their stylistic approach and language evolve?
To answer these questions, website MyPoeticSide.com, in collaboration with linguistic experts, scrutinized the vocabulary evolution in the works of 20 renowned authors, ranging from Ray Bradbury to Mary Shelley, Doris Lessing, and Kazuo Ishiguro.
The goal was to discern whether the lexical diversity of these writers increased or diminished over the course of their literary endeavors. Utilizing cutting-edge artificial intelligence and natural language processing technologies, the study examined 40 novels from these writers, comparing an early work with a later one from each author, yielding surprising findings.
In this unprecedented AI-powered study, a database incorporating over 3 million words from the 40 books was compiled. A lemmatization process, which consolidates words to their root forms, was employed to assess lexical diversity, thereby minimizing the impact of word form variations.
The study unveiled which authors enriched their linguistic variety in their more recent publications compared to their initial works, such as Beryl Bainbridge, Margaret Drabble, Mary Shelley and Muriel Spark.
On the other hand, authors who decreased their lexical variety include Charles Dickens, Alice Munro, Kazuo Ishiguro and Doris Lessing.
"This inquiry paves new avenues for literary studies through state-of-the-art technological tools. It will equip linguists and academics from various fields with deeper insights into the masterpieces of legendary writers, their writing progression, and, more importantly, spark intriguing new queries regarding the literary creation process," stated Julian Yanover, the developer behind MyPoeticside and leader of the research.
The case of Agatha Christie deserves special mention. This detective novel author made headlines in 2009 when a group of researchers suggested, after analyzing several of her works and noting how her vocabulary narrowed in her books as she aged, that she must have suffered from Alzheimer's. In this study, two of her books were analyzed: "The Mysterious Affair at Styles", her first Hercules Poirot novel published in 1920 when she was 30 years old, and "Elephants Can Remember" from 1972, also featuring detective Poirot, when she was 82.
While "The Mysterious Affair at Styles" achieved a lexical diversity score of 84.9, "Elephants Can Remember", which was published 52 years later, only obtained a score of 67.4, showing an extremely wide difference of 17.5 points between them. This finding supports the Alzheimer theory, as such a big gap was not found in any other writer.