Here’s an interesting idea it wouldn’t have occured to me to ask. What is the length of time described in the average 250 words of narration and how has this changed over time? Most famously James Joyce’s “Ulysses” is a long novel about single day with many pages describing brief experiences in minute detail. In contrast, Olaf Stapledon’s Last and First Men covers 2 billion years in fewer words than Joyce uses to cover a single day.
Using human readers grading 1000 passages, Underwood et al. (2018) finds that the average length of time described in a typical passage has declined substantially since the 1700s, from a day to about an hour so a decline by a factor of 24. Writers have become much more focused on describing individual experiences than events.
In a blog post, Underwood revisits his earlier work but this time comparing human readers with various statistical techniques and also GPT. To use GPT he prompts
Read the following passage of fiction. Then do five things. 1: Briefly summarize the passage. 2: Reason step by step to decide how much time is described in the passage. If the passage doesn’t include any explicit reference to time, you can guess how much time the events described would have taken. Even description can imply the passage of time by describing the earlier history of people or buildings. But characters’ references to the past or future in spoken dialogue should not count as time that passed in the scene. Report the time using units of years, weeks, days, hours, or minutes. Do not say zero or N/A. 3: If you described a range of possible times in step 2 take the midpoint of the range. Then multiply to convert the units into minutes. 4: Report only the number of minutes elapsed, which should match the number in step 3. Do not reply N/A. 5: Given the amount of speculation required in step 2, describe your certainty about the estimate–either high, moderate, or low. The passage follows: <omitting this to save space>
Here’s an example of the analysis:
ABRIDGED PASSAGE FROM Jane Eyre: And signs, for aught we know, may be but the sympathies of Nature with man. When I was a little girl, only six years old, I one night heard Bessie Leaven say to Martha Abbot that she had been dreaming about a little child … Of late I had often recalled this saying and this incident; for during the past week scarcely a night had gone over my couch that had not brought with it a dream of an infant, which I sometimes hushed in my arms, sometimes dandled on my knee, sometimes watched playing with daisies on a lawn, or again, dabbling its hands in running water. It was a wailing child this night, and a laughing one the next: now it nestled close to me, and now it ran from me; but whatever mood the apparition evinced, whatever aspect it wore, it failed not for seven successive nights to meet me the moment I entered the land of slumber.
1: The narrator recalls a saying about dreaming of children being a sign of trouble and remembers an incident from her childhood. She then describes her recent dreams of infants over the past week.
2: The passage mentions the narrator’s childhood memory, which happened when she was six years old, and the past week of dreams. The time elapsed in the passage is the week of dreams.
3: 1 week has elapsed. At seven days a week that’s 7 days. 24 hours in a day, so 168 hours. 60 minutes in an hour, so 10080 minutes.
4: 10080 minutes.
5: Moderate confidence, as the childhood memory is not counted as time passing in the scene.
Overall, Underwood finds that GPT-4 is more accurate than previous statistical techniques in that its judgments correlate with those of human readers nearly as much as human readers correlate with themselves.
Addendum: See also my paper with Tyler on how to use GPT models.
The post Time Passages appeared first on Marginal REVOLUTION.