"Pull Out All the Stops: Textual Analysis via Punctuation Sequences"

One of my papers, which has been available publicly for more than a year, is finally out in final form, with its coordinates (its page numbers and so on). Here are the details.

Title: Pull Out All the Stops: Textual Analysis via Punctuation Sequences

Authors: Alexandra N. M. Darmon, Marya Bazzi, Sam D. Howison, and Mason A. Porter

Abstract: Whether enjoying the lucid prose of a favourite author or slogging through some other writer's cumbersome, heavy-set prattle (full of parentheses, em dashes, compound adjectives, and Oxford commas), readers will notice stylistic signatures not only in word choice and grammar but also in punctuation itself. Indeed, visual sequences of punctuation from different authors produce marvellously different (and visually striking) sequences. Punctuation is a largely overlooked stylistic feature in stylometry, the quantitative analysis of written text. In this paper, we examine punctuation sequences in a corpus of literary documents and ask the following questions: Are the properties of such sequences a distinctive feature of different authors? Is it possible to distinguish literary genres based on their punctuation sequences? Do the punctuation styles of authors evolve over time? Are we on to something interesting in trying to do stylometry without words, or are we full of sound and fury (signifying nothing)?

In our investigation, we examine a large corpus of documents from Project Gutenberg (a digital library with many possible editorial influences). We extract punctuation sequences from each document in our corpus and record the number of words that separate punctuation marks. Using such information about punctuation-usage patterns, we attempt both author and genre recognition, and we also examine the evolution of punctuation usage over time. Our efforts at author recognition are particularly successful. Among the features that we consider, the one that seems to carry the most explanatory power is an empirical approximation of the joint probability of the successive occurrence of two punctuation marks. In our conclusions, we suggest several directions for future work, including the application of similar analyses for investigating translations and other types of categorical time series.

Revenge of the Oxford Comma: 2020 Edition

Truth is stranger than fiction. Always.

Update your lesson plans, we have a new perfect example for Oxford commas. https://t.co/gm1K8IHkGv

— Laura Ansley (@lmansley) November 14, 2020

(Tip of the cap to Jan van den Heuvel.)

Attention, Reuters: Proper Use of Colons is Important

Gosh, I hope the governor recovers soon. 🙄

(Reuters needs to make sure everyone on staff takes an English class.) https://t.co/Kh6KtDlUej

— Dr. Jonathan Foley (@GlobalEcoGuy) March 2, 2020

(Tip of the cap to Calling Bullshit.)

Update: Well, from the link (below) that Gregg Schneider just sent me, it appears that Reuters may have a writer who does not understand how to use colons properly.

Just one American with coronavirus still in hospital: Vice President Pence https://t.co/0aM9djXlEx pic.twitter.com/Zha44JLUmb

— Reuters (@Reuters) February 28, 2020

Boycotting a Coin Over a "Missing" Oxford Comma

Perhaps Philip Pullman is overreacting in his boycott of a coin over a missing Oxford comma, but this does pull at my heart strings. :)

(Tip of the cap to Sam Howison.)

"Topological Data Analysis of Continuum Percolation with Disks"

One of my papers came out in final form today. Here are some details and a story.

Title: Topological Data Analysis of Continuum Percolation with Disks

Authors: Leo Speidel, Heather A. Harrington, S. Jonathan Chapman, and Mason A. Porter

Abstract: We study continuum percolation with disks, a variant of continuum percolation in two-dimensional Euclidean space, by applying tools from topological data analysis. We interpret each realization of continuum percolation with disks as a topological subspace of [0,1]^2 and investigate its topological features across many realizations. Specifically, we apply persistent homology to investigate topological changes as we vary the number and radius of disks, and we observe evidence that the longest persisting invariant is born at or near the percolation transition.


And to give a story, or at least the hint of the interesting relationship that I sometimes have with typesetters and editors, here is a note that I received from them while we were working on the galley proofs.

Update (8/05/18): A nice way of phrasing things is that we're in a nonassociative situation, and hyphens are a great tool to indicate exactly (and tersely) where the parentheses should be to group terms in a way that renders their meaning unambiguous. (And, naturally, if somebody makes a change in my text that I don't like, my immediate desire is to change it back.)

Number of Spaces and Periods

Let the debating commence.

Hurray! Science vindicates my longstanding practice, learned at age 12, of using TWO SPACES after periods in text. NOT ONE SPACE. Text is easier to read that way. Of course, on twitter, I use one space, given 280 characters. https://t.co/4xI6sVbF88 Will arm-wrestle @Neuro_Skeptic pic.twitter.com/XpEr4KFR4x

— Nicholas A. Christakis (@NAChristakis) April 28, 2018

An Oxford Comma's Twitter Account

I should have known that an 'Oxford Comma' Twitter account exists. It's pretty funny.

(Tip of the cap to Kerstin Nordstrom.)

Subtitles: When You Run Out of Ideas

As you can see from the picture (of one of the books in Somerville College's Senior Common Room), some people have clearly run out of ideas when it comes to book subtitles.

Maybe I should write a book called "Networks: Those Objects with Vertices and Edges"? There does appear to be some evidence that using colons in titles increases citation counts.

Tales from the ArXiv: "Other Naive Models"

This paper's abstract has the following final sentence: "Furthermore our transition probability model is up to 20% more accurate than other naive models."

Notice the phrasing "other naive models", which contrasts rather sharply with the phrasing "other, naive models".

Comparing Novels Based Only on Punctuation

Can one algorithmically discern writing styles in novels based only on punctuation (no words)?

Take a look at this discussion.

I want to see someone compare the writing styles of different scientists in this way. :)

(Tip of the hat to Santa Fe Institute.)

Update (3/19/16): Here is my article on this for the Improbable Research blog.

New Punctuation Marks

Here are eight new punctuation marks for you to use and abuse. A couple of them are awesome. Sadly, they missed to 'bidirectional semicolon' :: (which I saw discussed in an awesome short play whose mechanism of delivering its premise was a seminar in which the speaker introduced many new punctuation marks that were heretofore missing), in which the left side explains the right side and vice versa. The example used in the play was "To be a Jew :: To be a Jew".

(Tip of the cap to Meredith Alden for the website.)

All the Quotes You Ever Wanted

Courtesy a link Ken Kharma posted on Facebook, here is an "amusing" website called The "Blog" of "Unnecessary" Quotation Marks that collects "pictures" of signs with "head-scratching" quotation marks. It's not as cool as Sad Guys on Trading Floors, but some of the pictures are pretty damned funny.