CourtCast, a machine-learning model, relies only on PDF files of oral argument transcripts. There are three inputs: the number of words spoken by justices to each party, the sentiment of those words, and the number of times a justice interrupts an attorney. That’s really it — CourtCast doesn’t care about body language, it doesn’t care about justices’ ideologies, and it doesn’t care about who’s arguing the case in front of the court. It doesn’t know the law or the precedent or the political climate. The model trains itself on past cases, learning which justice tendencies are pertinent. It can then analyze the transcript from any fresh case and predict an outcome.It's an interesting idea, though more as a starting point than as a finished product (the creator agrees that it needs refinement). The biggest problem I see is with the 'sentiment' parameter -- there's a big difference between Justice Ginsburg, for example, expressing mild skepticism concerning an argument and her shouting, "That's bullshit!"
OK, you're right -- she probably doesn't often do that.
An interesting sidelight to the article is the chart detailing how often each Justice interrupts attorneys and how many words they speak in the course of questioning or commenting. Sotomayor gets the title of Chief Interrupter by a narrow margin over Scalia and Breyer, while Thomas never interrupts and Alito and Kagan seldom do so. Breyer is Mr. Loquacious, by a good margin, and Thomas (this is not exactly news) is The Court Clam.
I thought the interruption stats were of interest, since the conventional wisdom is that men do much more interrupting than women do. That doesn't seem to hold with the Court, where there seems, overall, to be little gender difference.
I'm afraid that if I were appointed to the Court (which seems unlikely) I would probably give Sotomayor a run for her money -- I have to admit that I fit the male stereotype in regard to interrupting people.
By the way, the model predicts a 61% likelihood that the King v. Burwell decision will uphold Obamacare.