Are machine-written wine reviews closer than ever?
Dartmouth researcher: “We couldn’t tell them apart from human reviews”
A group of Dartmouth researchers have apparently taken the next step in machine-written wine reviews. Their study, published earlier this year in the International Journal of Research in Marketing, takes the work we’ve seen with artificial intelligence and brings it to a terrifying new place: The results “show strong support for the assertion that machines can write reviews that are indistinguishable from those written by experts.”
Keith Carlson, a doctoral research fellow at Dartmouth’s Tuck School of Business, didn’t say that the algorithm he and four others developed would show up as part of Wine Spectator tasting notes anytime soon. Some work still needs to be done, including further research into how similar the machine reviews are to human reviews.
Which is what I noticed: The examples were close, but not quite there – one machine rose review mentioned vanilla, which isn’t all that common in rose.
Still, Carlson told me, advancements in machine neural networks allowed the group to apparently come closer than anyone has before in making AI-generated wine reviews practical. Their algorithm used thousands of tasting notes from wine magazines to come up with a way that a machine could “teach” itself to write reviews.
Take that as you will. Regular readers will know how I feel. Wine has enough problems without some marketing guru -- or, even worse, some media type – using AI reviews to flog product on the cheap. If this is practical, I can see AI reviews trolling sites like Vivino and Cellar Tracker, making consumers think the wines are more popular than they are – or taste a certain way when they may not.
That the study was published in a marketing journal is especially bothersome, as if the only use for technology is to sell stuff. And the Dartmouth news release even used the word “disrupt,” which is tech speak for “this will make us a gazillion dollars and aren’t we smarter than everyone else.”
Carlson emphasized that the last thing the group wants is for AI reviews to replace people. Rather, he says, they can be used to make wine reviewing easier, as a starting point for human reviewers. Perhaps. But I don’t know that the machine’s cabernet sauvignon review – dry, with blackberry fruit – is going to tell me anything new about cabernet.
But what do I know? I’m not out to disrupt anything.
More about AI wine reviews:
• "Crisp and fresh:" AI wine writing strikes again
• Artificial intelligence and wine recommendations
• AI wine writing: Maybe it’s not around the corner after all
Create your profile
Only paid subscribers can comment on this post
Check your email
For your security, we need to re-authenticate you.
Click the link we sent to , or click here to sign in.