I'd argue that titles, as long as they're neutral and accurate, have nothing to do with the upvotes you'll get. This is a perfect example of using data to try to find something that simply doesn't exist or that bear so little weight in comparison to the other variables that you can safely ignore it.
Show HN: Testing HN titles against a neural network
61–70 of 225 posts
Re: Show HN: Testing HN titles against a neural network
#62Show HN: Can a neural network predict if your HN post title will get up votes? Bad: 0.0598 - Good: 0.9307 Can an AI predict if your HN post will go viral? The results will shock you Bad: 0.9539 - Good: 0.0401 Seems to work!
Lol, you forgot to put "Show HN" in the second one :p
Re: Show HN: Testing HN titles against a neural network
#63Re: Show HN: Testing HN titles against a neural network
#64"How to better waste time by using your time less efficiently."
Bad: 0.0005 - Good: 0.9995
Re: Show HN: Testing HN titles against a neural network
#65"creating linux network socketss" -> Good 0.99
"creating linux network sockets" -> Good: 0.01
Re: Show HN: Testing HN titles against a neural network
#66I'd argue that titles, as long as they're neutral and accurate, have nothing to do with the upvotes you'll get. This is a perfect example of using data to try to find something that simply doesn't exist or that bear so little weight in comparison to the other variables that you can safely ignore it.
> I'd argue that titles, as long as they're neutral and accurate, have nothing to do with the upvotes you'll get.
I'd argue that titles that are neutral and accurate have been edited from the original linkbait title that got the link to the front page.
Re: Show HN: Testing HN titles against a neural network
#67HN downvoted the news of Elon Musk's passing as well as the DIY portable fusion reactor.
Re: Show HN: Testing HN titles against a neural network
#68It's basically a buzzword detector.
"this is just a tool for detecting buzzwords"
=> Bad: 0.9991 - Good: 0.0011
"this is merely a device for detecting artificially sophisticated words"
=> Bad: 0.0019 - Good: 0.9980
Re: Show HN: Testing HN titles against a neural network
#69This comment is going to collect the most votes yet is predicted to be Bad: 0.9320 - Good: 0.0800
Does this not add up to 1.0 by the way.
Re: Show HN: Testing HN titles against a neural network
#70Makes me wonder if there is ever any non-toy usage of AI sentiment analysis. People (managers, customers, marketing, etc) think is the hottest thing since sliced bread, but every time I've looked at it, the results are meaningless noise, like in the myriad of examples in the comments here.
It's a cool bullet point in the slide deck, and it gives you some metrics to graph on dashboards, but I'm unconvinced that it means anything.