Show HN: An Open Source Tool to Combat Clickbait Links
links.spince.com
Show HN: An Open Source Tool to Combat Clickbait Links
1–10 of 29 posts
Re: Show HN: An Open Source Tool to Combat Clickbait Links
#2Be interesting to train a model using user generated, is this click bait title yes/no. Is this something machine learning could get very good at?
Re: Show HN: An Open Source Tool to Combat Clickbait Links
#3Be interesting to train a model using user generated, is this click bait title yes/no. Is this something machine learning could get very good at?
There was a cool article on identifying clickbait headlines with machine learning just last month. (There was probably an HN discussion but I can't find it on my phone.) the main difference is that it operated only on the headline, not comparing it to the actual article.
https://www.linkedin.com/pulse/identifying-clickbaits-using-...
Re: Show HN: An Open Source Tool to Combat Clickbait Links
#4Be interesting to train a model using user generated, is this click bait title yes/no. Is this something machine learning could get very good at?
There are definitely training sets paired with Bayesian inference that attempt to do this.
Re: Show HN: An Open Source Tool to Combat Clickbait Links
#5Oh...nice try. I almost clicked on that link.
Re: Show HN: An Open Source Tool to Combat Clickbait Links
#6Be interesting to train a model using user generated, is this click bait title yes/no. Is this something machine learning could get very good at?
"Avoid clickbait links with this one weird trick!"
Re: Show HN: An Open Source Tool to Combat Clickbait Links
#7So that means it's fetching the content (or at least the HTML portion) of every eligible link? That seems like potentially a lot of network traffic for what it does. Find if you have a fast connection, I suppose.
Re: Show HN: An Open Source Tool to Combat Clickbait Links
#8Be interesting to train a model using user generated, is this click bait title yes/no. Is this something machine learning could get very good at?
Don't even need to use humans, I tried something easier -- http://github.com/peterldowns/clickbait-classifier
Re: Show HN: An Open Source Tool to Combat Clickbait Links
#9It assumes "a relevant (i.e. non-clickbait) link would have its text appear frequently on the actual page".
Is there empirical evidence for this claim? The examples featured in the article seem mixed (some right, some wrong).
It's easy enough to test: collect human judgement scores for a few hundred article links from several news sites (an afternoon's work) and compare to the algorithm.
Re: Show HN: An Open Source Tool to Combat Clickbait Links
#10I like the idea behind using TF-IDF. Feels like a lot of unnecessary network traffic though.