TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Predicting Popularity of Posts on Hacker News (2016) [pdf]

45 pointsby adgasfalmost 8 years ago

3 comments

hanozalmost 8 years ago
I predict this post would be a lot more popular if its title ended with "with machine learning".
评论 #14501006 未加载
AndrewKemendoalmost 8 years ago
<i>The content of a news post is the most powerful source for predicting its popularity.</i><p>I would like to believe this is true, and I would guess that it&#x27;s probably more true on HN than elsewhere, but I would really like to see them dive more into how they came to this conclusion.<p>I think the moderator led title editing makes this comparison more difficult (not bad necessarily) but it would be worth comparing popularity:content to popularity:title to have a more rigorous understanding.<p>Overall I applaud the approach they took. It seems however that the conclusion&#x2F;output doesn&#x27;t give better insight into the parameters which drive post popularity on HN, over previous approaches which seek to understand the underlying voting mechanism [1]. While different they are trying to basically understand the question &quot;what makes for a popular post on HN.&quot;<p>Modeling the sentiment of a community under a formal mechanism (vote algo) is incredibly difficult to do correctly, so again kudos for the work and it seems like it&#x27;s something that could be built on.<p>[1]<a href="http:&#x2F;&#x2F;sangaline.com&#x2F;post&#x2F;reverse-engineering-the-hacker-news-ranking-algorithm&#x2F;" rel="nofollow">http:&#x2F;&#x2F;sangaline.com&#x2F;post&#x2F;reverse-engineering-the-hacker-new...</a>
patmcguirealmost 8 years ago
It isn&#x27;t too particular to hacker news, although I did like the tables, definitely recognized the topics.<p>SELECTED TOPICS EXTRACTED BY NMF<p>Topic 1 js javascript node react component python config browser<p>Topic 2 pple iphone ipad fbi mac cook sir headphone watch steve<p>Topic 3 invest startup fund venture capital entrepreneur tech raise<p>Topic 4 game pokemon vr nintendo virtual oculus headset steam<p>Topic 5 email clinton website inbox gmail slack spam campaign<p>Topic 7 tesla vehicle musk autopilot elect autonomous battery road<p>Topic 8 facebook twitter advertise zuckerberg messenger snapchat<p>Topic 11 docker deploy cloud kubernet swarm cluster microservices<p>Topic 12 ai intelligence algorithm neurual deep alphago deepmind<p>Topic 14 uber ride city lyft tax vehicle hail self did transport kalanick