LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
1–10 of 79 posts
Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
#2Great analysis. How is divisiveness actually calculated?
Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
#3[flagged]
Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
#4Great analysis. How is divisiveness actually calculated?
search "divisive" here: https://github.com/outerbounds/hacker-news-sentiment/blob/ma...
I actually spent 10 minutes trying to see if there are obvious tests for U-shaped distributions. I'd love to hear if anyone has ideas here.
Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
#5[flagged]
Listen you just had to be there. Who wants a file picker with no thumbnails? That's no way to live.
Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
#6[flagged]
And Tesla is the most disliked with a real number of posts.
In the other direction math is the most liked! And if you go a little further Python is the clear winner for languages.
Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
#7Is this just using LLM to be cool? How does pure LLM with basic "In the scale between 0-10 ..." prompt stack up against traditional, battle-tested sentiment analysis tools?
Gemini suggests NLTK and spaCy
Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
#8[flagged]
- - Its' pronounced 'GNome'
Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
#9>>Use the tool below to explore various topics and the sentiments they evoke.
This is a cool phrase.
It is personally important as when I was asked in a panel interview @ -- They asked "what do you think Twitter is?
My response was "You're a global sentiment engine""
(There are a lot of conversations I'd love to have with the HN community with respect to our shared experiences, and weird history flipped-bits that exists in the minds of those who experienced that...
like threads of how linux came, or how xml was born through things I touched in a forrest gump way - and how there are so many stories from so many.
Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
#10[flagged]
I got a fairly good chuckle seeing Gnome as the most divisive topic, too.