Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023

outerbounds.com

Post reply on HN
Print view View original

11–20 of 79 posts

Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023

#14

Post by elashri »

> It is worth clarifying though that Hacker News does not hate International Students, but the posts related to them tend to be overwhelmingly negative, reflecting the community’s sympathy for the challenges faced by those studying abroad.

I was horrified when I read international students as one of top on the hate list. Although I saw a couple of comments attributed their cities housing crises on international students and thought that this sentiment is wide supported.

Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023

#15

Post by MBCook »

samstave wrote: post #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 ex…

Speaking of Twitter, it would be very neat to be able to see a graph of sentiment over time if you select a term.

You could watch Twitter go from being a niche little new thing to popular to "twitter is trash" too popular to increasingly divisive to the purchase and rename to X to today.

Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023

#17

Post by synicalx »

> Hate : Torture

Great work folks, glad we can all agree on that one.

Interesting that they used an LLM for this. I mean it makes sense and the data seems to pass the pub test but I, in my ignorance, would not have assumed that a language model would be well suited for number crunching.

Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023

#18

Post by antihipocrat »

tantalor wrote: post #7

Is 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 https://www.nltk.org/ https://spacy.io/

I'm wondering how their LLM parsing 250 mil words in 9 hours compares with performance of traditional sentiment analysis.

Also, many exisiting sentiment analysis tools have a lot of research behind them that can be referenced when interpreting the results (known confounds etc). I don't think there is yet an equivalent for the LLM approach

Re: LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023

#19

Post by silisili »

synicalx wrote: post #17

> Hate : Torture Great work folks, glad we can all agree on that one. Interesting that they used an LLM for this. I mean it makes sense and the data seems to pass the pub test but I, in my ignorance, would not have assumed that a language model would be well suited for number crunching.

Seems we mostly agree on hating Atlassian, too, so it's working as intended.
Post reply on HN