Show HN: Mental State of HN Users Before/After Lockdown
1–10 of 38 posts
Re: Show HN: Mental State of HN Users Before/After Lockdown
#2This is a really cool idea. Would be really interesting to run it through a sentiment analysis engine as well.
Re: Show HN: Mental State of HN Users Before/After Lockdown
#3You could probably use NRC Emotion Lexicon[1] to categorize the titles into different emotions and sort it like that, as well and give it some normalized emotional score/category for X. Then use logistic regression for Y being before/after lockdown or linear regression for Y being (current_date - lockdown_date). The linear regression will assume that things get linearly worse over time (it can be smoothed out better probably).
1: https://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm#:~....
Re: Show HN: Mental State of HN Users Before/After Lockdown
#4slightly OT and totally non scientific (just my gut feeling), but I have a feeling that HN became more polarized and negative/combative in recent months. I think I notice much more downvotes and flagging taking place than before. I wonder if this is also something that can be analyzed? (not sure HN exposes it, but in a way simpler than sentiment analysis, right?)
Re: Show HN: Mental State of HN Users Before/After Lockdown
#5You could probably use NRC Emotion Lexicon[1] to categorize the titles into different emotions and sort it like that, as well and give it some normalized emotional score/category for X. Then use logistic regression for Y being before/after lockdown or linear regression for Y being (current_date - lockdown_date). The linear regression will assume that things get linearly worse over time (it can be smoothed out better…
> You could probably use NRC Emotion Lexicon
Thanks and good idea! How does this compare to some pre-trained ML model for sentiments analysis?
> Then use logistic regression for Y being before/after lockdown ...
Just googled logistic regression but would love to hear some examples in this context to get a better grasp on this. Thanks!
Re: Show HN: Mental State of HN Users Before/After Lockdown
#6Wow, very interesting. Thanks for posting this, I really appreciate how clear and simple your notebook is. I had a sense that this sentiment had grown significantly, but I thought that perhaps it might be receding after a temporary spike. Perhaps that was too optimistic.
Re: Show HN: Mental State of HN Users Before/After Lockdown
#7For those only interested in the results:
> 40.0% more submissions with depression related keywords in the title after lockdown vs before
18% more comments on posts with depression related keywords in the title after lockdown vs before
9% more upvotes on posts with depression related keywords in the title after lockdown vs before
Re: Show HN: Mental State of HN Users Before/After Lockdown
#8Was there an uptick in show hn post?
Re: Show HN: Mental State of HN Users Before/After Lockdown
#9For those only interested in the results: > 40.0% more submissions with depression related keywords in the title after lockdown vs before 18% more comments on posts with depression related keywords in the title after lockdown vs before 9% more upvotes on posts with depression related keywords in the title after lockdown vs before
The way this is worded, it seems like the author simply counted the number of posts with negative words in them. And then compared the number to last year.
In that case, the increase could be explained by more posts on HN overall. Without any change in "mental state".
Lets have a look into the calculations ...
Hmm.. as far as I can see, the calculations indeed do not take overall change in posts into account.
Re: Show HN: Mental State of HN Users Before/After Lockdown
#10slightly OT and totally non scientific (just my gut feeling), but I have a feeling that HN became more polarized and negative/combative in recent months. I think I notice much more downvotes and flagging taking place than before. I wonder if this is also something that can be analyzed? (not sure HN exposes it, but in a way simpler than sentiment analysis, right?)
Totally non scientific (just my gut feeling), but I have a feeling that this is because the number of non-technical submissions has increased dramatically.