Faith in Humanity
AI
sentiment analysis
SHOW HN2013
How HN took it
1 positive, 5 neutral or asking, 2 mixed, 11 critical, out of 19 comments about the project. Thread score -0.45.
Performance: 0 for, 6 againstIdea: 0 for, 3 againstDesign: 1 for, 1 againstPrivacy: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Cool little weekend hack with a nice UI
From 1 comment
Cool little weekend hack. Love the UI. It's a refreshing take on sentiment analysis.
jimmybook on HN
Objections
Sentiment analysis misclassifies many tweets, including negated phrases
From 4 comments
Pretty neat, though it looks like the sentiment analysis could use some work. There are quite a lot of negative ones on the positive side. EDIT: Might be useful to expand this…
jstanley on HNI see some positive ones on the negative side too: "Batman no!! You can't lose your faith in humanity!" "You must not lose faith in humanity. [...] - Gandhi" I don't know how the…
ScottBurson on HNThey'll be cancelled out by false positives, eg 'I try to maintain my my faith in humanity. Sometimes I succeed.'
anigbrowl on HNSome are misclassified, such as "before I lose faith", or "else I will lost faith"
xijuan on HN
Measuring humanity via Twitter is not representative
From 2 comments
I can't help but lose a little faith in humanity when I see that faith in humanity is measured via Twitter.
joshrotenberg on HNTwitter is not the world or a meaningful representation of the world.
RyanIyengar on HN
Requests
Allow users to enter their own search terms
From 2 comments
Pretty neat, though it looks like the sentiment analysis could use some work. There are quite a lot of negative ones on the positive side. EDIT: Might be useful to expand this…
jstanley on HNHi! Creator here, yes the sentiment analysis could definitely use more work but we've found our naiive approach to be about 95% accurate which was good enough for our MVP.…
imkevinxu on HN
Let users correct sentiment labels to improve the algorithm
From 1 comment
Or allow page viewers to move something from one column to the other and have the back-end receive notification so that it modifies its sentiment algorithm automagically.
locopati on HN
Questions
What is the naive approach used for classification?
From 1 comment
Might I ask what exactly is the naive approach? Is it simply searching for keywords like "lose", "lost", etc?
fatjokes on HN