News for hackers. Stuff that matters.
Re:Show HN: London Feels – Sentiment-analysis of Londoners T... by aw3c2 on Monday October 27, 2014 @08:00AM (#8514974)
Clicked through ~20 of them and the analysis was completely off in most cases.
Re:Show HN: London Feels – Sentiment-analysis of Londoners T... by robin_reala on Monday October 27, 2014 @08:20AM (#8515036)
Yep, although in some cases understandably. One tweet listed as ‘Not good’ had the text ‘Killed it! 🔫’ and a location given as a comedy club. I’m assuming someone had had a good gig, but I’m not surprised a classifier algorithm got that wrong.
Re:Show HN: London Feels – Sentiment-analysis of Londoners T... by _delirium on Monday October 27, 2014 @08:51AM (#8515133)
Some cases are just difficult, but the overall accuracy could probably be improved considerably if the sentiment analyzer were calibrated for the domain. AFINN (linked above) is calibrated from newspaper articles, which almost certainly have a different distribution of word/sentiment correlations than Tweets do. It's not hard for me to imagine that "killed" is a better predictor of negative sentiment when classifying news articles.
Re:Show HN: London Feels – Sentiment-analysis of Londoners T... by MrMattWright on Monday October 27, 2014 @08:55AM (#8515146)
Sentiment.js (which is what we used in devwax and I am guessing the same here) is just AFINN based Sentiment.https://www.npmjs.org/package/sentiment which you can customize. So in our case we added things like {"barreling": 2} etc. What would be better is a bigram/trigram based approach do you could score "Going Off" and "Killed It" etc, but I am not sure if there is a js library that does that?
Re:Show HN: London Feels – Sentiment-analysis of Londoners T... by chatmasta on Monday October 27, 2014 @08:24AM (#8515048)
Makes sense, since AFINN is just a tab-separated list of words and [-5, 5] valence scores. [1]

The impressive part of this for me is the visualization. Really nice.

http://www2.imm.dtu.dk/pubdb/views/publication_details.php?i...