It just means that you don't have insulting comments that it can find. Hover over titles with asterisks to better understand the context of your score and worst comment when you get your score, it just finds the "worst" one out of the bunch and if you don't have a bad comment then it just brings back something like that lol. :)
Great idea! I'll make another option that does exactly this. I think it's potentially a better way to think about it. Since I have to make an individual call for each comment it gets pretty hairy past 50 but I'm sure I can do it differently in the future. I tried to not put a limit on it at first and realized that @pg has something like 13,000 comments... lol. I could also just pull back every user's comments and run them through the model off line and update it every night. I just need a list of every user :)
Hello! I wrote this in on of the other threads about so I figured I would leave it here too.
A few things:
1. Thanks for posting my blog post (https://news.ycombinator.com/item?id=8517727) @chippy. :) The actual app ( haternews.co ) kept getting booted off HN... And now thanks @melling for posting it.
2. There have been a lot of interesting comments on the three (now four) threads on here. People pointed out some bugs and overall issues which I will be fixing (also, the site should not crash half as much now). This is just a fun side project I have been messing around with so I can get better at using data science in various applications. If you would like to help build it out for fun further let me know! Also, feel free to submit a bug or suggestion for an improvement if you really want to.(https://github.com/kevinmcalear/hater_news/issues)
3. I wanted to build the "hater score" for two reasons. First, to see how accurately I could build a model to measure insulting comments in the wild and second (if it's accurate), to see how people would react to seeing how positive or negative they usually are on Hacker news (or other social networks).
4. I wanted to make sure everyone knows that just because something is your "Worst Comment" doesn't mean it is negative. Most people have very low scores and most of your comments are not identified as insulting. (It would be over 50% if it is actually an insulting comment.) So most people on HN are not actually haters. I just had a more "hater" focused design just for fun. There are in fact actual haters though, if you look hard enough.
5. Something I found interesting is clicking the "Back In The Day" checkbox. It takes your 50 oldest comments and analyses them, instead of your 50 most recent.
6. Finally, if you're not sure why some comments are getting ranked higher than others, feel free to look at the training data I used (it's from a kaggle competition from a while back.) and read my blog post. If you don't want to here are additional features I used on top of standard bag-of-words (CountVectorizer):
* badwords_count – A count of bad words used in each comment.
* n_words – A count of words used in each comment.
* allcaps – A count of capital letters in each comment.
* allcaps_ratio – A count of capital letters in each comment / the total words used in each comment.
* bad_ratio – A count of bad words used in each comment / the total words used in each comment.
* exclamation – A count of "!" used in each comment.
* addressing – A count of "@" symbols used in each comment.
* spaces – A count of spaces used in each comment.
If you have suggestions on other features I could collect let me know! I'll also be building a way to get actual training data from HN itself and letting HN users determine if a comment is actually insulting or not so that the predictions constantly improve.
1. I wish everything was made from *fairy dust. How awesome would that be? :)
2. "Hate" is definitely hard to quantify. It's in fact quite difficult to map words to their intentions and get it right consistently (especially within a proper context). So difficult that people set up Kaggle competitions on exactly this. I actually got my "magical" training data from a competition that paid out $10k, which I explained in the article but here it is again:
They did a great job building a baseline training data set to evaluate several different models on. Which are all briefly explained or at least shown in code in the article. And what "hate" actually means here is the probability that a comment is considered insulting. The "hater score" is just an average of the most recent (or oldest, depending on your settings) comments' probabilities that they are insulting.
3. I read and looked at several different attempts to build something similar by various data scientists who were kind enough to share their findings, including a huge contributor to scikit-learn (https://github.com/amueller).
4. Taking out quoted text would be a great feature to add. I have about 5 or 6 new features I will probably add and see if the model works any better for it, thanks for the suggestion (another person was suggesting the same thing). :)
5. This was just to see how well "sprinkled algorithms" and magical coding works in the wild world of actual comments. I love learning and improving my knowledge base with actual experience so I figured why not build something and see what happens. :)
Yes and yes. :) The problem with the first one is I have to make an individual API call for each comment currently. If you go past 50 comments it starts to get slowwww. For example, I tried to pull back all of @pg's comments... Bad idea. It's like 13,000 of them. Check it:
https://hacker-news.firebaseio.com/v0/user/pg.json?print=pre...
1. Thanks for posting my blog post @chippy. :) The actual app ( haternews.co ) kept getting booted off HN...
2. There have been a lot of interesting comments on the three threads on here. People pointed out some bugs and overall issues which I will be fixing (also, the site should not crash half as much now). This is just a fun side project I have been messing around with so I can get better at using data science in various applications. If you would like to help build it out for fun further let me know! Also, feel free to submit a bug or suggestion for an improvement if you really want to.(https://github.com/kevinmcalear/hater_news/issues)
3. I wanted to build the "hater score" for two reasons. First, to see how accurately I could build a model to measure insulting comments in the wild and second (if it's accurate), to see how people would react to seeing how positive or negative they usually are on Hacker news (or other social networks).
4. I wanted to make sure everyone knows that just because something is your "Worst Comment" doesn't mean it is negative. Most people have very low scores and most of your comments are not identified as insulting. (It would be over 50% if it is actually an insulting comment.) So most people on HN are not actually haters. I just had a more "hater" focused design just for fun. There are in fact actual haters though, if you look hard enough.
5. Something I found interesting is clicking the "Back In The Day" checkbox. It takes your 50 oldest comments and analyses them, instead of your 50 most recent.
6. Finally, if you're not sure why some comments are getting ranked higher than others, feel free to look at the training data I used (it's from a kaggle competition from a while back.) and read my blog post. If you don't want to here are additional features I used on top of standard bag-of-words (CountVectorizer):
* badwords_count – A count of bad words used in each comment.
* n_words – A count of words used in each comment.
* allcaps – A count of capital letters in each comment.
* allcaps_ratio – A count of capital letters in each comment / the total words used in each comment.
* bad_ratio – A count of bad words used in each comment / the total words used in each comment.
* exclamation – A count of "!" used in each comment.
* addressing – A count of "@" symbols used in each comment.
* spaces – A count of spaces used in each comment.
If you have suggestions on other features I could collect let me know! I'll also be building a way to get actual training data from HN itself and letting HN users determine if a comment is actually insulting or not so that the predictions constantly improve.
