There's a bunch of features we want to include in future releases. I can imagine a few summary points that would be interesting (net avg scores, deviation from overall HN scores, etc.) What did you have in mind for a summary?
And thanks for taking the time to give feedback, btw!
I'm not really sure what I'm looking at here. Could you put some sort of explanation for the y-axis? I haven't the foggiest what a sentiment score is, and nothing seems to really change when I put in Obama, Trump, Angular, or React.
We can definitely add some copy around that. The scores that we're using are normalized on [0, 1] and broken into three categories - positive, negative, and neutral. It's possible for something to be all positive or all negative, but most things are a mix. The relative differences between positive and negative sentiment are the most interesting. For example, if you search Obama, you'll note that in September '13 the average positive and negative sentiment trends cross. On average, sentiment expressed in comments on stories mentioning Obama were more negative than positive. They later return to being more positive than negative, but this is the sort of thing that's interesting to investigate. In this particular case there were a string of very negative stories involving the NSA [1], the assassination of U.S. citizens [2] and Obamacare [3].
In the case of React you'll note an overall trend of increasingly positive sentiment and less negative sentiment. Sometimes it's fun to figure out what the spikes were by searching on HN. The big positive spike on 20015-07-15 was [4], a Show HN with very positive reception.
Ah, so you have to pay more attention to how the positive and negative scores are interacting, and sort of disregard the neutral score, even though it looks much larger. That's nonintuitive (for me). Unless the neutral score serves some other purpose, you might consider removing it from the visualization.
Thanks for the suggestion, we very well might do so. The line does add something for the cases where a topic is becoming less neutral (stronger language is being used, either positive or negative) but it's unfortunate that the scales are quite different on the whole. We're going to work on making the system more intuitive and find better ways to highlight the most interesting trends.
You should try providing this service to the new York times or something like that to do sentiment analysis on their articles. Something very ambitious you could do is to do sentiment analysis on say the 100 most read news sites in the country, to see how the general American population feels about various subjects. Could help out politicians, think tanks.
We would love to add other datasets in the future and have plans to do so. That said, this is just a fun side project so we have to triage what data sources go in and when. NYT is high on that list.
In this post [0] you get the sentiment for one post. What did you enter into the search to get the results for one post? Is there way I could submit a HN post url and get back the current sentiment from your service? If so, this would be really cool in my project. Do you think that'd be possible? Thanks!
It's definitely possible but we're not updating real time at the moment...that will change soon. We can add endpoints to return the sentiment on a single story/collection of comments. Shoot me an e-mail (link in profile) and let me know what you need - hopefully we can accommodate.
11 comments
[ 2.8 ms ] story [ 37.3 ms ] thread- A summary of the sentiment would be a nice to have as well!
Cheers!
And thanks for taking the time to give feedback, btw!
In the case of React you'll note an overall trend of increasingly positive sentiment and less negative sentiment. Sometimes it's fun to figure out what the spikes were by searching on HN. The big positive spike on 20015-07-15 was [4], a Show HN with very positive reception.
[1]: https://news.ycombinator.com/item?id=6347790
[2]: https://news.ycombinator.com/item?id=6435963
[3]: https://news.ycombinator.com/item?id=6462339
[4]: https://news.ycombinator.com/item?id=9891989
edit: formatting
[0]: https://news.ycombinator.com/item?id=11191394