StackOverflow2013

Note that there are some explanatory texts on larger screens.

plurals

PO
text
Body
copied!<p>I don't think there's anything particularly <strong><em>wrong</em></strong> with your algorithm, it's a fairly straightforward and practical way to go, but there are a lot of situations where it will get make mistakes.</p> <ol> <li><p><strong>Ambiguous sentiment words</strong> - "This product works terribly" vs. "This product is terribly good"</p></li> <li><p><strong>Missed negations</strong> - "I would never in a millions years say that this product is worth buying"</p></li> <li><p><strong>Quoted/Indirect text</strong> - "My dad says this product is terrible, but I disagree"</p></li> <li><p><strong>Comparisons</strong> - "This product is about as useful as a hole in the head"</p></li> <li><p><strong>Anything subtle</strong> - "This product is ugly, slow and uninspiring, but it's the only thing on the market that does the job"</p></li> </ol> <p>I'm using product reviews for examples instead of news stories, but you get the idea. In fact, news articles are probably harder because they will often try to show both sides of an argument and tend to use a certain style to convey a point. The final example is quite common in opinion pieces, for example.</p> <p>As far as NLP helping you with any of this, <a href="http://en.wikipedia.org/wiki/Word_sense_disambiguation" rel="noreferrer">word sense disambiguation</a> (or even just <a href="http://en.wikipedia.org/wiki/Part-of-speech_tagging" rel="noreferrer">part-of-speech tagging</a>) may help with (1), <a href="http://en.wikipedia.org/wiki/Statistical_parsing" rel="noreferrer">syntactic parsing</a> might help with the long range dependencies in (2), some kind of <a href="http://en.wikipedia.org/wiki/Shallow_parsing" rel="noreferrer">chunking</a> might help with (3). It's all research level work though, there's nothing that I know of that you can directly use. Issues (4) and (5) are a lot harder, I throw up my hands and give up at this point.</p> <p>I'd stick with the approach you have and look at the output carefully to see if it is doing what you want. Of course that then raises the issue of what you want you understand the definition of "sentiment" to be in the first place...</p>

Querying!

Guidance

An individual column

Larger individual text columns get their own page to allow for proper reading.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload