I just analysed my entire whatsapp history and either sentiment analysis doesn't work or I'm fucking obtuse.
-
-
Replying to @GwilymLockwood
but seriously, sentiment analysis: in "debt of gratitude", context doesn't overwrite sad and negative coding. How do we use it properly?
1 reply 0 retweets 1 like -
Replying to @GwilymLockwood
Are there any full sentence/phrase level R packages rather than tidytext or syuzhet? Is this where people get into LSA?
1 reply 0 retweets 1 like -
-
Replying to @o_guest
good resources for how to get started? I'm an R person. At this point I just want it to not misinterpret simple text messages...
1 reply 0 retweets 0 likes -
Replying to @GwilymLockwood
I'm not an R person altho I understand R enough to code in it when I have to. I Googled it though: https://cran.r-project.org/web/packages/topicmodels/vignettes/topicmodels.pdf …
1 reply 0 retweets 0 likes -
Replying to @o_guest @GwilymLockwood
If u need conceptual intro to topic modelling I know a couple. Could u tell me a little more on why/what you want to do?
1 reply 0 retweets 0 likes -
Replying to @o_guest
thanks, I'll give that a read. I was reading this article on analysing Trump's twitter feed... http://varianceexplained.org/r/trump-tweets/
2 replies 0 retweets 0 likes
oh yeah I speed-read that when it came out haha
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.