I have a question relating to my student research project in data- & textmining.
In this project, I want to figure out, how tweets and other comments in social media can "predict" box-office sales.
So I have tweets/comments on the one hand and the box-office sales on the other.
I want to classify these comments as "positive", "negative" and "neutral" according to the sentiment.
Can I do this by simply adding an additional column and entering the particular keyword in it?
And how can I cluster this data best, so that I can see clearly, for example if some positive comments
can be associated with high box-office sales?
I hope this is comprehensible to you. I'm quite a newbie on this..
Thank you for your help :-)
there are two whitepapers on the KNIME web site exactly on this topic.
These are two parts of the study "Usable Customer Intelligence from Media Data".
The first one shows how to combine sentiment with the data you already have and second shows how to cluster them.
Let me know if you have any questions on the whitepapers. My email address is on the first page of both whitepapers.
Oh, thank you very much for your help :-)
I'll check it out!