I'm working with Enron email data set, and try to get some psychological intentions about email marketing. I know that we can derive Sentimental analysis like emotions and mode and opinion mining like positive or negative through text data. what else can I do regarding human psychological intentions?
If you have a broad meaning of "intentions" in mind, you might be interested in research showing that a person's personality (in the sense of the "big five" psychological personality theory) can be inferred with remarkable accuracy from facebook likes. Original research showing this can be found here and here. Obviously, facebook likes are not the same as the textual information you work with, but it may be possible to infer certain likes and dislikes from the text.
DISCLAIMER : I'm not sure that this will be the answer you are looking for but I'll give a try.
According to Noam Chomsky
Language is a process of free creation; its laws and principles are fixed, but the manner in which the principles of generation are used is free and infinitely varied. Even the interpretation and use of words involves a process of free creation.
On one hand, data or text mining the combined large lexical data resources of linguistics and psychology suggests that the linguistic variable of 'word frequency' should be rehabilitated in psychology.
But you have to remember that, correlation does not imply causation.
This said, there is not much way to apply cross text mining with psychological intuition. In other words, use cases are not too many.
You can always try quantitative text analysis. It is a set of techniques stemming from the social sciences where either a human judge or a computer extracts semantic or grammatical relationships between words in order to find out the meaning or stylistic patterns of, usually, a casual personal text for the purpose of psychological profiling etc.
And by psychological profiling, I'm talking about offender profiling per example.
You can get more information upon that on the following websites :
- Criminal Investigative Research & Analysis
- http://www.psychlotron.org.uk/ article about criminal profiling.
- Here is a very intersting article about criminal profiling for beginners.
You can also try to take a look at this presentation by Harold Baize who talks about the intersection of text mining in the content analysis of psychology.
I hope this can help!
Actually, there isn't any limit of what you can do, if you have the right data.
I can remember a startup that was working on identify anxiety and suicidal thoughts on Tweets and Facebook status. First, they created a system where a user could raise a flag in case of a related Tweet/status about anxiety. They used those data to create a labeled dataset.
If you have labeled data and you know the psychological intentions from them, then you can just train a model to classify all the other dataset to one of these labels.
I am not aware if there is any public dataset with already labeled text, but you can either search for one or create your own.