One of the big issues in procuring personality insights from linguistic data is that the two major software systems that do so, LIWC and IBM Watson, are not open source. We have little, if any, idea what goes on behind-the-scenes. On top of that, those two systems are not (entirely) free.
This is my attempt to implement a system like LIWC or IBM Watson that can predict the personality aspects of the author of a piece of writing.