A long line of research in Natural Language Processing (NLP),
including our own, has addressed the task of identifying and
extracting information about opinions with the goal of determining
what people (and other entities) are thinking or feeling.  In this
talk, I'll present new research on argument mining, a relatively new
area of study in NLP that focuses less on extracting from text WHAT
people think or feel, but rather analyzing argumentative text to
understand WHY they do so.

Specifically, I will first present some of our new research on the
automatic analysis of informal, user-generated arguments in which we
aim to expose the intended underlying structure of the argument.
Next, we will examine the arguments on a public debate forum to
determine what makes one argument more convincing than another.  In
particular, recent studies in NLP have provided empirical evidence
that the language of the debaters and their patterns of interaction
play a key role in changing the mind of a reader/listener. On the
other hand, research in psychology has shown that prior beliefs can
affect our interpretation of an argument.  Using debate forum data, I
will present the results of our work to determine the relative roles
of language use vs. prior beliefs in the creation of persuasive
argumentative text.