|
Language Use in Written Dialog: Studying the Enron Corpus| old_uid | 10129 |
|---|
| title | Language Use in Written Dialog: Studying the Enron Corpus |
|---|
| start_date | 2015/11/03 |
|---|
| schedule | 11h30 |
|---|
| online | no |
|---|
| summary | While there have been many studies based on the Enron corpus,
surprisingly few have treated the data as what it is: written dialog. I
will present a series of studies performed at Columbia University whose
aim is to understand how linguistic choices in dialog are affected by
various aspects of the communicative setting, such as power, gender, and
the underlying social network. Specifically, we have investigated how
power relations affect linguistic choices, both lexical choices and
choices in terms of dialog acts. We see pervasive differences between
language use by people in power and people without power, which allows
us to predict who has power in a dialog. We have asked how this
power-related behavior changes when we incorporate the gender of the
discourse participants in the analysis. We have found profound
differences in language use between men and women in power, and also in
female and non-female gender environments (the gender environment
reflects the gender of all discourse participants). We are investigating
how the social networks that pre-exist a particular dialog relate to
power relations. We find that when we take the content of emails into
account, we can make better predictions about power relations than if we
only use meta-data (as has often been done in the literature). Finally,
I will report on ongoing work to distinguish personal email from
professional email. We find that the social network helps us find personal email. |
|---|
| responsibles | Grau |
|---|
| |
|