Language innovation and change in on-line social networks

Language is fundamental to human communication - throughout the course of history language has constantly evolved. This can currently be seen in the changing forms of colloquial language in various on-line social networks (OSN's). These innovations in language are even appearing in every day life with the recent induction of 'lol' and 'ro' into modern dictionaries. Changes and varying forms of language pose challenges to both academics and people in business when attempting to assess and communicate with different communities. In this Ph.D, we aim to forecast online language change through the use of predictive and descriptive methodologies. Through using data sets mined from a number of OSNs, we aim to develop generalizable models and theories for assessing and predicting such language changes. We philosophically frame this work by drawing on structuration theory [11] which helps us structure our analysis of the dynamics of language (re)production - i.e. by the agent (user), the social structure and their interplay. We draw on stateof-the-art work and methods, including the development of neural nets to analyse language usage, along with network and community classification too uncover social structures within language. Preliminary results have identified statistically significant innovations usage across communities across a number of OSN's, this was done by operationalizing known linguistic models of innovation acceptance.