Dr Daniel Angus, The University of Queensland, Australia - Computational Discourse Analysis
Discursis is a new communication analytics technology that allows a user to objectively analyse many text based communications including conversations, web forums, training scenarios, and many more. Discursis automatically processes transcribed text to show participant interactions around specific topics and over the full time-course of the conversation. Discursis can assist practitioners in understanding the structure, information content, and inter-speaker relationships that are present within input data. Discursis also provides quantitative measures of key metrics, such as topic introduction; topic consistency; and topic novelty. In this talk Dr Angus did a showcase on recent findings from the application of Discursis to doctor/patient consultations, and conversations with persons with language impairments.
Dr Daniel Angus is a Lecturer with the University of Queensland, Australia, who has spent the last three years working on a large interdisciplinary ARC project called Thinking Systems. In 2012, a UQ Vice-Chancellor's Strategic Initiative grant sees Dr Angus collaborating between the School of Journalism and Communication and School of Information Technology and Electrical Engineering. Dr Angus’s research explores how conceptual information is processed and stored by mammals and how this can inspire the development of conceptual mapping tools. An outcome of this research is the Discursis text analytic tool which is a useful way to visualise and obtain metrics from conversation transcripts. Dr Angus has previously worked with the Complex Systems Laboratory at Swinburne University, Melbourne. There he completed his PhD thesis in Ant Colony Optimisation, a group of algorithms inspired by the foraging behaviour of Argentine ants that are useful for finding solutions to complex engineering problems.
The seminar was hosted by Dr Alex Gillespie.