Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Accept all cookies Reject all non-essential cookies Find out more

Algorithms for Narrative Generation on Social Media

Social media symbols

PI: Pete Grindrod

Department: Mathematical Institute

Citizens are increasingly relying upon social media to source and broadcast information about events.

The algorithmic toolset developed by Prof Grindrod’s group will support the monitoring of social media for events occurring in the public sphere, particularly in public spaces. By accessing “real-time” narratives created by spontaneous, changing groups of people (“crowds”), the tools will provide a targeted conduit for information analysis, decision making and advice. This exploits the spontaneously generated social media data resources in real-time to create a time-stamped unfolding narrative.

This algorithmic approach to narrative generation offers a novel and state-of-the-art method to understanding events as they unfold and the technology developed in this project will be of interest to a wide number of SMEs across a number of sectors (including defence, marketing, and politics). Through collaborator Dr Dave Sloggett (Behavioural Dynamics Institute) Prof Grindrod is already in talks with police forces across the UK who have identified the need for such a technology during marauding terrorist attacks in public spaces. During these attacks there is often great confusion as to the number and location of attackers as well as of any civilians who may be at risk. There is however often a plethora of images and statuses posted on social media which provide valuable intelligence for the first-responders (police, medics, and fire service). By working with two SMEs with the relevant technical expertise (Bloom Agency and CountingLab), Prof Grindrod’s team will produce a prototype implementation of their algorithms which will have demonstrable social benefit (saving lives) and will also showcase the project for other potential end users. In addition to this, other EPSRC funded research from the University of Bath will be incorporated in human-computer interaction to understand the best ways to communicate the dynamic narrative.

Related themes

Technology Fund
Technology Fund