Centre for Climate Communication and Data Science

Latest News

Read more...
Card image cap
C3DS AI powers new CCDH study on climate misinformation

Created on Jan. 16, 2024

A new report released by the Center for Countering Digital Hate (CCDH) uses an AI model developed by C3DS researchers to study misinformation on social media. The model was originally developed by Travis Coan, Mirjam Nanko (C3DS), Constantine Boussalis (Trinity College Dublin), and John Cook (University of Melbourne). The report, entitled "The New Climate Denial", documents a shift in towards undermining climate solutions.

Read More
Card image cap
C3DS researchers win knowledge exchange award

Created on Oct. 26, 2023

C3DS Deputy Director Chico Camargo and Research Associate Ranadheer Malla won Bright Futures Award for Early Career Research Impact at the University of Exeter Knowledge Exchange Awards for their “YouTube Regrets Project”. Chico and Ranadheer partnered with the Mozilla Foundation to develop a pioneering set of projects designed to scrutinize and gather evidence on the harmful and dangerous nature of YouTube recommendations.

Read More
Card image cap
C3DS AI powers new CCDH study on climate misinformation

Created on Jan. 16, 2024

A new report released by the Center for Countering Digital Hate (CCDH) uses an AI model developed by C3DS researchers to study misinformation on social media. The model was originally developed by Travis Coan, Mirjam Nanko (C3DS), Constantine Boussalis (Trinity College Dublin), and John Cook (University of Melbourne). The report, entitled "The New Climate Denial", documents a shift in towards undermining climate solutions.

Read More
Card image cap
C3DS researchers win knowledge exchange award

Created on Oct. 26, 2023

C3DS Deputy Director Chico Camargo and Research Associate Ranadheer Malla won Bright Futures Award for Early Career Research Impact at the University of Exeter Knowledge Exchange Awards for their “YouTube Regrets Project”. Chico and Ranadheer partnered with the Mozilla Foundation to develop a pioneering set of projects designed to scrutinize and gather evidence on the harmful and dangerous nature of YouTube recommendations.

Read More
Card image cap
Prof. O’Neil leads workshop on ‘Seeing the city through a climate lens’

Created on Sept. 8, 2023

Prof. O’Neil, together with WellImage CIC founder, photographer Vanessa Miles, ran a session on ‘Seeing the city through a climate lens’ as part of the British Science Festival. The session included a seminar and guided photography walk through Exeter city centre. Participants were challenged to view the city in a new way, and to create photographs which might re-envision how we might cope, adapt, and flourish in a climate-changed future.

Read More

Latest Research

Read more...
Card image cap
C3DS researchers introduce "Dynamic Few Shot Learning"

Feb. 6, 2024

This study contrasts the performance of state-of-the-art closed-source Large Language Models (LLMs) with their open-source counterparts across 10 multi-class classification tasks critical to social science research. We introduce dynamic few-shot learning, an enhancement to static few-shot learning, that leverages semantic similarity to dynamically choose contextually relevant examples from a pre-defined corpus for improved prompt engineering.

Read More
Card image cap
New research examines fossil fuel advertising on Facebook

Nov. 29, 2023

C3DS researcher, Ben Dennes, coauthored Section 3 on the "Fossil Fuel Lobby" in Climate Action Against Disinformation's (CAAD) recent COP28 Pre-summit Report. Ben developed software to collect and analyse data on fossil fuel advertising on Facebook. The report identifies 13 entities who posted 2,562 ads in the run up to COP28, with a total associated spend of $4.13 million-$5.21 million.

Read More
Card image cap
C3DS researchers introduce "Dynamic Few Shot Learning"

Feb. 6, 2024

This study contrasts the performance of state-of-the-art closed-source Large Language Models (LLMs) with their open-source counterparts across 10 multi-class classification tasks critical to social science research. We introduce dynamic few-shot learning, an enhancement to static few-shot learning, that leverages semantic similarity to dynamically choose contextually relevant examples from a pre-defined corpus for improved prompt engineering.

Read More
Card image cap
New research examines fossil fuel advertising on Facebook

Nov. 29, 2023

C3DS researcher, Ben Dennes, coauthored Section 3 on the "Fossil Fuel Lobby" in Climate Action Against Disinformation's (CAAD) recent COP28 Pre-summit Report. Ben developed software to collect and analyse data on fossil fuel advertising on Facebook. The report identifies 13 entities who posted 2,562 ads in the run up to COP28, with a total associated spend of $4.13 million-$5.21 million.

Read More
Card image cap
Research reveals the social media "echo" in climate communication

March 29, 2023

Online discourse covers a wide range of topics and many actors tailor their content to impact online discussions through carefully crafted messages and targeted campaigns. Yet the scale and diversity of online media content make it difficult to evaluate the impact of a particular message. In this paper, we present a new technique that leverages semantic similarity to quantify the change in the discussion after a particular message has been published.

Read More

Working with C3DS

If you are an organisation that could benefit from applying data science and/or social science methods to measure, monitor, and evaluate the impact of your strategic communication, please get in touch

Contact

Email the Centre team at c3ds@exeter.ac.uk for more information or to set up a meeting