Stance Recognition

Tackling Biases In or Using Generative AI

Dec 4, 2024

We've created the Touché23-ValueEval dataset, a large collection of over 9,300 arguments annotated with 54 human values, to help develop methods for analyzing the values that make arguments persuasive. Our dataset, which more than doubles the size of its predecessor, has already been used to achieve state-of-the-art results in identifying human values behind arguments, and has shown promising performance with large language models like Llama-2-7B.

May 1, 2024

We've developed a machine learning approach to automatically recognize the opinions of citizens in online public consultations, using three datasets to train a model that can classify stances on various topics. Our work experiments with different methods, including self-supervised learning, and makes several annotated datasets available for others to use. This work was used in the Touché shared task of CLEF 2023.

Apr 1, 2023

A new dataset for Stance Recognition using data from the Participatory Democracy platform of the Conference for the Future of Europe. This dataset contains highly-multilingual interactions, as the platform used Machine Translation, in the sense that users interacts in using their (different) native languages in the same thread.

Nov 1, 2022

A new dataset of 2,600 online debate comments has been created to improve stance classification models. Fine-tuning and semi-supervised learning can boost accuracy by 3.4% over a baseline model.

Jun 1, 2022