Psychological Effect Computation of Courtroom Arguments: A Deep Learning Approach of EEG Signal Data
- Guanghua Law School, Zhejiang University,
Hangzhou 310008, China
{zhoushelley, jiaobaoqian}@ zju.edu.cn - School of Mechanical & Automotive Engineering, South China University of Technology,
Guangzhou 510641, China
yamingliu1@163.com - School of Management, Fudan University,
Shanghai 200433, China
{ouyanghanzhen, whdai}@fudan.edu.cn
Abstract
Previous studies have shown that the attorney’s speeches can exert significant impacts on the cognition and judgment of the jury in court arguments. However, the psychological effects induced by these speeches are intricately tied to subconscious brain states, making them challenging to accurately and comprehensively describe through subjective self-reports. This study aims to explore a neural reaction observation method for psychological effect analysis of the attorney’s speeches in courtroom scenarios. We utilized a corpus of courtroom arguments from legal movies and television series as source material. Participants’ psychological responses to these speeches were monitored using wearable electroencephalography (EEG) devices. Building upon this data, we employed a deep learning model based on Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to compute attention intensity, cognitive load, and emotional changes. Our test results demonstrate that this approach enables continuous and dynamic computation within courtroom argument contexts, providing a more accurate assessment of attorneys’ language skills.
Key words
Courtroom argument, attorney’ Speech, psychological effect, EEG, CNN-LSTM
Digital Object Identifier (DOI)
https://doi.org/10.2298/CSIS240122037Z
Publication information
Volume 21, Issue 4 (September 2024)
Year of Publication: 2024
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium
Full text
Available in PDF
Portable Document Format
How to cite
Zhou, X., Liu, Y., Jiao, B., Ouyang, H., Dai, W.: Psychological Effect Computation of Courtroom Arguments: A Deep Learning Approach of EEG Signal Data. Computer Science and Information Systems, Vol. 21, No. 4, 1321–1334. (2024), https://doi.org/10.2298/CSIS240122037Z