홈 › Papers

EEG Based Decoding of the Perception and Regulation of Taboo Words

2024-10-25 · Parisa Ahmadi Ghomroudi, Michele Scaltritti, Bianca Monachesi, Peera Wongupparaj, Remo Job, Alessandro Grecucci

In daily interactions, emotions are frequently conveyed and triggered through verbal exchanges. Sometimes, we must modulate our emotional reactions to align with societal norms. Among the emotional words, taboo words represent a specific category that has been poorly studied. One intriguing question is whether these word categories can be predicted from EEG responses with the use of machine learning methods. To address this question, Support Vector Machine (SVM) was applied to decode the word categories from Event Related Potential (ERP) in 40 native Italian speakers. 240 neutral, negative and taboo words were used to this aim. Results indicate that the SVM classifier successfully distinguished between the three-word categories, with significant differences in neural activity ascribed to the late positive potential mainly detected in the central-parietal-occipital and anterior right scalp areas in the time windows of 450-649 ms and 650-850 ms. These findings were in line with the established distribution pattern of the late positive potential. Intriguingly, the study also revealed that word categories were still detectable in the regulate condition. This study extends previous results on the domain of the cortical responses of taboo words, and how machine learning methods can be used to predict word categories from EEG responses.

📄 PDF Abstract BibTeX arXiv:2410.19953

Code (0)

등록된 구현이 없습니다.

Tasks

EEGERP

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness

2026-08-10 · Tadanobu Chuyo Kamijo, Ori Rottenstreich, Javier Conde, Gonzalo Martínez 외 hf

Large language model evaluations typically focus on performance under nominal conditions, creating an illusion of capability where models comfortably walk a narrow, highly optimized generation corridor. In real-world dep…

Linguistic Taboos and Euphemisms in Nepali

2020-07-27 · Nobal B. Niraula, Saurab Dulal, Diwa Koirala

Languages across the world have words, phrases, and behaviors -- the taboos -- that are avoided in public communication considering them as obscene or disturbing to the social, religious, and ethical values of society. H…

Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation

2024-01-12 · Jan Cegin, Branislav Pecher, Jakub Simko, Ivan Srba 외

The latest generative large language models (LLMs) have found their application in data augmentation tasks, where small numbers of text samples are LLM-paraphrased and then used to fine-tune downstream models. However, m…

Data Augmentation Diversity Text Augmentation

Detection of Slang Words in e-Data using semi-Supervised Learning

2015-11-19 · Alok Ranjan Pal, Diganta Saha

The proposed algorithmic approach deals with finding the sense of a word in an electronic data. Now a day,in different communication mediums like internet, mobile services etc. people use few words, which are slang in na…

Taboo Wordnet

2021-01-01 · EACL (GWC) 2021 1 · Francis Bond, Merrick Yeu Herng Choo

This paper describes the development of an online lexical resource to help detection systems regulate and curb the use of offensive words online. With the growing prevalence of social media platforms, many conversations …