scholarly journals Event-related brain responses to emotional words, pictures, and faces – a cross-domain comparison

2014 ◽  
Vol 5 ◽  
Author(s):  
Mareike Bayer ◽  
Annekathrin Schacht
2021 ◽  
pp. 016555152110123
Author(s):  
Yueting Lei ◽  
Yanting Li

The sentiment classification aims to learn sentiment features from the annotated corpus and automatically predict the sentiment polarity of new sentiment text. However, people have different ways of expressing feelings in different domains. Thus, there are important differences in the characteristics of sentimental distribution across different domains. At the same time, in certain specific domains, due to the high cost of corpus collection, there is no annotated corpus available for the classification of sentiment. Therefore, it is necessary to leverage or reuse existing annotated corpus for training. In this article, we proposed a new algorithm for extracting central sentiment sentences in product reviews, and improved the pre-trained language model Bidirectional Encoder Representations from Transformers (BERT) to achieve the domain transfer for cross-domain sentiment classification. We used various pre-training language models to prove the effectiveness of the newly proposed joint algorithm for text-ranking and emotional words extraction, and utilised Amazon product reviews data set to demonstrate the effectiveness of our proposed domain-transfer framework. The experimental results of 12 different cross-domain pairs showed that the new cross-domain classification method was significantly better than several popular cross-domain sentiment classification methods.


PLoS ONE ◽  
2013 ◽  
Vol 8 (8) ◽  
pp. e70788 ◽  
Author(s):  
Kati Keuper ◽  
Pienie Zwitserlood ◽  
Maimu A. Rehbein ◽  
Annuschka S. Eden ◽  
Inga Laeger ◽  
...  

2010 ◽  
Vol 24 (2) ◽  
pp. 76-82 ◽  
Author(s):  
Martin M. Monti ◽  
Adrian M. Owen

Recent evidence has suggested that functional neuroimaging may play a crucial role in assessing residual cognition and awareness in brain injury survivors. In particular, brain insults that compromise the patient’s ability to produce motor output may render standard clinical testing ineffective. Indeed, if patients were aware but unable to signal so via motor behavior, they would be impossible to distinguish, at the bedside, from vegetative patients. Considering the alarming rate with which minimally conscious patients are misdiagnosed as vegetative, and the severe medical, legal, and ethical implications of such decisions, novel tools are urgently required to complement current clinical-assessment protocols. Functional neuroimaging may be particularly suited to this aim by providing a window on brain function without requiring patients to produce any motor output. Specifically, the possibility of detecting signs of willful behavior by directly observing brain activity (i.e., “brain behavior”), rather than motoric output, allows this approach to reach beyond what is observable at the bedside with standard clinical assessments. In addition, several neuroimaging studies have already highlighted neuroimaging protocols that can distinguish automatic brain responses from willful brain activity, making it possible to employ willful brain activations as an index of awareness. Certainly, neuroimaging in patient populations faces some theoretical and experimental difficulties, but willful, task-dependent, brain activation may be the only way to discriminate the conscious, but immobile, patient from the unconscious one.


2014 ◽  
Vol 35 (3) ◽  
pp. 137-143 ◽  
Author(s):  
Lindsay M. Niccolai ◽  
Thomas Holtgraves

This research examined differences in the perception of emotion words as a function of individual differences in subclinical levels of depression and anxiety. Participants completed measures of depression and anxiety and performed a lexical decision task for words varying in affective valence (but equated for arousal) that were presented briefly to the right or left visual field. Participants with a lower level of depression demonstrated hemispheric asymmetry with a bias toward words presented to the left hemisphere, but participants with a higher level of depression displayed no hemispheric differences. Participants with a lower level of depression also demonstrated a bias toward positive words, a pattern that did not occur for participants with a higher level of depression. A similar pattern occurred for anxiety. Overall, this study demonstrates how variability in levels of depression and anxiety can influence the perception of emotion words, with patterns that are consistent with past research.


Sign in / Sign up

Export Citation Format

Share Document