EEG Functional Connectivity Underlying Emotional Valance and Arousal Using Minimum Spanning Trees

Cao, Rui; Yan, Hao; Wang, Xin; Gao, Yuan; Shi, Huiyu; Huo, Shoujun; Wang, Bin; Guo, Hao; Xiang, Jie

doi:10.3389/fnins.2020.00355

Cited by 27 publications

(32 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, negative appeals remain highly featured in social advertising messages. This is attributed to the rich action tendency potential negative appeals hold [ 71 ], along with their ability to activate the brain more than other emotions [ 72 ]. Negative appeals have the ability to drive action without being liked first.…”

Section: Literature Reviewmentioning

confidence: 99%

Social Advertising Effectiveness in Driving Action: A Study of Positive, Negative and Coactive Appeals on Social Media

Yousef

Dietrich

Rundle‐Thiele

2021

IJERPH

View full text Add to dashboard Cite

Background: Social media offers a cost-effective and wide-reaching advertising platform for marketers. Objectively testing the effectiveness of social media advertising remains difficult due to a lack of guiding frameworks and applicable behavioral measures. This study examines advertising appeals’ effectiveness in driving engagement and actions on and beyond social media platforms. Method: In an experiment, positive, negative and coactive ads were shared on social media and promoted for a week. The three ads were controlled in an A/B testing experiment to ensure applicable comparison. Measures used included impressions, likes, shares and clicks following the multi-actor social media engagement framework. Data were extracted using Facebook ads manager and website data. Significance was tested through a series of chi-square tests. Results: The promoted ads reached over 21,000 users. Significant effect was found for appeal type on engagement and behavioral actions. The findings support the use of negative advertising appeals over positive and coactive appeals. Conclusion: Practically, in the charity and environment context, advertisers aiming to drive engagement on social media as well as behavioral actions beyond social media should consider negative advertising appeals. Theoretically, this study demonstrates the value of using the multi-actor social media engagement framework to test advertising appeal effectiveness. Further, this study proposes an extension to evaluate behavioral outcomes.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Social Advertising Effectiveness in Driving Action: A Study of Positive, Negative and Coactive Appeals on Social Media

Yousef

Dietrich

Rundle‐Thiele

2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…Since the average classification accuracy by selecting robust features is still lower than the participant-dependent models (Shu et al, 2018 ), researchers are also investigating other approaches such as functional brain connectivity patterns, domain adaptation, or hybrid methods. An example of cross-subject functional brain connectivity investigation is from Cao et al ( 2020 ), who studied the key information flow of the different parts of the brain with minimum spanning trees (MST). About domain adaption, the study by Chai et al ( 2016 ) presents several unsupervised domain adaptation techniques based on autoencoders for non-stationary EEG-based emotion recognition.…”

Section: Introductionmentioning

confidence: 99%

Cross-Subject EEG-Based Emotion Recognition Through Neural Networks With Stratified Normalization

et al. 2021

View full text Add to dashboard Cite

Due to a large number of potential applications, a good deal of effort has been recently made toward creating machine learning models that can recognize evoked emotions from one's physiological recordings. In particular, researchers are investigating the use of EEG as a low-cost, non-invasive method. However, the poor homogeneity of the EEG activity across participants hinders the implementation of such a system by a time-consuming calibration stage. In this study, we introduce a new participant-based feature normalization method, named stratified normalization, for training deep neural networks in the task of cross-subject emotion classification from EEG signals. The new method is able to subtract inter-participant variability while maintaining the emotion information in the data. We carried out our analysis on the SEED dataset, which contains 62-channel EEG recordings collected from 15 participants watching film clips. Results demonstrate that networks trained with stratified normalization significantly outperformed standard training with batch normalization. In addition, the highest model performance was achieved when extracting EEG features with the multitaper method, reaching a classification accuracy of 91.6% for two emotion categories (positive and negative) and 79.6% for three (also neutral). This analysis provides us with great insight into the potential benefits that stratified normalization can have when developing any cross-subject model based on EEG.

show abstract

“…We analyzed the multistability in a star network of Kuramoto-type phase oscillators in the presence of phase-difference-depended plasticity. A star-type network is the simplest network model that captures many of the typical properties of real-world networks; it can be considered an essential building block of neural networks 29 – 31 . The relative simplicity of the network allowed us to accurately estimate the number of possible asymptotic configurations which can be attained during the plastic evolution of the network.…”

Section: Discussionmentioning

confidence: 99%

“…In the star network, there is a center node (hub), and each of the other nodes (leaves) is connected only to this center but not between each other. The star network can be considered as an essential building block in real neural networks 29 – 31 ; it is the simplest network model that captures the sparse, clustering, small-world and other important properties of many real-world networks 32 – 34 . An advantage of a star network over more complex networks is that the number of dynamic variables associated with synaptic weights increases linearly, rather than quadratically, with the size of the network.…”

mentioning

confidence: 99%

Multistability in a star network of Kuramoto-type oscillators with synaptic plasticity

Ratas

Pyragas

Tass

2021

Sci Rep

View full text Add to dashboard Cite

We analyze multistability in a star-type network of phase oscillators with coupling weights governed by phase-difference-dependent plasticity. It is shown that a network with N leaves can evolve into $$2^N$$ 2 N various asymptotic states, characterized by different values of the coupling strength between the hub and the leaves. Starting from the simple case of two coupled oscillators, we develop an analytical approach based on two small parameters $$\varepsilon$$ ε and $$\mu$$ μ , where $$\varepsilon$$ ε is the ratio of the time scales of the phase variables and synaptic weights, and $$\mu$$ μ defines the sharpness of the plasticity boundary function. The limit $$\mu \rightarrow 0$$ μ → 0 corresponds to a hard boundary. The analytical results obtained on the model of two oscillators are generalized for multi-leaf star networks. Multistability with $$2^N$$ 2 N various asymptotic states is numerically demonstrated for one-, two-, three- and nine-leaf star-type networks.

show abstract

EEG Functional Connectivity Underlying Emotional Valance and Arousal Using Minimum Spanning Trees

Cited by 27 publications

References 40 publications

Social Advertising Effectiveness in Driving Action: A Study of Positive, Negative and Coactive Appeals on Social Media

Social Advertising Effectiveness in Driving Action: A Study of Positive, Negative and Coactive Appeals on Social Media

Cross-Subject EEG-Based Emotion Recognition Through Neural Networks With Stratified Normalization

Multistability in a star network of Kuramoto-type oscillators with synaptic plasticity

Contact Info

Product

Resources

About