OPO-FCM: A Computational Affection Based OCC-PAD-OCEAN Federation Cognitive Modeling Approach

Liu, Feng; Wang, Han-Yang; Shen, Siyuan; Jia, Xun; Hu, Jingyi; Zhang, Jiahao; Wang, Xi-Yi; Lei, Ying; Zhou, Aimin; Qi, Jiayin; Li, Zhibin

doi:10.1109/tcss.2022.3199119

Cited by 12 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…gesture emotion recognition [5], multimodal emotion recognition [6] [7] and some personality recognition [8] based on dynamic expression recognition [9] and other related technologies [10]. As the research of skeletonbased action recognition is becoming more and more popular, its robustness in practical application scenarios has attracted extensive attention and exploration [11,12,13].…”

Section: Introductionmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune" and "pre-train, prompt" paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on graphs is still limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template, but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt. CCS CONCEPTS• Computing methodologies → Learning latent representations; • Information systems → Data mining.

show abstract

Section: Introductionmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

show abstract

“…Due to the influence of the Hawthorne effect and the idea of catering to social expectations, measurement errors would inevitably occur. Therefore, we use the facial emotion detection method based on deep learning to directly identify the emotions of the subjects in the experiment, providing more objectivity and accuracy of emotion detection [23] . We refer to and apply the machine learning method for Facial Expression Recognition (FER) [24] .…”

Section: Measures and Methodsmentioning

confidence: 99%

Emotional Mechanisms in Supervisor-Student Relationship: Evidence from Machine Learning and Investigation

Liu

et al. 2023

J. Soc. Comput.

Self Cite

View full text Add to dashboard Cite

How to cultivate innovative talents has become an important educational issue nowadays. In China's long-term mentorship education environment, supervisor-student relationship often affects students' creativity.From the perspective of students' psychology, we explore the influence mechanism of supervisor-student relationship on creativity by machine learning and questionnaire survey. In Study 1, based on video interviews with 16 postgraduate students, we use the machine learning method to analyze the emotional states exhibited by the postgraduate students in the videos when associating them with the supervisor-student interaction scenario, finding that students have negative emotions in bad supervisor-student relationship.Subsequently, we further explore the impact of supervisor-student relationship on postgraduate students' development in supervisor-student interaction scenarios at the affective level. In Study 2, a questionnaire survey is conducted to explore the relationship between relevant variables, finding that a good supervisorstudent relationship can significantly reduce power stereotype threat, decrease emotional labor surface behaviors, and promote creativity expression. The above results theoretically reveal the internal psychological processes by which supervisor-student relationship affects creativity, and have important implications for reducing emotional labor and enhancing creativity expression of postgraduate students.

show abstract

“…Compared with general verbal or pictural stimulation, virtual reality (VR) technology is more effective to induce emotions for diagnosis [ 71 ]. Li, ZB et al [ 72 ] constructed a computational affection-based OCC-PAD-OCEAN federation cognitive modelling (OPO-FCM), which can capture expression features by training a deep neural network, map expression features to the PAD emotion space by the established expression–emotion space mapping connection, and complete the mapping of the average emotion during a period. Liu, TT et al [ 73 ] found that the integration of AI in the research of emotions of loneliness, depression, and anxiety (EMO-LDA) research is a promising direction for addressing mental health.…”

Section: Treatmentmentioning

confidence: 99%