Sentiment Propensity Analysis of a Multimodal Chinese Corpus Using Fuzzy Logic DOI Creative Commons

Chunrong Chen

Applied Mathematics and Nonlinear Sciences, Год журнала: 2024, Номер 9(1)

Опубликована: Янв. 1, 2024

Abstract In the face of massive multimodal information, it has become one current research hotspots to categorize according its sentiment so as guide users find valuable information from a large amount data. Based on application fuzzy logic in analysis, this paper designs method analyze tendencies Chinese corpus. Firstly, text, audio, and video features corpus are extracted, dictionary is constructed. Then, double hesitant set used reduce intensity sentiment, value calculated. fusion lexicon, intuitionistic inference, comprehensive evaluation model obtain final tendency analysis results. The models constructed based different lexicons all converge after 4 epochs, indicating that strong feature learning ability. After combining accuracy model’s classification improves by 2.27%. Compared with other common models, precision rate, recall rate F1 paper’s improved 2.41%-6.57%, 2.36%-4.91% 2.38%-5.58%, respectively. result inclination positive 82.3%, difference only 1% average 83.3% user evaluation, better than plain text (80.8%), which proves can correctly complete review This provides new feasible approach for propensity sentiment.

Язык: Английский

A coupled framework for power load forecasting with Gaussian implicit spatio temporal block and attention mechanisms network DOI
Dezhi Liu, Xuan Lin,

Hanyang Liu

и другие.

Computers & Electrical Engineering, Год журнала: 2025, Номер 123, С. 110263 - 110263

Опубликована: Март 20, 2025

Язык: Английский

Процитировано

2
Ensemble learning unlocking point load forecasting accuracy: A novel framework based on two-stage data preprocessing and improved multi-objective optimisation strategy DOI
Jingmin Luan,

Q. Li,

Yuyan Qiu

и другие.

Computers & Electrical Engineering, Год журнала: 2025, Номер 124, С. 110282 - 110282

Опубликована: Апрель 5, 2025

Язык: Английский

Процитировано

1
Generalization of neural network for manipulator inverse dynamics model learning DOI
Wenhui Huang,

Lin Yunhan,

Jie Chen

и другие.

Applied Intelligence, Год журнала: 2025, Номер 55(7)

Опубликована: Апрель 17, 2025

Язык: Английский

Процитировано

0
An Improved Short-Term Electricity Load Forecasting Method: The VMD–KPCA–xLSTM–Informer Model DOI Creative Commons

Jiaxing You,

Huafeng Cai,

Dongxiao Shi

и другие.

Energies, Год журнала: 2025, Номер 18(9), С. 2240 - 2240

Опубликована: Апрель 28, 2025

This paper proposes a hybrid forecasting method (VMD–KPCA–xLSTM–Informer) based on variational-mode decomposition (VMD), kernel principal component analysis (KPCA), extended long short-term memory network (xLSTM), and the Informer model. First, decomposes original power load data environmental parameter using VMD to capture their multi-scale characteristics. Next, KPCA extracts nonlinear features reduces dimensionality of decomposed modals eliminate redundant information while retaining key features. The xLSTM then models temporal dependencies enhance model’s capability prediction accuracy. Finally, model processes long-sequence improve efficiency. Experimental results demonstrate that VMD–KPCA–xLSTM–Informer achieves an average absolute percentage error (MAPE) as low 2.432% coefficient determination (R2) 0.9532 dataset I, while, II, it attains MAPE 4.940% R2 0.8897. These confirm significantly improves accuracy stability forecasting, providing robust support for system optimization.

Язык: Английский

Процитировано

0
Sentiment Propensity Analysis of a Multimodal Chinese Corpus Using Fuzzy Logic DOI Creative Commons

Chunrong Chen

Applied Mathematics and Nonlinear Sciences, Год журнала: 2024, Номер 9(1)

Опубликована: Янв. 1, 2024

Abstract In the face of massive multimodal information, it has become one current research hotspots to categorize according its sentiment so as guide users find valuable information from a large amount data. Based on application fuzzy logic in analysis, this paper designs method analyze tendencies Chinese corpus. Firstly, text, audio, and video features corpus are extracted, dictionary is constructed. Then, double hesitant set used reduce intensity sentiment, value calculated. fusion lexicon, intuitionistic inference, comprehensive evaluation model obtain final tendency analysis results. The models constructed based different lexicons all converge after 4 epochs, indicating that strong feature learning ability. After combining accuracy model’s classification improves by 2.27%. Compared with other common models, precision rate, recall rate F1 paper’s improved 2.41%-6.57%, 2.36%-4.91% 2.38%-5.58%, respectively. result inclination positive 82.3%, difference only 1% average 83.3% user evaluation, better than plain text (80.8%), which proves can correctly complete review This provides new feasible approach for propensity sentiment.

Язык: Английский

Процитировано

0