A5056150936- Sentiment Analysis and Opinion Mining
- Complex Network Analysis Techniques
- Topic Modeling
- Text and Document Classification Technologies
- Advanced Text Analysis Techniques
- Opinion Dynamics and Social Influence
- Spam and Phishing Detection
- Misinformation and Its Impacts
- Neural Networks and Applications
- Chaos control and synchronization
- Advanced Algorithms and Applications
- Transportation Planning and Optimization
- Medicinal Plant Pharmacodynamics Research
- Anomaly Detection Techniques and Applications
- Metabolism, Diabetes, and Cancer
- Cholesterol and Lipid Metabolism
- Human Mobility and Location-Based Analysis
- Traffic Prediction and Management Techniques
- Time Series Analysis and Forecasting
Jiangxi University of Finance and Economics
2025
Zhejiang Lab
2023-2025
Hohai University
2024
Xian Yang Central Hospital
2020
First People's Hospital of Jingzhou
2020
Harbin Engineering University
2017-2020
Heilongjiang University of Science and Technology
2017-2020
Aspect-based sentiment analysis (ABSA) through joint task learning aims to simultaneously identify aspect terms and predict their polarities. However, existing methods face two major challenges: (1) Most studies focus on the polarity classification task, ignoring critical role of term extraction, leading insufficient performance in capturing aspect-related information; (2) typically model tasks independently, failing effectively share underlying features semantic information, which weakens...
Analyzing massive user-generated microblogs is very crucial in many fields, attracting researchers to study. However, it challenging process such noisy and short microblogs. Most prior works only use texts identify sentiment polarity assume that are independent identically distributed, which ignore networked data. Therefore, their performance not usually satisfactory. Inspired by two sociological theories (sentimental consistency emotional contagion), this paper, we propose a new method...
Sentiment analysis is widely studied to extract opinions from user generated content (UGC), and various methods have been proposed in recent literature. However, these are likely introduce sentiment bias, the classification results tend be positive or negative, especially for lexicon-based methods. The existence of bias leads poor performance analysis. To deal with this problem, we propose a novel processing strategy which can applied method. Weight threshold parameters learned small...
This work tackles the seldom discussed task of predicting chaotic time series generated by dynamic systems with evolving parameters. Representative produced different system dimensions are introduced a critical parameter linearly depending on time. The character qualitatively studied phase portraits. We assess predictability fuzzy neural network (FNN) architectures several series. Experiments illustrate that FNN models can generally better approximate comparing to autoregression method as...
Neuronal insulin resistance is implicated in neurodegenerative diseases. Icariin has been reported to improve skeletal muscle cells and restore impaired hypothalamic signaling the rats with chronic unpredictable mild stress. In addition, icariin can exert neuroprotective effects mouse models of However, molecular mechanisms by which affects neuronal are poorly understood. present study, amyloid-β (Aβ) was used induce human neuroblastoma SK-N-MC cells. Insulin sensitivity evaluated measuring...
Accurate and timely passenger flow prediction is important for the successful deployment of rail transit intelligent operation. The Sparrow Search Algorithm (SSA) has been applied to parameter optimization a Long-Short-Term Memory (LSTM) model. To solve inherent weaknesses SSA, this paper proposes an improved SSA-LSTM model with strategies including Tent Map Levy Flight practice short-term boarding at stations. Aimed four stations in Nanjing, China, it found that day week rainfall are...
Key nodes detection is conducive to the information promotion and public opinion monitoring. Traditional works mainly focus on affecting breadth of diffusion. However, there are several concentrate depth Breadth dictates number receiving in one-hop propagation. Depth implies length retweeting cascade social circles getting information. as important breadth, for which contribute diffusion can promote society propagation (SP). If we have a good control these nodes, will ignite community...
As online social networks provide people with a popular and convenient platform to express opinions, microblog sentiment analysis has become hot research area. Currently, relations between microblogs are extracted integrated into content-based models. However, these methods take all links consideration, ignoring that some noisy neighbor ambiguous semantically, resulting in the insufficiency of analysis. To deal this problem, we propose method introduces sparse modeling contexts tries balance...