A5109088889- Sentiment Analysis and Opinion Mining
- Advanced Text Analysis Techniques
- Tactile and Sensory Interactions
- Text and Document Classification Technologies
- Natural Language Processing Techniques
- Semantic Web and Ontologies
- Digital Accessibility for Disabilities
- Technology Adoption and User Behaviour
- Advanced Measurement and Detection Methods
- Complex Network Analysis Techniques
- Public Relations and Crisis Communication
- Topic Modeling
- Speech and Audio Processing
- Web Data Mining and Analysis
- Face recognition and analysis
- Advanced MRI Techniques and Applications
- Data Visualization and Analytics
- Software Engineering Research
- Opinion Dynamics and Social Influence
- Time Series Analysis and Forecasting
- Geographic Information Systems Studies
- Stock Market Forecasting Methods
- Interactive and Immersive Displays
- Software System Performance and Reliability
- Music and Audio Processing
Sichuan Tourism University
2022-2024
Nanjing University of Science and Technology
2007-2024
Philips (China)
2024
United Imaging Healthcare (China)
2023
Chongqing University of Posts and Telecommunications
2022
Shandong Institute of Commerce & Technology
2021
Nanjing University
2009-2020
Columbia University
2020
State Grid Corporation of China (China)
2019
Xi'an Shiyou University
2019
Background: Intravascular optical coherence tomography (IVOCT) enables detailed plaque characterisation in vivo, but visual assessment is time-consuming and subjective. Aims: This study aimed to develop validate an automatic framework for IVOCT using artificial intelligence (AI). Methods: pullbacks from five international centres were analysed a core lab, annotating basic components, inflammatory markers other structures. A deep convolutional network with encoding-decoding architecture...
During the COVID-19 emergency, people must face invisible threat of uncertain death and comply with social distancing other related protective measures. But networking sites (SNSs) like WeChat have emerged as alternative contexts where can maintain self obtain gratification, despite disclosure to others often being a challenging issue. To examine effect personality factors on people's self-disclosure SNSs, we develop model based time perspective theory socioemotional selectivity theory. We...
This paper presents the SIGHT (Summarizing Information GrapHics Textually) system that enables visually impaired users to gain access information graphics appear on a web page. The user interface is implemented as browser extension launched by keystroke combination. output of textual summary graphic, core content which hypothesized intended message graphic designer. then conveyed screen reading software (such JAWS). approach has benefits 1) not requiring any action part page developer, and...
Abstract The rapid development of technology allows people to obtain a large amount data, which contains important information and various noises. How useful knowledge from data is the most thing at this stage machine learning (ML). problem unbalanced classification currently an topic in field mining ML. At present, has attracted more attention relatively new challenge for academia industry. involves classifying when there insufficient or severe category distribution deviations. Due inherent...
Although intelligent interactive systems have been the focus of many research efforts, very few addressed for individuals with disabilities. This article presents our methodology an system that provides sight impairments access to content information graphics (such as bar charts and line graphs) in popular media. The describes underlying system's behavior, its interface interacting users, examples processed by implemented system, evaluation studies both effectiveness overall system. advances...
Purpose The purpose of this paper is to identify enablers and inhibitors the adoption mobile internet services by socioeconomically disadvantaged people: an understudied population adversely affected digital inequality. Design/methodology/approach A qualitative study combining a questionnaire semi-structured interviews. In total, 32 people explored lottery subsequently were asked series questions about their perceptions technology. Findings Users’ attitudes toward ambivalent. They...
Abstract It is necessary to analyze and mining marketing notification texts because there are various commercial information. The base of the operation Chinese word segmentation. speed accuracy segmentation have important influence on subsequent mining. We compared accuracy, recall, F-value four open-source tools (Ansj, HanLP, Word Jieba) third-party datasets. Then, we one million texts. Finally, segmented 5, 000 artificially. evaluated performance these by results artificial segmentation,...
Abstract Purpose Nowadays, public opinions during emergencies involve not only textual contents but also contain images. However, the existing works mainly focus on and they do provide a satisfactory accuracy of sentiment analysis, lacking combination multimodal contents. In this paper, we propose to combine texts images generated in social media perform analysis. Design/methodology/approach We Deep Multimodal Fusion Model (DMFM), which combines visual first train word2vec model large-scale...
Personal absorptive capacity of knowledge is basic foundation for creation and transfer. The Community Practice (CoP) the engine creation. In this paper, we analyzed relationship among SECI model, knowledge, CoP. We also bring forward conceptual model based on