- Spam and Phishing Detection
- Sentiment Analysis and Opinion Mining
- Complex Network Analysis Techniques
- Misinformation and Its Impacts
- Advanced Malware Detection Techniques
- Caching and Content Delivery
- Peer-to-Peer Network Technologies
- Network Security and Intrusion Detection
- Topic Modeling
- Hong Kong and Taiwan Politics
- Advanced Text Analysis Techniques
- Advanced Graph Neural Networks
- Web Data Mining and Analysis
- Hate Speech and Cyberbullying Detection
- Cybercrime and Law Enforcement Studies
- Opinion Dynamics and Social Influence
- User Authentication and Security Systems
- Mental Health via Writing
- Speech and Audio Processing
- Social Media and Politics
- Asian Culture and Media Studies
- Cinema and Media Studies
- Advanced Data Storage Technologies
- Authorship Attribution and Profiling
- Opportunistic and Delay-Tolerant Networks
Liaoning Technical University
2025
Beijing Film Academy
2021-2024
Sichuan University
2012-2024
Chengdu University
2020
Beijing University of Posts and Telecommunications
2017
Guangxi University
2011
Glocalization, adapting global practices to local contexts, has become increasingly important in scientific research. However, the impact of and collaboration networks on glocalization remains underexplored. In this study, we conduct a bibliometric analysis examine publications field recorded Scopus database from 1993–2023. Using data 12,046 publications, identify key themes, publication trends, methodological designs related networks. We then develop theoretical model incorporating these...
Online users are typically active on multiple social media networks (SMNs), which constitute a multiplex network. With improvements in cybersecurity awareness, increasingly choose different usernames and provide profiles SMNs. Thus, it is becoming challenging to determine whether given accounts SMNs belong the same user; this can be expressed as an interlayer link prediction problem To address challenge of predicting links, feature or structure information leveraged. Existing methods that...
The exponential growth of information on the World Wide Web makes it increasingly difficult to discover relevant data about a specific topic. In this case, growing interest is emerging in focused crawler, program that traverses Internet by choosing pages predefined topic and neglecting those out concern. A new crawler based Naive Bayes classifier was proposed here, which used an improved TF-IDF algorithm extract characteristics page content adopted compute rank. Then developed compared with...
Existing studies have shown that various types of information on the online social network (OSN) can help predict early stage depression. However, using machine learning methods to accomplish depression detection tasks still do not high classification performance, suggesting there is much potential for improvement in their feature engineering. In this paper, we first construct a dataset Sina Weibo (a leading OSN with largest number active users Chinese community), namely User Depression...
This paper proposes an anomalous behavior detection model based on cloud computing. Virtual Machines (VMs) are one of the key components Infrastructure as a Service (IaaS). The security such VMs is critical to IaaS security. Many studies have been done computing issues, but research into VM especially regarding network traffic detection, remains inadequate. More and more show that communication among internal nodes exhibits complex patterns. Communication in invisible. Researchers find...
The development of information technology and mobile Internet has spawned the prosperity online social networks. As world’s largest microblogging platform, Twitter is popular among people all over world. However, as number users on increases, rumors have become a serious problem. Therefore, rumor detection necessary since it can prevent unverified from causing public panic disrupting order. Cantonese widely used language in China. to best our knowledge, little research been done detection....
The pervasiveness of offensive language on social networks has caused adverse effects society, such as abusive behavior online. It is urgent to detect and curb its spread. In the popular datasets, distribution users tweets imbalanced, which limits generalization ability model. addition, existing research shows that methods with community information extracted from graphs effectively improve performance detection. However, models deal independently, seriously affects effectiveness detection...
With the continuous development of darknet technology, scale and have increased rapidly in recent years, leading to rampant crime these anonymous trading markets. Monitoring markets can effectively combat criminal forces that hide behind them. One difficulties understanding is criminals usually use jargons disguise transactions thus avoid surveillance. These distort original meaning innocent-looking words obscure ways, posing significant challenges for tracking. Current research on Chinese...
Twitter is a popular social networking platform. While people enjoy the news and anecdotes on Twitter, there are also lots of rumors, which have negative impact users can compromise order. Among these many them written in Cantonese. At present, research English rumor detection relatively comprehensive, but Cantonese rumors rarely studied, brings great challenges to Twitter. Firstly, no available benchmark dataset rumors. Secondly, it difficult completely extract features Thirdly, classical...
Abstract Nowadays, millions of people use Online Social Networks (OSNs) like Twitter, Facebook and Sina Microblog, to express opinions on current events. The widespread these OSNs has also led the emergence social bots. What is more, existence bots so powerful that some them can turn into influential users. In this paper, we studied automated construction technology infiltration strategies in aiming at building friendly resist malicious interpretations. Firstly, critical Microblog data...