A5021992851- Complex Network Analysis Techniques
- Misinformation and Its Impacts
- Spam and Phishing Detection
- Opinion Dynamics and Social Influence
- Advanced Graph Neural Networks
- Sentiment Analysis and Opinion Mining
- Advanced Text Analysis Techniques
- Topic Modeling
- Advanced Malware Detection Techniques
- Topological and Geometric Data Analysis
- User Authentication and Security Systems
- Digital Marketing and Social Media
- Network Security and Intrusion Detection
- Hate Speech and Cyberbullying Detection
- Authorship Attribution and Profiling
- Bioinformatics and Genomic Networks
- Time Series Analysis and Forecasting
- Advanced Clustering Algorithms Research
- Neural Networks and Applications
- Mobile Crowdsensing and Crowdsourcing
- Machine Learning and Algorithms
- Solar Radiation and Photovoltaics
- Web Data Mining and Analysis
- Human Mobility and Location-Based Analysis
- Machine Learning and ELM
Syracuse University
2015-2024
Evolutionary Genomics (United States)
2024
Astronomy and Space
2024
Virtual High School
2024
Pennsylvania State University
2019
Arizona State University
2009-2015
University of New Brunswick
2007-2009
National Research Council Canada
2009
University of Isfahan
2005-2007
Universitas Nusa Bangsa
2007
People use various social media for different purposes. The information on an individual site is often incomplete. When sources of complementary are integrated, a better profile user can be built to improve online services such as verifying information. To integrate these information, it necessary identify individuals across sites. This paper aims address the cross-media identification problem. We introduce methodology (MOBIUS) finding mapping among identities It consists three key...
Sarcasm is a nuanced form of language in which individuals state the opposite what implied. With this intentional ambiguity, sarcasm detection has always been challenging task, even for humans. Current approaches to automatic rely primarily on lexical and linguistic cues. This paper aims address difficult task Twitter by leveraging behavioral traits intrinsic users expressing sarcasm. We identify such using user's past tweets. employ theories from psychological studies construct modeling...
The increasing popularity and diversity of social media sites has encouraged more people to participate on multiple online networks enjoy their services. Each user may create a identity, which can includes profile, content, or network information, represent his her unique public figure in every network. Thus, fundamental question arises -- we link identities across networks? User identity linkage is an emerging task attracted attention recent years. Advancements could potentially impact...
The explosive growth of fake news and its erosion to democracy, justice, public trust increased the demand for detection. As an interdisciplinary topic, study encourages a concerted effort experts in computer information science, political journalism, social psychology, economics. A comprehensive framework systematically understand detect is necessary attract unite researchers related areas conduct research on news. This tutorial aims clearly present (1) research, challenges, directions; (2)...
Massive dissemination of fake news and its potential to erode democracy has increased the demand for accurate detection. Recent advancements in this area have proposed novel techniques that aim detect by exploring how it propagates on social networks. Nevertheless, at an early stage, i.e., when is published a outlet but not yet spread media, one cannot rely propagation information as does exist. Hence, there strong need develop approaches can focusing content. In article, theory-driven model...
Consuming news from social media is becoming increasingly popular. Social appeals to users due its fast dissemination of information, low cost, and easy access. However, also enables the widespread fake news. Due detrimental societal effects news, detecting has attracted increasing attention. detection performance only using contents generally not satisfactory as written mimic true Thus, there a need for an in-depth understanding on relationship between user profiles In this paper, we study...
Fake news gains has gained significant momentum, strongly motivating the need for fake research. Many detection approaches have thus been proposed, where most of them heavily rely on content. However, networkbased clues revealed when analyzing propagation social networks is an information that hardly comprehensively explored or used detection. We bridge this gap by proposing a network-based pattern-driven approach. aim to study patterns in networks, which refer being spread, spreaders and...
First identified in Wuhan, China, December 2019, the outbreak of COVID-19 has been declared as a global emergency January, and pandemic March 2020 by World Health Organization (WHO). Along with this pandemic, we are also experiencing an "infodemic" information low credibility such fake news conspiracies. In work, present ReCOVery, repository designed constructed to facilitate research on combating regarding COVID-19. We first broadly search investigate ~2,000 publishers, from which 60...
One of the most interesting challenges in area social computing and media analysis is so-called community analysis. A well known barrier cross-community (multiple website) disconnectedness these websites. In this paper, our aim to provide evidence on existence a mapping among identities across multiple communities, providing method for connecting Our studies have shown that simple, yet effective approaches, which leverage media's collective patterns can be utilized find such mapping. The...
Social networks have been widely studied over the last century from multiple disciplines to understand societal issues such as inequality in employment rates, managerial performance, and epidemic spread. Today, these many more can be at global scale thanks digital footprints that we generate when browsing Web or using social media platforms. Unfortunately, scientists often struggle access data primarily because it is proprietary, even shared with privacy guarantees, either no representative...
People use various social media sites for different purposes. The information on each site is often partial. When sources of complementary are integrated, a better profile user can be built. This help improve online services such as advertising across sites. To integrate these information, it necessary to identify individuals paper aims address the cross-media identification problem. We provide evidence existence mapping among identities sites, study feasibility finding this mapping, and...
The incredible growth of the social web over last decade has ushered in a flurry new media sites. On one hand, users have an inordinate number choices; on other are constrained by limited time and resources to choose sites order remain active. Hence, dynamic entails user migration, well studied phenomenon fields such as sociology psychology. Users valuable assets for they help contribute site generate revenue increased traffic. We intrigued know if migration can be studied, what patterns...
Effective detection of fake news has recently attracted significant attention. Current studies have made contributions to predicting with less focus on exploiting the relationship (similarity) between textual and visual information in articles. Attaching importance such similarity helps identify stories that, for example, attempt use irrelevant images attract readers' In this work, we propose a $\mathsf{S}$imilarity-$\mathsf{A}$ware $\mathsf{F}$ak$\mathsf{E}$ method ($\mathsf{SAFE}$) which...
Fake news has become a global phenomenon due its explosive growth, particularly on social media. The goal of this tutorial is to (1) clearly introduce the concept and characteristics fake how it can be formally differentiated from other similar concepts such as mis-/dis-information, satire news, rumors, among others, which helps deepen understanding news; (2) provide comprehensive review fundamental theories across disciplines illustrate they used conduct interdisciplinary research,...
Social media is gaining popularity as a medium of communication before, during, and after crises. In several recent disasters, it has become evident that social sites like Twitter Facebook are an important source information, in cases they have even assisted relief efforts. We propose novel approach to identify subset active users during crisis who can be tracked for fast access information. Using dataset consists 12.9 million tweets from 5 countries part the "Arab Spring" movement, we show...
Network data has become widespread, larger, and more complex over the years. Traditional network is dyadic, capturing relations among pairs of entities. With need to model interactions than two entities, significant research focused on higher-order networks ways represent, analyze, learn from them. There are main directions studying networks. One direction patterns in traditional (dyadic) graphs by changing basic unit study nodes small frequently observed subgraphs, called motifs. As most...