A5050833068- Access Control and Trust
- Semantic Web and Ontologies
- Social Media and Politics
- Complex Network Analysis Techniques
- Digital Marketing and Social Media
- Misinformation and Its Impacts
- Opinion Dynamics and Social Influence
- Peer-to-Peer Network Technologies
- Recommender Systems and Techniques
- Service-Oriented Architecture and Web Services
- Hate Speech and Cyberbullying Detection
- Advanced Graph Neural Networks
- Privacy, Security, and Data Protection
- Privacy-Preserving Technologies in Data
- Personality Traits and Psychology
- Spam and Phishing Detection
- Caching and Content Delivery
- Mental Health via Writing
- Public Relations and Crisis Communication
- Data Quality and Management
- Impact of Technology on Adolescents
- Scientific Computing and Data Management
- Innovative Human-Technology Interaction
- Biomedical Text Mining and Ontologies
- Sexuality, Behavior, and Technology
University of Maryland, College Park
2016-2025
AID Atlanta
2016
Human Media
2014
Vrije Universiteit Amsterdam
2008
University of Maryland, Baltimore
2004-2007
University of Southampton
2007
Argonne National Laboratory
2007
University of Chicago
2007
Park University
2007
Williams (United States)
2006
Social media is a place where users present themselves to the world, revealing personal details and insights into their lives. We are beginning understand how some of this information can be utilized improve users' experiences with interfaces one another. In paper, we interested in personality users. Personality has been shown relevant many types interactions, it useful predicting job satisfaction, professional romantic relationship success, even preference for different interfaces. Until...
Social media is a place where users present themselves to the world, revealing personal details and insights into their lives. We are beginning understand how some of this information can be utilized improve users' experiences with interfaces one another. In paper, we interested in personality users. Personality has been shown relevant many types interactions; it useful predicting job satisfaction, professional romantic relationship success, even preference for different interfaces. Until...
Abstract Twitter is a microblogging and social networking service with millions of members growing at tremendous rate. With the buzz surrounding have come claims its ability to transform way people interact share information calls for public figures start using service. In this study, we are interested in type content that legislators posting service, particularly by United States Congress. We read analyzed over 6,000 posts from all Congress site. Our analysis shows Congresspeople primarily...
The growth of Web-based social networking and the properties those networks have created great potential for producing intelligent software that integrates a user's network preferences. Our research looks particularly at assigning trust in investigates how information can be mined integrated into applications. This article introduces definition suitable use with discussion will influence its computation. We then present two algorithms inferring relationships between individuals are not...
Online social networks, where users maintain lists of friends and express their preferences for items like movies, music, or books, are very popular. The Web-based nature this information makes it ideal use in a variety intelligent systems that can take advantage the users' personal data. For those to be effective, however, is important understand relationship between preferences. In work we investigate features profile similarity how relate way determine trust. Through controlled study,...
In this paper, we present FilmTrust, a website that integrates Semantic Web-based social networks, augmented with trust, to create predictive movie recommendations. We show how these recommendations are more accurate than other techniques in certain cases, and discuss technique as mechanism of Web interaction.
Social networks have interesting properties. They influence our lives enormously without us being aware of the implications they raise. The authors investigate following areas concerning social networks: how to exploit unprecedented wealth data and we can mine for purposes such as marketing campaigns; a particular form influence, i.e.., way that people agree on terminology this phenomenon's build ontologies Semantic Web; something discover from data; use network information offer new...
Information quality in social media is an increasingly important issue, but web-scale data hinders experts' ability to assess and correct much of the inaccurate content, or "fake news," present these platforms. This paper develops a method for automating fake news detection on Twitter by learning predict accuracy assessments two credibility-focused datasets: CREDBANK, crowdsourced dataset events Twitter, PHEME, potential rumors journalistic their accuracies. We apply this content sourced...
A fundamental part of conducting cross-disciplinary web science research is having useful, high-quality datasets that provide value to studies across disciplines. In this paper, we introduce a large, hand-coded corpus online harassment data. team researchers collaboratively developed codebook using grounded theory and labeled 35,000 tweets. Our resulting dataset has roughly 15% positive examples 85% negative examples. This data useful for training machine learning models, identifying textual...
As user-generated content and interactions have overtaken the web as default mode of use, questions whom what to trust become increasingly important. Fortunately, online social networks media made it easy for users indicate they do not. However, this does not solve problem since each user is only likely know a tiny fraction other users, we must methods inferring - distrust between who one another. In paper, present new method computing both (i.e., positive negative trust). We by combining an...
There is great interest in understanding media bias and political information seeking preferences. As many outlets create online personas, we seek to automatically estimate the preferences of their audience, rather than outlet itself. In this paper, present a novel method for computing preference among an organization's Twitter followers. We application technique audiences U.S. outlets. also discuss how these results may be used extended.