A5033780559- Spam and Phishing Detection
- Misinformation and Its Impacts
- Hate Speech and Cyberbullying Detection
- Complex Network Analysis Techniques
- Authorship Attribution and Profiling
- Digital Marketing and Social Media
- Network Security and Intrusion Detection
- Social Media and Politics
Centre Universitaire de Mila
2021-2023
McGill University
2021-2023
Given a million escort advertisements, how can we spot near-duplicates? Such micro-clusters of ads are usually signals human trafficking. How summarize them, visually, to convince law enforcement act? Can build general tool that works for different languages? Spotting near-duplicate documents is useful in multiple, additional settings, including spam-bot detection Twitter ads, plagiarism, and more.We present INFOSHIELD, which makes the following contributions: (a) Practical, being scalable...
Given a million escort advertisements, how can we spot near-duplicates? Such micro-clusters of ads are usually signals human trafficking (HT). How summarize them to convince law enforcement act? Spotting near-duplicate documents is useful in multiple, additional settings, including spam-bot detection Twitter ads, plagiarism, and more. We present InfoShield , which makes the following contributions: practical being scalable effective on real data; parameter-free principled requiring no...
Social media sites are becoming a key factor in politics. These platforms easy to manipulate for the purpose of distorting information space confuse and distract voters. Past works identify disruptive patterns mostly focused on analyzing content tweets. In this study, we jointly embed from both user posted as well user's follower network, detect groups densely connected users an unsupervised fashion. We then investigate these dense sub-blocks flag anomalous behavior. our experiments, study...
Recent events have led to a burgeoning awareness on the misuse of social media sites affect political events, sway public opinion, and confuse voters. Such serious, hostile mass manipulation has motivated large body works bots/troll detection fake news detection, which mostly focus classifying at user level based content generated by users. In this study, we jointly analyze connections among users, as well them Spot Coordinated Groups (SCG), sets users that are likely be organized towards...