Hi! I'm Kai-Cheng Yang (杨凯程), the pronunciation is KY-cheng YAHNG. I also go by Kevin.
I'm a second year Ph.D student in Informatics at School of Informatics, Computing and Engineering in Indiana University Bloomington. I mainly work with Filippo Menczer, Yong-Yeol Ahn and Brea L. Perry. Check out the Projects and Publications sections for what I have been working on.
Before joining the Ph.D program at IU, I received my bachelor and master degree in theoretical physics from Lanzhou University in China.
Hoaxy is a tool that visualizes the spread of fake news and related fact checking articles on Twitter. With the incorporation of Botometer, Hoaxy can also visualize the bot-like activities involved in the spread of the articles.
Contribution: maintaining, developing API for Hoaxy to fetch Botometer scores
Identifying fake news has been a challenging task due the complex nature of the problem. A common approach adopted by researchers is to code the news sources manually and label all articles based on their source. However, to cope with the large amount of emerging fake news sources, a scalable method is needed. This project I construct the co-occurrence network of news sources from social media and find that although noisy this approach provides strong signal to distinguish the fake news sources.
Botometer is a machine learning tool that extracts over 1000 different features from a Twitter account and evaluates its likelihood of being social bot. Currently Botometer is handling over 250,000 requests every day and serves as the foundation for many researches.
Contribution: maintaining, training data annotation and model retraining
BEV is a tool that visualizes the activity of likely bots on Twitter around the 2018 US midterm elections. It allows to explore how active bots are on a daily basis in efforts to influence online discourse about the elections. It also shows what topics are being targeted by likely bots.
BotometerLite is a light version of Botometer. Using only part of the features from Botometer, BotometerLite is 200x faster but still yields comparable results. Because of the simplified design, it becomes possible to interpret BotometerLite's results.
So far, studies of social bots have largely been conducted in computational perspectives. How social media users perceive social bots and a series of related questions remain unclear. In this human subject research project we use experimental design to understand social media users' perception towards social bots. We also characterize the effect of human biases on the efficacy of social bot detection task.
Traditional methods for identifying drug seeking behavior focus on each patient's medical history individually. Typical criteria involves the number of different prescriber, visits of different pharmacies and total drug dose in certain time period. Our analysis shows such type of methods has become less useful as the patients are intentionally altering their behaviors to avoid being spotted by those methods. This project tends to utilize social network analysis to identify drug seeking behavior which has proven to be very effective and harder to trick.
Doctor shoppers are people that visit multiple physicians to obtain multiple prescriptions of controlled substances. The opioid doctor shoppers have been found to be more likely to overdose leading to the ever severer opioid crisis in US. The project intends to apply computational methods to over 9 years of longitudinal medical records from a large group of patients to characterize the geographic related behaviors of doctor shoppers.
Word2vec is applied to large scale of medical records to find a distributed representation of the diagnoses. The embedding can effectively reduce the dimensions needed to encode all the diagnoses therefore serves as a preprocessing step for other machine learning tasks. Besides, the embedding itself can reveal interesting relationship between diagnoses.
Multipartite viruses have multiple segmented genomes that are packaged in separate virus particles. This peculiar genetic organization makes multipartite viruses the most strange viruses and has drawn great attention from academia recently. Yet, a solid understanding of why such seemingly disadvantageous strategy has emerged is still lacking. This project extends the SIR model with multipartite mechanism and studies the spread of multipartite viruses on networks. Analysis reveals the sudden outbreak nature of multipartite viruses and finds that counterintuitively multipartite viruses favor static networks over dynamical networks. The results may may explain the prevalence of multipartite viruses in plants.