I am a PhD candidate in Computer and Information Science at Syracuse University, advised by Dr Reza Zafarani, and was a research intern at the University of Southern California, mentored by Dr Emilio Ferrara. My research has also been conducted closely with Drs Huan Liu, Vir Phoha, and Kai Shu. Before pursuing a PhD, I was an undergraduate student in Computer Science at Southwest University in China, advised by Dr Yong Deng. I have learned a lot from these talented researchers and appreciate their tremendous support for me.
About My Research
My research broadly spans (applied) machine learning, natural language processing, and computational social science, with a long-term goal of reducing bias and promoting diversity and inclusion of online communities. My research has leveraged multimodal and behavioral data, social theories, and AI techniques to understand, predict, and mitigate misleading content, particularly m/disinformation (“fake news”). Below are some examples of my work.
Survey of m/disinformation. Our work accepted to ACM Computing Surveys extensively investigates the theoretical foundations of “fake news” in social science and its detection approaches based on knowledge graphs, writing styles, propagation on social media, and source credibility.
Intent assessment of m/disinformation spreaders. People may spread m/disinformation unintentionally without knowing it is false. Our WWW 2022 paper probes the psychological interpretations behind the phenomenon (i.e., individuals’ beliefs and social influence) and computes them to assess the intent of m/disinformation spreaders. Data are available upon request. Code will be released soon.
Multimodal m/disinformation detection. Our PAKDD paper develops neural networks to predict m/disinformation by learning its within-modality information and cross-modality relationship, where its falsehood can exist. Code is available on GitHub.
Writing-style-aware disinformation detection. Our ACM DTRAP paper predicts disinformation with a psychology-inspired feature extraction process that captures disinformation’s linguistic styles at lexicons, syntax, semantics, and discourse levels.
“Fake news” datasets. We created datasets, ReCOVery (in CIKM) and CHECKED (in SNAM), rich in textual, visual, audio, network, and meta data for “fake news” research on coronavirus. ReCOVery collects labeled news articles in English and their circulation on Twitter. CHECKED contains labeled microblogs in Chinese and their dissemination on Weibo.
- [06/2022] Invited to serve as a PC member for ASONAM 2022.
- [04/2022] I will attend SICSS at UPenn and appreciate the organizing team for the travel grant. See you in Philadelphia in June!
- [03/2022] Invited to serve as a PC member for CIKM 2022.
- [01/2022] I was awarded Syracuse University Ph.D. Fellowship. Special thanks to my advisor and Dr Jae Oh for their great help.
- [01/2022] One paper was accepted by WWW 2022. Thank all reviewers’ positive comments!
- [01/2022] Invited to serve as a PC member for SIGIR 2022.
- [11/2021] Invited to serve as a PC member for CHIIR 2022 and KDD 2022.
- [07/2021] Invited to serve as a PC member for CIKM 2021 and WSDM 2022.
- [06/2021] One paper was accepted by SNAM.
- [05/2021] Invited to serve as a PC member for ASONAM 2021.
- [01/2021] Invited to serve as a PC member for SIGIR 2021.
- [11/2020] Invited to serve as a PC member for ECIR 2021.
- [11/2020] Invited as a guest on The Data Exchange to introduce our research on fake news.
- [07/2020] One paper was accepted by CIKM 2020. Thank all reviewers’ positive comments!
- [05/2020] I will intern at USC this summer.
- [04/2020] Our survey was accepted by CSUR. Thank all reviewers’ constructive comments!
- [01/2020] One paper was accepted by PAKDD 2020. Thank all reviewers’ positive comments!
- [01/2020] I was awarded Varshney Scholarship. Thank you, Drs Pramod Varshney, Anju Varshney, and the EECS department!