CAREER: Tracking, Revealing and Detecting Crowdsourced Manipulation
National Science Foundation Award Number CNS 1755536 PI: Kyumin Lee Duration (expected): March 2016 - February 2023Project Overview
The goal of this project is to create the algorithms, frameworks, and systems for defending the open web ecosystem from emerging threats. This project aims to (i) analyze malicious tasks and behaviors of crowdturfers; (ii) detect malicious tasks on crowdsourcing platforms by developing novel malicious task detectors; (iii) design and build a task blacklist; (iv) uncover the ecosystem of crowdturfers and detect crowdturfers; (v) combine crowdturfer detection approaches with other malicious participants detection approaches. Crowdsourcing systems have successfully leveraged the attention of millions of "crowdsourced" workers to tackle vexing problems. From specialized systems for crisis mapping, for protein folding, for translation to general-purpose crowdsourcing platforms. However, these positive opportunities have sinister counterparts: large-scale "crowdturfing", wherein masses of cheaply paid workers can be organized to spread malicious URLs in social media, formation of artificial grassroots campaigns ("astroturf"), and manipulation of search engines. As a result, crowdsourced manipulation threatens the foundations of the open web ecosystem, reducing the quality of online social media, degrading our trust in search engines, manipulating political opinion and ultimately, reducing security and trustworthiness of cyberspace. Products of the research will be available for public use. The education and outreach efforts of the project are tightly linked to the research goals through curriculum development, workshops, direct training of underrepresented women, and involvement of industry.
Publications
- Y. Li, K. Lee, N. Kordzadeh, and R. Guo. What Boosts Fake News Dissemination on Social Media? A Causal Inference View, PAKDD 2023
- W. Ge, G.uanyi Mou, E. O. Agu, and K. Lee. Heterogeneous Hyper-Graph Neural Networks for Context-aware Human Activity Recognition, PerCom 2023
- H. Varzgani, N. Kordzadeh, and K. Lee. Toward Designing Effective Warning Labels for Health Misinformation on Social Media, HICSS 2023.
- K. Lee, G. Mou, and S. Sievert. Energy-based Domain Adaption with Active Learning for Emerging Misinformation Detection, BigData 2022.
- D. You, and K. Lee. Multi-Behavior Recommendation with Hyperbolic Geometry, BigData 2022.
- G. Mou, and K. Lee. An Effective, Robust and Fairness-aware Hate Speech Detection Framework. BigData 2021.
- G. Mou, Y. Li, and K. Lee. Reducing and Exploiting Data Augmentation Noise through Meta Reweighting Contrastive Learning for Text Classification. BigData 2021.
- N. Vo, and K. Lee. Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detection. EACL 2021.
- V. Sharma, K. Lee, and C. Dyreson. Popularity versus quality: analyzing and predicting the success of highly rated crowdfunded projects on Amazon. Computing 2021.
- Y. Li, K. Lee, N. Kordzadeh, B. Faber, C. Fiddes, E. Chen, and K. Shu. Multi-Source Domain Adaptation with Weak Supervision for Early Fake News Detection. BigData 2021.
- G. Mou, and K. Lee. Malicious Bot Detection in Online Social Networks: Arming Handcrafted Features with Deep Learning. SocInfo 2020.
- G. Mou, P. Ye, and K. Lee. SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detection. CIKM 2020.
- N. Vo, and K. Lee. Where are the Facts? Searching for Fact-checked Information to Alleviate the Spread of Fake News. EMNLP 2020.
- S. Subramanian, and K. Lee. Hierarchical Evidence Set Modeling for Automated Fact Extraction and Verification. EMNLP 2020.
- T. Tran, D. You, and K. Lee. Quaternion-based self-Attentive Long Short-term User Preference Encoding for Recommendation. CIKM 2020.
- T. Tran, Y. Hu, C. Hu, K. Yen, F. Tan, K. Lee, and S. R. Park. HABERTOR: An Efficient and Effective Deep Hatespeech Detector. EMNLP 2020.
- D. You, N. Vo., K. Lee, and Q. Liu. Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation. CIKM 2019.
- J. Lin, G. Taylor, G. Mou, D. You, and K. Lee. Detecting Fake News Articles (short). REU Symposium at IEEE BigData 2019.
- N. Vo, and K. Lee. Learning from Fact-checkers: Analysis and Generation of Fact-checking Language. SIGIR 2019.
- T. Tran, R. Sweeney, and K. Lee. Adversarial Mahalanobis Distance-based Attentive Song Recommender for Automatic Playlist Continuation. SIGIR 2019.
- T. Tran, X. Liu, K. Lee, and X. Kong. Signed Distance-based Deep Memory Recommender. WWW, 2019.
- T. Ha, Q. Hoang, and K. Lee. Building a Task Blacklist for Online Social Platforms (demo). ASONAM 2019.
- T. Tran, K. Lee, Y. Liao, and D. Lee. Regularizing Matrix Factorization with User and Item Embeddings for Recommendation. CIKM, 2018.
- V. Sharma, and K. Lee. Predicting Highly Rated Crowdfunded Products. ASONAM, August, 2018.
- N. Vo, and K. Lee. The Rise of Guardians: Fact-checking URL Recommendation to Combat Fake News. SIGIR, July 2018.
- N. Vo, K. Lee, and T. Tran. MRAttractor: Detecting Communities from Large-Scale Graphs. Big Data, December 2017.
- T. Tran, K. Lee, N. Vo, and H. Choi. Identifying On-time Reward Delivery Projects with Estimating Delivery Duration on Kickstarter. ASONAM, July 2017.
- N. Vo, K. Lee, C. Cao, T. Tran, and H. Choi. Revealing and Detecting Malicious Retweeter Groups. ASONAM, July 2017.
- Y. Liao, T. Tran, D. Lee, and K. Lee. Understanding Temporal Backing Patterns in Online Crowdfunding Communities. WebSci, June 2017.
- T. Tran, and K. Lee. Characteristics of On-time and Late Reward Delivery Projects. ICWSM, May 2017.
- P. Badri, K. Lee, D. Lee, T. Tran, and J. Zhang. Uncovering Fake Likers in Online Social Networks. CIKM, October 2016.
- H. Choi, K. Lee, and S. Webb. Detecting Malicious Campaigns in Crowdsourcing Platforms. ASONAM, August 2016.
- T. Tran, and K. Lee. Understanding Citizen Reactions and Ebola-Related Information Propagation on Social Media. ASONAM, August 2016.
Participants
- Kyumin Lee, PI
- Yichuan Li, PhD Student
- Guanyi Mou, PhD Student
- Di You, PhD Student
- Nguyen Vo, PhD Student
- Thanh Tran, PhD Student
- Renee Sweeney, PhD Student
- Shyam Subramanian, MS Student
- Hongkyu Choi, MS Student
- Prudhvi Badri, MS Student
- William Burke, REU Participant
- Devin Coughlin, REU Participant
- Eren Eroglu, REU Participant
- Philip Rago, REU Participant
- Taylor, Glenna, REU Participant
- Jun Lin, REU Participant
- Trang Ha, undergraduate Student
- Quyen Hoang, undergraduate Student