Auth-Integrate Toward Combating False Data on the Internet

The advent of the collaborative Web and the abundance of usergenerated data has resulted in the problem of information overload; it is becoming increasingly difficult to discern relevant information and discard false data. Recently, a number of solutions for automated fact-checking have been proposed that view the problem from a largely linguistic perspective. We observe that the problem of false data detection has roots in several extensively studied research areas in data management and data mining such as data integration, data cleaning, crowdsourcing and machine learning. Specifically, detection of false data has significant overlap with data fusion, an active area of research in data integration that focuses on distinguishing correct from incorrect information in a structured data setting. In this vision paper, we propose the architecture of AuthIntegrate, an end-to-end system that ingests conflicting data from disparate information providers, curates and presents highly accurate data to end-users. We discuss the technical challenges in building this system and outline an agenda for future research. ACM Reference Format: Romila Pradhan and Sunil Prabhakar. 2018. AuthIntegrate: Toward Combating False Data on the Internet. In Woodstock ’18: ACM Symposium on Neural Gaze Detection, June 03–05, 2018, Woodstock, NY. ACM, New York, NY, USA, 5 pages. https://doi.org/10.1145/1122445.1122456