A decade after publishing “Finding Deceptive Opinion Spam by Any Stretch of the Imagination," Claire Cardie, Professor in the departments of Computer Science and Information Science, along with a team of alumni and former Cornellians, won a Test of Time award from the Association for Computational Linguistics (ACL).
Cardie, who also serves at the inaugural Associate Dean for Education in the Cornell Ann S. Bowers College of Computing and Information Science, worked on the article with Myle Ott (CS Ph.D. ’13), now an NLP Researcher at Facebook AI Research; Yejin Choi (CS Ph.D. ’10), now Brett Helsel Professor at the University of Washington; and former Cornell Professor of Information Science and Communication, Jeff Hancock, now at Stanford University, where he is Professor in the Department of Communication and founding director of the Stanford Social Media Lab.
This paper was one of the earliest to address the issue of detecting online misinformation, now often called “fake news,” and in this way pioneered a topic that has become enormously important in NLP and also more generally in society. The paper’s influence continues to be significant, both in NLP and computational linguistics and in neighboring fields in the social sciences.
As the authors explained in 2011, consumers “increasingly rate, review, and research products online. Consequently, websites containing consumer reviews are becoming targets of opinion spam. While recent work has focused primarily on manually identifiable instances of opinion spam, in this work we study deceptive opinion spam—fictitious opinions that have been deliberately written to sound authentic.” In their effort to integrate work from psychology and computational linguistics, the authors develop and compare “three approaches to detecting deceptive opinion spam, and ultimately develop a classifier that is nearly 90% accurate on our gold-standard opinion spam dataset.” Based on their models, the authors were able to reveal a relationship “between deceptive opinions and imaginative writing.”
The ACL awarded the authors with this Test of Time award because their findings and proposals have exhibited a “long-lasting influence on the field” of computational linguistics. Moreover, the work shows how the authors “may have proposed new research directions and new technologies, or released results and resources that have greatly benefited the community.” The winners were honored at ACL 2021.
Cardie, Ott, Choi, and Hancock joined together in what was described as Brady Bunch-inspired acceptance remarks.