Friendships, Rivalries, and Trysts: Characterizing Relations between Ideas in Texts

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 773–783 Vancouver, Canada, July 30 - August 4, 2017. c⃝2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1072 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 773–783 Vancouver, Canada, July 30 - August 4, 2017. c⃝2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1072 Friendships, Rivalries, and Trysts: Characterizing Relations between Ideas in Texts Chenhao Tan∗ Dallas Card† Noah A. Smith∗ ∗Paul G. Allen School of Computer Science & Engineering †School of Computer Science University of Washington Carnegie Mellon University Seattle, WA 98195, USA Pittsburgh, PA 15213, USA chenhao@chenhaot.com dcard@cmu.edu nasmith@cs.washington.edu Abstract Understanding how ideas relate to each other is a fundamental question in many domains, ranging from intellectual his- tory to public communication. Because ideas are naturally embedded in texts, we propose the first framework to systemat- ically characterize the relations between ideas based on their occurrence in a cor- pus of documents, independent of how these ideas are represented. Combining two statistics—cooccurrence within doc- uments and prevalence correlation over time—our approach reveals a number of different ways in which ideas can cooper- ate and compete. For instance, two ideas can closely track each other’s prevalence over time, and yet rarely cooccur, almost like a “cold war” scenario. We observe that pairwise cooccurrence and prevalence correlation exhibit different distributions. We further demonstrate that our approach is able to uncover intriguing relations be- tween ideas through in-depth case studies on news articles and research papers. 1 Introduction Ideas exist in the mind, but are made manifest in language, where they compete with each other for the scarce resource of human attention. Milton (1644) used the “marketplace of ideas” metaphor to argue that the truth will win out when ideas freely compete; Dawkins (1976) similarly likened the evolution of ideas to natural selection of genes. We propose a framework to quantitatively charac- terize competition and cooperation between ideas in texts, independent of how they might be repre- sented. By “ideas”, we mean any discrete conceptual units that can be identified as being present or ab- sent in a document. In this work, we consider representing ideas using keywords and topics ob- tained in an unsupervised fashion, but our way of characterizing the relations between ideas could be applied to many other types of textual repre- sentations, such as frames (Card et al., 2015) and hashtags. What does it mean for two ideas to compete in texts, quantitatively? Consider, for example, the issue of immigration. There are two strongly com- peting narratives about the roughly 11 million peo- ple1 who are residing in the United States without permission. One is “illegal aliens”, who “steal” jobs and deny opportunities to legal immigrants; the other is “undocumented immigrants”, who are already part of the fabric of society and deserve a path to citizenship (Merolla et al., 2013). Although prior knowledge suggests that these two narratives compete, it is not immediately ob- vious what measures might reveal this competition in a corpus of …

Content truncated to 500 words