Learning From Collective Human Behavior to Introduce Diversity in Lexical Choice

Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, pages 1098–1108, Portland, Oregon, June 19-24, 2011. c⃝2011 Association for Computational Linguistics Learning From Collective Human Behavior to Introduce Diversity in Lexical Choice Vahed Qazvinian Department of EECS University of Michigan Ann Arbor, MI vahed@umich.edu Dragomir R. Radev School of Information Department of EECS University of Michigan Ann Arbor, MI radev@umich.edu Abstract We analyze collective discourse, a collective human behavior in content generation, and show that it exhibits diversity, a property of general collective systems. Using extensive analysis, we propose a novel paradigm for de- signing summary generation systems that re- flect the diversity of perspectives seen in real- life collective summarization. We analyze 50 sets of summaries written by human about the same story or artifact and investigate the diver- sity of perspectives across these summaries. We show how different summaries use vari- ous phrasal information units (i.e., nuggets) to express the same atomic semantic units, called factoids. Finally, we present a ranker that em- ploys distributional similarities to build a net- work of words, and captures the diversity of perspectives by detecting communities in this network. Our experiments show how our sys- tem outperforms a wide range of other docu- ment ranking systems that leverage diversity. 1 Introduction In sociology, the term collective behavior is used to denote mass activities that are not centrally coordi- nated (Blumer, 1951). Collective behavior is dif- ferent from group behavior in the following ways: (a) it involves limited social interaction, (b) mem- bership is fluid, and (c) it generates weak and un- conventional norms (Smelser, 1963). In this paper, we focus on the computational analysis of collective discourse, a collective behavior seen in interactive content contribution and text summarization in on- line social media. In collective discourse each in- dividual’s behavior is largely independent of that of other individuals. In social media, discourse (Grosz and Sidner, 1986) is often a collective reaction to an event. One scenario leading to collective reaction to a well- defined subject is when an event occurs (a movie is released, a story occurs, a paper is published) and people independently write about it (movie reviews, news headlines, citation sentences). This process of content generation happens over time, and each per- son chooses the aspects to cover. Each event has an onset and a time of death after which nothing is written about it. Tracing the generation of content over many instances will reveal temporal patterns that will allow us to make sense of the text gener- ated around a particular event. To understand collective discourse, we are inter- ested in behavior that happens over a short period of time. We focus on topics that are relatively well- defined in scope such as a particular event or a single news event that does not evolve over time. This can eventually be extended to events and issues that are evolving either in time or scope such as elections, wars, or the economy. In social sciences and the …

Content truncated to 500 words