An Analysis of Novelty Dynamics in News Media Coverage Ronaldo Cristiano Prati Universidade Federal do ABC Santo Andr´e, S˜ ao Paulo, Brazil ronaldo.prati@ufabc.edu.br Walter Teixeira Lima J´ unior Univerisdade Federal do Amap´ a Macap´ a, Amap´ a, Brazil contato@walterlima.net Abstract Computer Science has affected almost all fields of human knowledge, contributing to scientific advances in many branches of Nat- ural and Social Sciences. Journalism is one of the fields that is benefiting of the advance of computer science. Among the journalis- tic concepts that can be analyzed computa- tionally is News Value. Novelty is one of the most important news value. A possible ap- proach to get novelty elements in a story con- siders word frequency, through of the capac- ity to collect and analyze massive amounts of data. In this paper, we use the News Cover- age Index dataset (NCI), maintained by the Pew Research Center, to analyze the novelty dynamics of news coverage, using the novelty signatures proposed by [12]. As a definition of novelty, we used the first appearance of a new lead newsmaker. Results show a good fit of the model to the dataset. Furthermore, an analysis by media sector and broad topic shows interesting insights for the analysis of media coverage. 1 Introduction The Computational Science has affected almost all fields of human knowledge, contributing to scientific advances in many branches of Natural and Social Sci- ences. For instance, the capacity to collect and analyze Copyright c  2016 for the individual papers by the paper’s au- thors. Copying permitted for private and academic purposes. This volume is published and copyrighted by its editors. In: M. Martinez, U. Kruschwitz, G. Kazai, D. Corney, F. Hopf- gartner, R. Campos and D. Albakour (eds.): Proceedings of the NewsIR’16 Workshop at ECIR, Padua, Italy, 20-March-2016, published at http://ceur-ws.org massive amounts of data has transformed intensely fields such as biology and physics [7]. In Social Science, despite the difficulties to formalize computationally many scientific subjects of the human behavior, “a computational social science is emerg- ing that leverages the capacity to collect and ana- lyze data with an unprecedented breadth and depth and scale” [7]. Unfortunately, most of the advances in this area have been progressing at a much slower pace. However, substantial barriers that might limit progress are being overcome in recent years. The emer- gence of a powerful new field of data analysis of Social Science has also influenced the research on a branch of it, Journalism. Journalism is an important social prac- tice. Therefore, to find non-trivial information on con- tent produced by journalism, it is necessary to count with the support of the current stage of technologies to advance in analytical techniques “Computation can advance journalism by drawing on innovations in topic detection, video analysis, personalization, aggregation, visualization, and sense making [10]. Among the journalistic concepts that can be ana- lyzed computationally is News Value. News value as a concept was thought by Johan Galtung and Mari Holmboe Ruge’s seminal publication in the Journal of Peace Research. In 1965, the paper suggested a range of attributes that establish news values in discursive el- ements contained in newspapers and broadcast news. Galtung and Ruge established the news values ele- ments as Frequency; Threshold; Unambiguity; Mean- ingfulness; Consonance; Unexpectedness; Continuity; Composition; Reference to Elite Nations; Reference to Elite People; Reference to Persons; and Reference to Something Negative [3]. These factors have been the base to compose the structure of the theory of news- worthiness. The theory is based on the psychology of individual perception and explain which factors influ- ence newsworthiness of an event [6]. News values are studied considering a range of at-