Please use this identifier to cite or link to this item:
Type: Artigo
Title: A computational tool for weak signals classification – detecting threats and opportunities on politics in the cases of the United States and Brazilian presidential elections
Author: Garcia-Nunes, Pedro Ivo
Rodrigues, Pedro Artico
Oliveira, Kaulitz Guimarães
Silva, Ana Estela Antunes da
Abstract: The literature on weak signals (WS) has been fruitful in recent years and this specific type of information has attracted the attention of several disciplines, notably the futures studies. However, most of these studies still focus on conceptual discussions, terminology, or the proposal for frameworks that do not take advantage of the evolution of information and communication technologies. In this paper, authors discussed the lack of tools to computationally support WS handling. In response to this lack, a computational tool was developed considering a previously published method for WS classification based on conceptual systems. This tool was applied and evaluated in experimental cases about surprising events that occurred in politics in recent years, considering traditional metrics of information retrieval. Experiments illustrate that organizations can create several conceptual systems to represent different scenarios and types of knowledge; after all, results showed that the tool can operate according to different artifacts of knowledge representation. This capacity is useful to mitigate the effects of the surveillance filter though the evidence does not directly confirm its usefulness for the monitoring activities. Furthermore, the tool provides a list of threats, opportunities and unlabeled WS that can trigger other steps of sensemaking about these signals
Subject: Classificação
Country: Reino Unido
Editor: Elsevier
Rights: Fechado
Identifier DOI: 10.1016/j.futures.2020.102607
Date Issue: 2020
Appears in Collections:FT - Artigos e Outros Documentos

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.