Nar-A-Viz: A methodology to visually extract the narrative structure of text. (September 2019)

• Record Type: Journal Article
• Authors: Dessavre, Dante Gama; Ramirez-Marquez, Jose E.
• Is Part Of: Computer speech & language. Volume 57(2019)
• Page Start: 81
• Page End: 97
• Publication Date: 2019-09
• Subjects: Visual text analytics -- Exploratory analytics -- Document summarization -- Topic analysis -- Interactive visualization; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2019.02.004
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Created a new model of narrative structure quantifying message delivery in documents. Created a new visualization analytics for narrative structure. Showed visual analytics can summarize contents of a speech and identify structural analysis. Developed system for speech comparison and analysis with political speeches. Abstract: Being able to tell and understand stories is a key component for efficient communications. The narrative structure is the structural framework that underlies the order and manner in which this story is presented to a reader, listener, or viewer, this work presents a novel visualization methodology that can be used to extract the narrative structure of texts and present in a visual, immediate and intuitive manner. This tool efficiently summarizes the content of a text, and it also allows in depth analysis of the narrative structure. The characteristics and use of the tool are exemplified using a TED talk by Hans Rosling. Its potential then is shown using two historical speeches: President Donald Trump's inaugural speech and I Have a Dream by Dr. Martin Luther King Jr.