{"title":"叙事地图可视化工具(NMVT):基于叙事地图框架的交互式叙事分析系统","authors":"Brian Keith Norambuena","doi":"10.1016/j.softx.2025.102377","DOIUrl":null,"url":null,"abstract":"<div><div>The <strong>Narrative Maps Visualization Tool</strong> (NMVT) is an interactive visual analytics system designed to help analysts understand complex narratives from collections of text documents. NMVT leverages graph-based representations to extract and visualize coherent storylines, showing how events connect over time. The system integrates advanced features including document clustering, coherence-based optimization, storyline extraction, and explainable AI components that provide interpretable insights into narrative connections. NMVT supports both directed analysis (connecting specific events) and exploratory analysis (discovering emerging storylines). By enabling analysts to make sense of large document collections, NMVT addresses critical challenges in intelligence analysis, computational journalism, and misinformation research, allowing users to effectively <em>connect the dots</em> between seemingly unrelated events. The system has been successfully demonstrated on news data by extracting coherent narrative structures that capture both main storylines and alternative perspectives. Case studies show that NMVT’s semantic interaction capabilities enable analysts to refine narratives based on domain expertise, while the explainable AI components increase trust in the system’s outputs.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"32 ","pages":"Article 102377"},"PeriodicalIF":2.4000,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Narrative Maps Visualization Tool (NMVT): An interactive narrative analytics system based on the narrative maps framework\",\"authors\":\"Brian Keith Norambuena\",\"doi\":\"10.1016/j.softx.2025.102377\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>The <strong>Narrative Maps Visualization Tool</strong> (NMVT) is an interactive visual analytics system designed to help analysts understand complex narratives from collections of text documents. NMVT leverages graph-based representations to extract and visualize coherent storylines, showing how events connect over time. The system integrates advanced features including document clustering, coherence-based optimization, storyline extraction, and explainable AI components that provide interpretable insights into narrative connections. NMVT supports both directed analysis (connecting specific events) and exploratory analysis (discovering emerging storylines). By enabling analysts to make sense of large document collections, NMVT addresses critical challenges in intelligence analysis, computational journalism, and misinformation research, allowing users to effectively <em>connect the dots</em> between seemingly unrelated events. The system has been successfully demonstrated on news data by extracting coherent narrative structures that capture both main storylines and alternative perspectives. Case studies show that NMVT’s semantic interaction capabilities enable analysts to refine narratives based on domain expertise, while the explainable AI components increase trust in the system’s outputs.</div></div>\",\"PeriodicalId\":21905,\"journal\":{\"name\":\"SoftwareX\",\"volume\":\"32 \",\"pages\":\"Article 102377\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2025-09-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"SoftwareX\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2352711025003437\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"SoftwareX","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352711025003437","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
Narrative Maps Visualization Tool (NMVT): An interactive narrative analytics system based on the narrative maps framework
The Narrative Maps Visualization Tool (NMVT) is an interactive visual analytics system designed to help analysts understand complex narratives from collections of text documents. NMVT leverages graph-based representations to extract and visualize coherent storylines, showing how events connect over time. The system integrates advanced features including document clustering, coherence-based optimization, storyline extraction, and explainable AI components that provide interpretable insights into narrative connections. NMVT supports both directed analysis (connecting specific events) and exploratory analysis (discovering emerging storylines). By enabling analysts to make sense of large document collections, NMVT addresses critical challenges in intelligence analysis, computational journalism, and misinformation research, allowing users to effectively connect the dots between seemingly unrelated events. The system has been successfully demonstrated on news data by extracting coherent narrative structures that capture both main storylines and alternative perspectives. Case studies show that NMVT’s semantic interaction capabilities enable analysts to refine narratives based on domain expertise, while the explainable AI components increase trust in the system’s outputs.
期刊介绍:
SoftwareX aims to acknowledge the impact of software on today''s research practice, and on new scientific discoveries in almost all research domains. SoftwareX also aims to stress the importance of the software developers who are, in part, responsible for this impact. To this end, SoftwareX aims to support publication of research software in such a way that: The software is given a stamp of scientific relevance, and provided with a peer-reviewed recognition of scientific impact; The software developers are given the credits they deserve; The software is citable, allowing traditional metrics of scientific excellence to apply; The academic career paths of software developers are supported rather than hindered; The software is publicly available for inspection, validation, and re-use. Above all, SoftwareX aims to inform researchers about software applications, tools and libraries with a (proven) potential to impact the process of scientific discovery in various domains. The journal is multidisciplinary and accepts submissions from within and across subject domains such as those represented within the broad thematic areas below: Mathematical and Physical Sciences; Environmental Sciences; Medical and Biological Sciences; Humanities, Arts and Social Sciences. Originating from these broad thematic areas, the journal also welcomes submissions of software that works in cross cutting thematic areas, such as citizen science, cybersecurity, digital economy, energy, global resource stewardship, health and wellbeing, etcetera. SoftwareX specifically aims to accept submissions representing domain-independent software that may impact more than one research domain.