Abstract

Media data has been the subject of large scale analysis with applications of text mining being used to provide overviews of media themes and information flows. Such information extracted from media articles has also shown its contextual value of being integrated with other data, such as criminal records and stock market pricing. In this work, we explore linking textual media data with curated secondary textual data sources through user-guided semantic lexical matching for identifying relationships and data links. In this manner, critical information can be identified and used to annotate media timelines in order to provide a more detailed overview of events that may be driving media topics and frames. These linked events are further analyzed through an application of causality modeling to model temporal drivers between the data series. Such causal links are then annotated through automatic entity extraction which enables the analyst to explore persons, locations, and organizations that may be pertinent to the media topic of interest. To demonstrate the proposed framework, two media datasets and an armed conflict event dataset are explored.

Original languageEnglish (US)
JournalIEEE Transactions on Visualization and Computer Graphics
DOIs
StateAccepted/In press - Sep 13 2017

Fingerprint

Semantics
Costs
Financial markets

Keywords

  • Causality Modeling
  • Media
  • Media Annotation
  • Semantic Similarity
  • Semantics
  • Social Media
  • Social network services
  • Time series analysis
  • Tools
  • Visual analytics
  • Visual Analytics

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Cite this

A Visual Analytics Framework for Identifying Topic Drivers in Media Events. / Lu, Yafeng; Wang, Hong; Landis, Steven; Maciejewski, Ross.

In: IEEE Transactions on Visualization and Computer Graphics, 13.09.2017.

Research output: Contribution to journalArticle

@article{6ab792b03cc4485d85a9d42687720f60,
title = "A Visual Analytics Framework for Identifying Topic Drivers in Media Events",
abstract = "Media data has been the subject of large scale analysis with applications of text mining being used to provide overviews of media themes and information flows. Such information extracted from media articles has also shown its contextual value of being integrated with other data, such as criminal records and stock market pricing. In this work, we explore linking textual media data with curated secondary textual data sources through user-guided semantic lexical matching for identifying relationships and data links. In this manner, critical information can be identified and used to annotate media timelines in order to provide a more detailed overview of events that may be driving media topics and frames. These linked events are further analyzed through an application of causality modeling to model temporal drivers between the data series. Such causal links are then annotated through automatic entity extraction which enables the analyst to explore persons, locations, and organizations that may be pertinent to the media topic of interest. To demonstrate the proposed framework, two media datasets and an armed conflict event dataset are explored.",
keywords = "Causality Modeling, Media, Media Annotation, Semantic Similarity, Semantics, Social Media, Social network services, Time series analysis, Tools, Visual analytics, Visual Analytics",
author = "Yafeng Lu and Hong Wang and Steven Landis and Ross Maciejewski",
year = "2017",
month = "9",
day = "13",
doi = "10.1109/TVCG.2017.2752166",
language = "English (US)",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - A Visual Analytics Framework for Identifying Topic Drivers in Media Events

AU - Lu, Yafeng

AU - Wang, Hong

AU - Landis, Steven

AU - Maciejewski, Ross

PY - 2017/9/13

Y1 - 2017/9/13

N2 - Media data has been the subject of large scale analysis with applications of text mining being used to provide overviews of media themes and information flows. Such information extracted from media articles has also shown its contextual value of being integrated with other data, such as criminal records and stock market pricing. In this work, we explore linking textual media data with curated secondary textual data sources through user-guided semantic lexical matching for identifying relationships and data links. In this manner, critical information can be identified and used to annotate media timelines in order to provide a more detailed overview of events that may be driving media topics and frames. These linked events are further analyzed through an application of causality modeling to model temporal drivers between the data series. Such causal links are then annotated through automatic entity extraction which enables the analyst to explore persons, locations, and organizations that may be pertinent to the media topic of interest. To demonstrate the proposed framework, two media datasets and an armed conflict event dataset are explored.

AB - Media data has been the subject of large scale analysis with applications of text mining being used to provide overviews of media themes and information flows. Such information extracted from media articles has also shown its contextual value of being integrated with other data, such as criminal records and stock market pricing. In this work, we explore linking textual media data with curated secondary textual data sources through user-guided semantic lexical matching for identifying relationships and data links. In this manner, critical information can be identified and used to annotate media timelines in order to provide a more detailed overview of events that may be driving media topics and frames. These linked events are further analyzed through an application of causality modeling to model temporal drivers between the data series. Such causal links are then annotated through automatic entity extraction which enables the analyst to explore persons, locations, and organizations that may be pertinent to the media topic of interest. To demonstrate the proposed framework, two media datasets and an armed conflict event dataset are explored.

KW - Causality Modeling

KW - Media

KW - Media Annotation

KW - Semantic Similarity

KW - Semantics

KW - Social Media

KW - Social network services

KW - Time series analysis

KW - Tools

KW - Visual analytics

KW - Visual Analytics

UR - http://www.scopus.com/inward/record.url?scp=85030264468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030264468&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2017.2752166

DO - 10.1109/TVCG.2017.2752166

M3 - Article

C2 - 28920902

AN - SCOPUS:85030264468

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

ER -