TU Darmstadt / ULB / TUbiblio

Storyfinder: Personalized Knowledge Base Construction and Management by Browsing the Web

Remus, Steffen and Kaufmann, Manuel and Ballweg, Kathrin and von Landesberger, Tatiana and Biemann, Chris (2017):
Storyfinder: Personalized Knowledge Base Construction and Management by Browsing the Web.
pp. 2519-2522, 2017 ACM Conference on Information and Knowledge Management - CIKM '17, Singapore, 06.-10.Nov., 2017, DOI: 10.1145/3132847.3133186,
[Conference or Workshop Item]

Abstract

This paper presents Storyfinder, an application which consists of a browser plugin and a web server backend with the goal to highlight and manage the information contained in web pages by combining techniques from natural language processing and visual analytics. Webpages are analyzed while visiting them by means of natural language processing components, and metadata in the form of named entities and keywords are extracted and stored for further reference. The extracted information is instantaneously highlighted in the web page and stored in a graph of entities and relations. The graph can be inspected and modified. The investigational scope can be set to a single web page, multiple web pages, or the complete set of analyzed web pages in a user's history. The graph view is designed to adhere to standards of visual analytics and information visualization. Storyfinder is available as an open source application. Its benefit for information access is evaluated in a small user study.

Item Type: Conference or Workshop Item
Erschienen: 2017
Creators: Remus, Steffen and Kaufmann, Manuel and Ballweg, Kathrin and von Landesberger, Tatiana and Biemann, Chris
Title: Storyfinder: Personalized Knowledge Base Construction and Management by Browsing the Web
Language: English
Abstract:

This paper presents Storyfinder, an application which consists of a browser plugin and a web server backend with the goal to highlight and manage the information contained in web pages by combining techniques from natural language processing and visual analytics. Webpages are analyzed while visiting them by means of natural language processing components, and metadata in the form of named entities and keywords are extracted and stored for further reference. The extracted information is instantaneously highlighted in the web page and stored in a graph of entities and relations. The graph can be inspected and modified. The investigational scope can be set to a single web page, multiple web pages, or the complete set of analyzed web pages in a user's history. The graph view is designed to adhere to standards of visual analytics and information visualization. Storyfinder is available as an open source application. Its benefit for information access is evaluated in a small user study.

Uncontrolled Keywords: Visualization, Interaction, Texture analysis, Natural language processing
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Event Title: 2017 ACM Conference on Information and Knowledge Management - CIKM '17
Event Location: Singapore
Event Dates: 06.-10.Nov., 2017
Date Deposited: 04 May 2020 12:55
DOI: 10.1145/3132847.3133186
Official URL: https://doi.org/10.1145/3132847.3133186
Corresponding Links:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details