Interactive Authoring of Visual Timelines from Unstructured Text

Johanna Fulda, Matthew Brehmer, and Tamara Munzner

Abstract | Paper | Talk | Web application | Videos | Figures


We present TimeLineCurator, a browser-based authoring tool that automatically extracts event data from temporal references in unstructured text documents using natural language processing and encodes them along a visual timeline. Our goal is to facilitate the timeline creation process for journalists and others who tell temporal stories online. Current solutions involve manually extracting and formatting event data from source documents, a process that tends to be tedious and error prone. With TimeLineCurator, a prospective timeline author can quickly identify the extent of time encompassed by a document, as well as the distribution of events occurring along this timeline. Authors can speculatively browse possible documents to quickly determine whether they are appropriate sources of timeline material. TimeLineCurator provides controls for curating and editing events on a timeline, the ability to combine timelines from multiple source documents, and export curated timelines for online deployment. We evaluate TimeLineCurator through a benchmark comparison of entity extraction error against a manual timeline curation process, a preliminary evaluation of the user experience of timeline authoring, a brief qualitative analysis of its visual output, and a discussion of prospective use cases suggested by members of the target author communities following its deployment.


Interactive Authoring of Visual Timelines from Unstructured Text
To appear in IEEE Transactions on Visualization and Computer Graphics (TVCG).
Proceedings of IEEE Conference on Visual Analytics Science and Technology (VAST), Chicago, USA, 2015
[Pre-Print PDF] [BibTeX]

Web application

The Software-page documents and explains the functionality of TimeLineCurator in more detail. To test and use TimeLineCurator, you can check out the web application in its current version v0.4 (alpha).


This paper will be presented by Johanna Fulda in the Visual Analytics of Textual Data (II) session at 08:30 AM on Friday, Nov 30th, 2015 at IEEE VAST 2015.

Slides (4 MB PDF)
Slides (4 MB Keynote)


High-Resolution Figures

Click on a Figure to open in a new tab.

Fig. 1. Teaser image: The browser-based visual timeline authoring tool TimeLineCurator, showing a timeline of Scandinavian pop music, where each colour corresponds to a country; access the interactive timeline at http://goo.gl/0bHlvA.

Fig. 2: A walkthrough of the TimeLineCurator curation process. We demonstrate this process using unstructured document text from the "The Fall" section of the Wikipedia article on the Berlin Wall [69]. The resulting timeline can be accessed at http://goo.gl/SU1faP.

(a) Initially, the timeline is empty. Annotations in orange demarcate the four main views: Timeline View, List View, Document View, and Control Panel.
(b) Unstructured text is added via a popup dialog. Optionally, the document creation time can be specified below the input field.
(c) A timeline immediately after importing text, with many vague and uncurated dates. General timeline information can be modified when no event is selected.
(d) Event dates, title, and description can be adjusted when an event is selected, it can also be assigned to another track, enriched with images, or deleted.
(e) The curated timeline can be exported; the presentation view is a read-only version of the editing interface.

(f) The curated timeline can also be exported using the open-source tool TimelineJS.

Fig. 3. An abstract representation of TimeLineCurator's pipeline: (i) unstructured text input; (ii) an authoring environment; (iii) curated timeline output.

Fig. 4. Processing pipeline for TimeLineCurator.

Johanna Fulda
Last modified: Aug 15, 2015.