19/10/2020

TiCCo: Time-centric content exploration

Philip Hausner, Dennis Aumiller, Michael Gertz

Keywords: co-occurrence graph, text exploration, text analytics, temporal information, automatic timeline generation

Abstract: Time is a natural way to order information and can be utilized to summarize events and to construct a chronology of contents within a document collection in many application domains. Structuring the sequence of events along a timeline allows users to grasp information at-a-glance, which enables them to get familiar with a topic in only a short amount of time and can hence support the analysis of more complicated and heterogeneous textual data. The manual construction of timelines, however, is a tedious and error-prone task, leading to static timeline representations that limit users to a passive role. In this paper, TiCCo, an automated extraction pipeline from arbitrary English and German text collections, is provided and presented to the user in an interactive manner. This puts the user in an active role in which she not only absorbs knowledge, but also influences in which ways the information is presented to her. In-depth investigations of a specific point in time are augmented by utilizing time-centric co-occurrence graphs that further summarize information extracted from a document collection, and enable users to explore the chronology of events by allowing them to interact with the constructed graphs as well as the underlying documents.

The video of this talk cannot be embedded. You can watch it here:
https://dl.acm.org/doi/10.1145/3340531.3417432#sec-supp
(Link will open in new window)
 0
 0
 0
 0
This is an embedded video. Talk and the respective paper are published at CIKM 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd

Similar Papers