[Invited Paper] Explain This to Me!

Abstract

This paper addresses a framework that facilitates the semi-automated authoring of already edited new stories available in the repository of a news corporation or a public broadcast video archive. The newly generated video explains the chronological development of a current event, such as the resignation of a Prime Minister. The aim is to facilitate a journalist with an audio-visual body based on which he/she can finalize the explanatory piece. The framework introduces techniques that exploit demoscopic data in form of polls for the development of the general story outline; the automatic retrieval of relevant material by using a combination of event templates and automatic news summarization over topic threads; and the generation of the final video by applying a set of trimming rules. Example generations are presented and discussed, and an outline of future work is presented.

Visual Analytics of Political Networks From Face-Tracking of News Video

“…News analysis has been a main target for visual analytics applications, for which the literature is prolific. The majority of related work explores text-based news data ( [6], [7], [8], [9], [10], [11], [12], [13], [14], [15]), the focus of which was often on event and topic analysis, to reveal stories to users. Although we wanted to differentiate our study from these by solely focusing on the cues we extract from the visual information of the videos, we also incorporated political affiliations in our design.…”

“…Although we wanted to differentiate our study from these by solely focusing on the cues we extract from the visual information of the videos, we also incorporated political affiliations in our design. It is important to note that the related studies somtimes incorporated external data such as demoscopic information [15] or sentiment analysis [7] sometimes in combination with geographical information [6].…”

“…It should also be noted that the studies by Luo et al [16], Itoh et al [18] and Ide et al [15] involved the same dataset we used with different purposes. Luo et al [16] presented users video excerpts from a news story, and the users could hop from one video to another based on their interests.…”

When face-tracking meets social networks: a story of politics in news videos

“…One of the most impressive approach on exploiting news data comes from (Ide and Nack 2013) in which the authors combine news topic threads and demoscopic information to retrieve videos and generate a new summary video to explain prime ministers’ resignations. A Natural Language Processing framework is designed in (Castillo et al 2013) to characterize news providers, programs, and newsmakers over many channels.…”

A Social Network Analysis of Face Tracking in News Video

“…Many interesting works approache news analysis in a data intensive way, from text analysis. One of the most impressive approach on exploiting news data comes from [9] in which the authors combine news topic threads and demoscopic information to retrieve videos and generate a new summary video to explain prime ministers' resignations. An NLP framework is designed in [10] to characterize news providers, programs, and newsmakers over many channels.…”