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

Abstract

In the age of data processing, news videos are rich mines of information. After all, the news are essentially created to convey information to the public. But can we go beyond what is directly presented to us and see a wider picture? Many works already focus on what we can discover and understand from the analysis of years of news broadcasting. These analysis bring monitoring and understanding of the activity of public figures, political strategies, explanation and even prediction of critical media events. Such tools can help public figures in managing their public image, as well as support the work of journalists, social scientists and other media experts. News analysis can also be seen from the lens of complex systems, gathering many types of entities, attributes and interactions over time. As many public figures intervene in different news stories, a first interesting task is to observe the social interactions between these actors. Towards this goal, we propose to use video analysis to automatise the process of constructing social networks directly from news video archives. In this paper we are introducing a system deriving multiple social networks from face detections in news videos. We present preliminary results obtained from analysis of these networks, by monitoring the activity of more than a hundred public figures. We finally use these networks as a support for political studies and we provide an overview of the political landscape presented by the Japanese public broadcaster NHK over a decade of the 7 PM news archives.

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

“…This makes it possible to measure the co-appearance airtime. Unfortunately, as discussed in our previous publication [5], the data obtained were too sparse, and this network is by far not representative enough to conduct our visual analysis. However, we will keep this as a property of our links (Fig 2c ).…”

“…Detangler [13] uses the coordination of two networks to reduce the visual complexity induced by multiple types of entities and relationships in the semantics extracted from news. We introduced network analysis from video analysis [5] -although we found an interesting effort in generating networks of multimedia content for digital forensics [25] -and our previous study [5] was aimed at validating the relevance of this method for political network analysis during the early steps of our design.…”

“…Our first intermediary step was to validate which abstraction would be sufficient for political analysis. This was the main focus of our previous study [5]. We now summarize the methodology we used to derive and choose the right data abstraction.…”

“…As we discussed in our previous study [5], our face-track analysis provides multiple ways to measure an actor's activity in the political landscape formed by the news. The first measure, maybe the most natural one, is "airtime", i.e., how long a person appears on screen.…”

“…In a previous study [5], we discussed our investigation on how we could automatically form social networks from face B. Renoust, D. Le and S. Satoh are with the National Institute of Informatics (NII), Tokyo Japan. B. Renoust is also with the Japanese-French Laboratory for Informatics (JFLI) CNRS UMI 3527, Tokyo, Japan.…”