Analysis of (social) streams and graphs
Modern social media like micromessaging, web logs or social networks allow us to perform a large number of social media analyses, requiring architectures and systems for distributed realtime computations on (social) streams and graphs. The large number of participants (more than 2 billion active users of Facebook) and interactions (around 500 million messages on Twitter per day) as well as the public, often instantaneous availability of data allows us (but also require us) to analyze current events in “live” manner and also perform predictions.
Our research focuses on Information Diffusion, tracing and understanding on which ways a particular piece of information (like a message, a picture or a term) is spreading, which roles particular users are playing and how popularity is affected (“virality”).
Computing diffusion pathways in realtime enables new applications in areas such as online journalism since both sources and paths of information become traceable and the own influence can be understood precisely. In turn, this allows users to assess trust and relevance of information, which so far to be done manually and thus could not keep up with the volume of information and the speed of existing detection tools.
ANtIDOTE: Realtime Analysis of Information Diffusion for Trust and Relevance
Start date: 01.01.2019
End date: 31.12.2021
Funded by: DFG (Deutsche Forschungsgemeinschaft)
Local head of project: Prof. Dr. Peter M. Fischer
Local scientists: Prof. Dr. Peter M. Fischer
Modern social media like Twitter or Facebook encompass a significant and growing share of the population, which is actively using it to share messages. Given this broad coverage of the world as well as its fast reaction times, social media acts as a powerful ”social sensor”, while activities originating on social media can also have significant impact on the physical world.
While scalable methods have been developed to detect trends and events in such media, assessing the relevance of social media messages and their trustworthiness is mostly driven by manual, after-the-fact checking. One of the most important factor for such an assessment is an understanding of the information diffusion. A typical use case for such analyses is online journalism, where journalists a) need to understand where information came from and how it reached them b) whom information published by themselves influences and in which way c) how the overall diffusion process is proceeding.
Yet, existing work on analyzing information diffusion is centered on complex models with offline computations, making them unsuitable for real-time, large-scale analyses. In this project we aim to develop algorithms and systems to trace the spreading of information in social media that produce large scale, rapid data. The results of these analysis are then used to assess trustworthiness; the results are compared against complex, state-of-the-art methods.