Gerhard Backfried

A General Framework for Using Social and Traditional Media During Natural Disasters: QuOIMA and the Central European Floods of 2013

Traditional media have a long history in covering natural disasters and crises. In many instances, these media remain major providers of information about an event. In recent years, however, information about natural disasters has increasingly been disseminated on a significant scale via Social Media platforms. These media provide new, additional and complementary angles on events and, combined with traditional media, produce a more complete spectrum of coverage. We present an approach, combining information from across the different kinds of media—traditional as well as social—and also across multiple languages, providing opportunities for first responders and decision makers to gain improved situational awareness and allowing for improved disaster relief, support, mitigation and resilience measures. The approach is put into context by relating it to a long-term strategic model including horizon-scanning and risk-management activities and a 5-phase disaster model forming the basis for information gathering and dissemination activities. To illustrate the research efforts the QuOIMA (Quelloffene Integrierte Multimedia Analyse) project, based on the pillars of cross-media, multimedia, and multilingual processing and representing major aspects of the general framework is presented. QuOIMA focuses on the information gathering aspects from the point of view of a first responder and crisis manager or -communicator rather than the management of active (outgoing) communication. Initial findings on data collected during the 2013 Central European floods are reported and discussed.

An SVM Plait for Improving Affect Recognition in Intelligent Tutoring Systems

Usually, in intelligent tutoring systems the task sequencing is done by means of expert and domain knowledge. In a former work we presented a new efficient task sequencer without using the expensive expert and domain knowledge. This task sequencer only uses former performances and decides about the next task according to Vygotskys Zone of Proximal Development, that is to neither bore nor frustrate the student. We aim to support this task sequencer by a further automatically to gain information, namely students affect recognized from his speech input. However, the collection of the data from children needed for training an affect recognizer in this field is challenging as it is costly and complex and one has to consider privacy issues carefully. These problems lead to small data sets and limited performances of classification methods. Hence, in this work we propose an approach for improving the affect recognition in intelligent tutoring systems, which uses a special structure of several support vector machines with different input feature vectors. Furthermore, we propose a new kind of features for this problem. Different experiments with two real data sets show, that our approach is able to improve the classification performance on average by 49% in comparison to using a single classifier.

Integration of Media Sources for Situation Analysis in the Different Phases of Disaster Management: The QuOIMA Project

In this paper we describe work in progress on a cross-media content analysis approach and framework, which is currently being developed within the QuOIMA project. We describe the role of media, and how possible links between social and traditional media and terminology and communication patterns are envisioned to be connected to the different phases of a disaster model. The paper continues with a discussion of potential benefits for decision makers and planners and concludes with an outlook on further planned activities and developments.

Fitting German into N-Gram Language Models

We report on a series of experiments addressing the fact that German is less suited than English for word-based n-gram language models. Several systems were trained at different vocabulary sizes using various sets of lexical units. They were evaluated against a newly created corpus of German and Austrian broadcast news.

SentiSAIL: Sentiment Analysis in English, German and Russian

Sentiment analysis has been well in the focus of researchers in recent years. Nevertheless despite the considerable amount of literature in the field the majority of publications target the domains of movie and product reviews in English. The current paper presents a novel sentiment analysis method, which extends the state-of-the-art by trilingual sentiment classification in the domains of general news and particularly the coverage of natural disasters in general news. The languages examined are English, German and Russian. The approach targets both traditional and social media content. The extensive experiments demonstrate that the performance of the proposed approach outperforms human annotators, as well as the original method, on which it is built and extended.

Pharos: an audiovisual search platform

1. THE PHAROS PLATFORM AND DEMO PHAROS [1] is an Integrated Project aimed at building a platform for advanced audiovisual search applications. The Consortium comprises 12 partners from 9 European countries. PHAROS unbundles the functionalities of an audiovisual search engine into an open service-based ecosystem, where content can be submitted to customized analysis pipelines, third-party annotation components can be plugged-in, and content based search engines can be registered. PHAROS enables a variety of application scenarios, from content acquisition and enrichment, to annotation fusion, to multi-modal queries. Figure 1 shows the architecture of PHAROS, which supports two main process: Content Caption and Refinement (CCR) executes flow of operators on the captured content and produces XML metadata (subsequently indexed by a core XML search engine) and derived artifacts(used for similarity querying and result presentation); Query Execution and Result Presentation (QUIRP) accepts a user’s query (by keyword, by image similarity, by audio similarity, by video similarity), expands it with user’s profile and social information, brokers its execution on the registered search engines, and presents results in a Rich Internet Interface. The demo exploits the online access to the PHAROS platform for an in-depth tour of: content acquisition, design and

Cross-Media Analysis for Communication during Natural Disasters

In this paper we describe the role of media in the context of natural disasters. Traditional media have a long history in covering disasters and will continue to be a major provider of information in the future. In recent years, however there has been a significant change: information about natural disasters has increasingly been disseminated on a large scale on social media platforms. These media are typically faster but may be less reliable. They provide additional and complementary angles on events and, combined with traditional media, provide a wider spectrum of coverage. We argue that cross-media information combined with multi-lingual data provides huge opportunities for first-responders and decision makers to gain improved situational awareness allowing for improved disaster relief, support, mitigation and resilience measures.

Next Generation Data Fusion Open Source Intelligence (OSINT) System Based on MPEG7

We describe the Sail Labs Media Mining System which is capable of processing vast amounts of data typically gathered from open sources in unstructured form. The data are processed by a set of components and the output is produced in MPEG7 format. The origin and kind of input may be as diverse as a set of satellite receivers monitoring TV stations or textual input from web-pages or RSS-feeds. A sequence of processing steps analyzing the audio, video and textual content of the input is carried out. The resulting output is made available for search and retrieval, analysis and visualization on a next generation Media Mining Server. Access to the system is web-based; the system can serve as a search platform across open, closed or secured networks. Data may also be extracted and exported and thus be made available in airgap networks. The Media Mining System can be used as a tool for situational awareness, information sharing and risk assessment.

Sentiment Analysis of Media in German on the Refugee Crisis in Europe

Since the summer of 2015, the refugee crisis in Europe has grown to be one of the biggest challenges Europe has faced since WW2. The development of this humanitarian crisis are the topic of discussions throughout Europe and covered by media on a daily basis. Germany in particular has been the focus of migration. Over time, in Germany and the neighboring German speaking countries a shift could be observed, from the initial hospitable Willkommenskultur (welcome culture), to more reserved and skeptical points of view. These factors - Germany as the prime-destination for migrants, as well as a shift in public perception and media coverage - are the motivation for our analysis. The current article investigates the coverage of this crisis on traditional and social media, employing sentiment analysis to detect tendencies and relates these to real-world events. To this end, sentiment analysis was applied to textual documents of a data-set collected from relevant and highly circulated German, Austrian and Swiss traditional media sources and from social media in the course of six months from October 2015 to March of 2016.

Towards a generic data-model for cross-media communication during disasters & crises: Proposed framework for classification of platforms and technologies

In this paper we present an approach to classify entities involved in cross-media crisis communication in a generic way. Due to the interdisciplinary nature of the field, some foundations regarding the terminology involved are laid out. Based on this terminology, a faceted classification scheme is proposed, linking technologies and platforms. The framework covers traditional and Social Media platforms and allows for rapid positioning of media platforms as well as the identification of requirements regarding the technologies involved.