Plüss, Brian, Fabian Sperrle, Valentin Gold, Mennatallah El-Assady, Annette Hautli-Janisz, Katarzyna Budzysnka, and Chris Reed. "Augmenting Public Deliberations through Stream Argument Analytics and Visualisations" In: Proceedings of Leipzig symposium on Visualization In Applications (LEVIA), 2018, pp. 1–9. Leipzig, Germany.
Public deliberations are organised by governments and other large institutions to take the views of citizens around controversial issues. Increasing public demand and the associated burden on public funding make the quality of public deliberation events and their outcomes critical to modern democracies. This paper focuses on technology developed around streams of computational argument data intended to inform and improve deliberative communication in real time. Combining state-of- the-art speech recognition, argument mining, and analytics, we produce dynamic, interactive visualisations intended for non-experts, deployed incrementally in real time to deliberation participants via large screens, hand-held and personal computing devices. The goal is to bridge the gap between theoretical criteria on deliberation quality from the political sciences and objective analytics calculated automatically from computable argument data in actual public deliberations, presented as a set of visualisations which work on stream data and are simple, yet informative enough to make a positive impact on deliberative outcomes.
Plüss, Brian, Mennatallah El-Assady, Fabian Sperrle, Valentin Gold, Katarzyna Budzysnka, Annette Hautli-Janisz, and Chris Reed. "ADD-up: Visual Analytics for Augmented Deliberative Democracy". In Modgil, Sanjay, Katarzyna Budzynska, and John Lawrence (Eds.) Computational Models of Argument. Proceedings of COMMA 2018. Vol. 305, pp. 471–472. IOS Press, Amsterdam.
Gold, Valentin, Brian Plüss, Mennatallah El-Assady, Fabian Sperrle, Katarzyna Budzynska, Annette Hautli-Janisz, and Chris Reed. "Towards Deliberation Analytics: Stream Processing of Argument Data for Deliberative Communication" Argumentation and Society Workshop, Computational Model of Argument (COMMA) Conference, pp. 1–3, Warsaw, Poland.
Gold, Valentin, Mennatallah El-Assady, and Christian Rohrdantz. "Explorative visuelle Textanalyse von politischen Debatten" In Blätte, Andreas, Joachim Behnke, Kai-Uwe Schnapp, and Claudius Wagemann (Eds.), Computational Social Science. Die Analyse von Big Data, pp. 211–234, Nomos, Baden-Baden, 2018.
Gold, Valentin, Mennatallah El-Assady, Annette Hautli-Janisz, Tina Bögel, Christian Rohrdantz, Miriam Butt, Katharina Holzinger, and Daniel A.Keim. "Visual Linguistic Analysis of Political Discussions: Measuring Deliberative Quality". Digital Scholarship in the Humanities 32(1), pp. 141–158. 2017.
This article reports on a Digital Humanities research project which is concerned with the automated linguistic and visual analysis of political discourses with a particular focus on the concept of deliberative communication. According to the theory of deliberative communication as discussed within political science, political debates should be inclusive and stakeholders participating in these debates are required to justify their positions rationally and respectfully and should eventually defer to the better argument. The focus of the article is on the novel interactive visualizations that combine linguistic and statistical cues to analyze the deliberative quality of communication automatically. In particular, we quantify the degree of deliberation for four dimensions of communication: Participation, Respect, Argumentation and Justification, and Persuasiveness. Yet, these four dimensions have not been linked within a combined linguistic and visual framework, but each single dimension helps determining the degree of deliberation independently from each other. Since at its core, deliberation requires sustained and appropriate modes of communication, our main contribution is the automatic annotation and disambiguation of causal connectors and discourse particles.
Gold, Valentin and Mennatallah El-Assady. "Visualisierung von deliberativer Kommunikation: Möglichkeiten und Potenziale für Planungs- und Beteiligungsverfahren." In Bade, Korinna, Matthias Pietsch, Susanne Raabe, and Lars Schütz (Eds.), Technologische Trends im Spannungsfeld von Beteiligung – Entscheidung – Planung. Fachforum Digitales Planen und Gestalten, pp. 39–52, Shaker Verlag, Aachen. 2016.
Hautli-Janisz, Annette, Mennatallah El-Assady, Valentin Gold, Miriam Butt, Katharina Holzinger, and Daniel A. Keim. "Interactive Visual Analysis of Transcribed Multi-Party Discourse". In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL): Systems Demonstrations, pp. 49–54, Stroudsburg, PA. 2017.
We present the first web-based Visual Analytics framework for the analysis of multi-party discourse data using verbatim text transcripts. Our framework supports a broad range of server-based processing steps, ranging from data mining and statistical analysis to deep linguistic parsing of English and German. On the client-side, browser-based Visual Analytics components enable multiple perspectives on the analyzed data. These interactive visualizations allow exploratory content analysis, argumentation pattern review and speaker interaction modeling.
El-Assady, Mennatallah, Valentin Gold, Markus John, Thomas Ertl, and Daniel A. Keim. "Visual Text Analytics in Context of Digital Humanities", In: IEEE Information Visualization Conference (InfoVis), Workshop on Visualization for the Digital Humanities (VIS4DH), pp. 1–5, Baltimore, MD, USA. 2016.
Digital Humanities (DH) research brings together scholars from different disciplines to work on tackling a common research challenge. Hence, DH-projects have to overcome common challenges of multi-disciplinary research, such as methodological differences or communication issues. However, in contrast to interdisciplinary collaborations from related fields of science, in the digital humanities, a gap between qualitative scholarship traditions and quantitative data-driven research has to be bridged to achieve a common goal. With this position paper, we aim at starting a discussion between the various involved disciplines in the digital humanities on how to approach the problem-solving process in DH-projects. Based on our experience in different visual text analytics projects and extensive two years of discussions, we propose an abstract conceptual workflow as a best practice for digital humanities projects.
El-Assady, Mennatallah, Valentin Gold, Carmela Acevedo, Christopher Collins, and Daniel A. Keim. "ConToVi: Multi-Party Conversation Exploration using Topic-Space Views", Computer Graphics Forum 35(5), pp. 431–440. 2016.
We introduce a novel visual analytics approach to analyze speaker behavior patterns in multi-party conversations. We propose Topic-Space Views to track the movement of speakers across the thematic landscape of a conversation. Our tool is designed to assist political science scholars in exploring the dynamics of a conversation over time to generate and prove hypotheses about speaker interactions and behavior patterns. Moreover, we introduce a glyph-based representation for each speaker turn based on linguistic and statistical cues to abstract relevant text features. We present animated views for exploring the general behavior and interactions of speakers over time and interactive steady visualizations for the detailed analysis of a selection of speakers. Using a visual sedimentation metaphor we enable the analysts to track subtle changes in the flow of a conversation over time while keeping an overview of all past speaker turns. We evaluate our approach on real-world datasets and the results have been insightful to our domain experts.
Gold, Valentin, Annette Hautli-Janisz, and Katharina Holzinger. "VisArgue. Analyse und Visualisierung von politischen Verhandlungen". Zeitschrift für Konfliktmanagement 3(16), pp. 98–99. 2016.
Politikwissenschaftler, Linguisten und Informatiker der Universität Konstanz haben interdisziplinär drei Jahre lang im Rahmen eines Projekts ``VisArgue`` eine Software entwickelt, die politische Kommunikation analysiert, visualisiert und Rückschlüsse auf deren Effektivität zulässt. Erprobt wurden die Tools am Beispiel von Stuttgart 21.
El-Assady, Mennatallah, Valentin Gold, Annette Hautli-Janisz, Wolfgang Jentner, Miriam Butt, Katharina Holzinger, and Daniel A. Keim. "VisArgue – A Visual Text Analytics Framework for the Study of Deliberative Communication". In Širinić, Daniela, Jan Šnajder, Zoltán Fazekas and Shaun Bevan (Eds.), Proceedings of the International Conference on the Advances in Computational Analysis of Political Text (PolText2016), pp. 31–36, University of Zagreb, Zagreb, Croatia. 2016.
For the last two decades, deliberative democracy has been intensively debated within political science and other related fields. Only recently, deliberation research has experienced a computational turn. In this paper, we present a linguistic and visual framework for the study of deliberative communication. The framework includes a range of visual analytics approaches to support research into deliberation. In particular, we propose a range of visualizations for highlighting deliberative patterns over time, speakers, and debates.
Gold, Valentin, Annette Hautli-Janisz, Katharina Holzinger, and Mennatallah El- Assady. "VisArgue: Analysis and Visualization of Deliberative Political Communication". Political Communication Report, Special Issue on ‘Fresh Perspectives in Deliberation Research 26.1-2. 2016.
Butt, Miriam, Gerhard Heyer, Katharina Holzinger, Cathleen Kantner, Daniel A.Keim, Jonas Kuhn, Gary Schaal, André Blessing, Sebastian Dumm, Mennatallah El-Assady, Valentin Gold, Matthias Lemke, Maike Müller, Andreas Niekler, Maximilian Overbeck, and Gregor Wiedemann. "Argumentanalyse in digitalen Textkorpora" In Digital Humanities im deutschsprachigen Raum. 2016.
Die Extrahierung und Annotation von Argumentationsstrukturen hat im Bereich der automatischen Diskursanalyse in den letzten Jahren an Bedeutung gewonnen, sei es in juristischen Dokumenten (Mochales / Moens 2011; Bach et al. 2013), wissenschaftlichen Texten (Kirschner et al. 2015), Zeitungsartikeln (Feng / Hirst 2011) oder Online-Diskussionen (Bex et al. 2013, 2014; Oraby et al. 2015). Vor diesem Hintergrund haben sich in den vergangenen Jahren die drei interdisziplinären Projekte e-Identity, ePol und VisArgue im Rahmen der eHumanities-Förderlinie des BMBF mit der semi-automatischen Identifikation und Analyse von Argumenten auseinandergesetzt.
Gold, Valentin, Christian Rohrdantz, and Mennatallah El-Assady. "Exploratory Text Analysis using Lexical Episode Plots." In: Bertini, E., J. Kennedy and E. Puppo (Eds.), Eurographics Conference on Visualization (EuroVis) – Short Papers, pp. 1–5, The Eurographics Association. 2015.
In this paper, we present Lexical Episode Plots, a novel automated text-mining and visual analytics approach for exploratory text analysis. In particular, we first describe an algorithm for automatically annotating text regions to examine prominent themes within natural language texts. The algorithm is based on lexical chaining to find spans of text in which the frequency of a term is significantly higher than its average in the document. In a second step we present an interactive visualization supporting the exploration and interpretation of Lexical Episodes. The visualization links higher-level thematic structures with content-level details. The methodological capabilities of our approach are illustrated by analyzing the televised US presidential election debates.
Gold, Valentin. "Partitioning ethnic groups and their members: Explaining variations in satisfaction with democracy in Africa." Peace Economics, Peace Science and Public Policy (PEPS) 18(3), pp. 1–13. 2012.
This article examines the conditions that influence citizens' satisfaction with democracy in Africa. In the analysis, individual, ethnic group, and national context determinants are combined in a multilevel model allowing a comparative analysis over time, countries, ethnic groups, and individuals. Using Afrobarometer survey data along with ethnic group-level and national-level data, I show that factors shaping citizens' satisfaction can be found on each contextual level. To a large extent, perceived economic and political inequalities between ethnic groups explain variations in citizens' satisfaction.
Gold, Valentin und Roos Haer. "The Diffusion of Atrocities: A Spatial Analysis on the Role of Refugees." Working Paper 5/2011, Network of European Peace Scientists (NEPS) Working Paper Series. 2011.
A range of theories have attempted to explain the existing variation in the level of civilian victimization across countries. To date, most of these theories have been focused on the influence of the strategic environment in which These atrocities take place or they have emphasized the organizational difference between the involved actors. Less attention is, however, devoted to the possible spillover effect of these atrocities. This study fills this niche by analyzing the role of refugee flows on the diffusion of atrocities. We do so through statistical analyses of refugee from neighboring countries and the occurrence of atrocities in Africa during the period of 1995-2010, controlling for other possible explanation of atrocities. Our study is the first to systematically examine the effect of refugees on the likelihood of atrocities in refugee-recipient states. We do this by employing a spatial lag model with a temporal component with two different spatial weighting matrices. The preliminary results of the analyses suggest that refugees indeed influence the amount of atrocities and that atrocities are spatially determined. Furthermore, civilian killings is primarily caused by strategic factors such as the number of atrocities and rebel groups in neighboring state and the number of rebel groups and battle deaths in the host country.