COST Action Training School in Computational Opinion Analysis - COpA
We are thrilled to announce the first OPINION COST Action Training School in Computational Opinion Analysis. The meeting will take place in Salamanca, Spain, from June 13 to 14, 2024.
First Day, June 13
8:30-9:00 Registration and coffee
9:00-9:30 Presentation of the Training School (Carlos Arcila Calderon)
9:35-12:15 Parallel workshops for Coding (R & Python) (Mariken van der Velden R - Aleksander Tomasevic Python)
12:15-12:30 Break
12:30-13:20 Inspiring examples of text analysis for opinion research (Christian Baden & Mariken van der Velden)
13:20-15:00 Lunch
15:00-17:30 Processing text and text as data (Valerie Hase)
Second Day, June 14
8:30-9:00 coffee
9:00-10:30 Lexicon-based approaches (Johannes Gruber)
10:30-10:45 Break
10:45-12:15 Topic Modeling (Valerie Hase)
12:15-12:30 Break
12:30-13:20 Machine Learning for opinion research (Damian Trilling)
13:20-15:00 Lunch
15:00-16:45 Supervised text classification (Damian Trilling, Johannes Gruber)
16:45-17:15 Conclusion (looking ahead) and evaluation (Carlos Arcila Calderon)
Instructors
Carlos Arcila Calderón
Professor at the Department of Sociology and Communication at the University of Salamanca (Spain). Member of the Audiovisual Content Observatory (OCA). Editor of the Electronic Yearbook of Social Communication Studies "Dissertations". European Doctorate in "Communication, Social Change and Development" from the Complutense University of Madrid. Master in Data Science and Master in Journalism, both from the Universidad Rey Juan Carlos (URJC). He has been a professor at the Universidad del Rosario (Colombia), Universidad del Norte (Colombia), Universidad de Los Andes (ULA) (Venezuela); post-doctoral researcher at the URJC; and associate researcher at the Universidad Católica Andrés Bello (UCAB) (Venezuela). He has also been visiting professor at the Universidad Nacional de Educación a Distancia (UNED) (Spain), Universidad de la Sabana (Colombia), Universidad de Santiago de Compostela (Spain), Universidad Mayor (Chile) and Universidade Estadual Paulista (Brazil).
Christian Baden
Christian Baden is Associate Professor at the Department of Communication and Journalism at the Hebrew University of Jerusalem, affiliated with the Center for Interdisciplinary Data Science Research (CIDR), and Paul F. Lazarsfeld Guest Professor at the Vienna University's Faculty of Social Sciences. His research focuses on dynamic processes of meaning negotiation, contestation and consensus formation in public discourse, with specific attention to the role of framing, cultural resonance, meaning multiplicity, and diversity of presented viewpoints. Integrating computational and manual, quantitative and qualitative approaches, his work has proposed novel strategies for the operational modeling of complex semantic constructs in evolving natural discourse. Specifically, his work aims to illuminate challenges to measurement validity, nuance and accountability that arise from available methodological strategies and computational technologies in social science text analysis. Christian Baden chairs the European COST network OPINION, which brings together researchers across countries and disciplines to advance the study of opinionated text.
Valerie Hase
Dr. Valerie Hase is a postdoctoral researcher at the Department of Media and Communication at LMU Munich, Germany. She holds an M.Sc. in Social Research Methods from LSE and a Ph.D. in communication research from the University of Zurich. Her research focuses on automated content analysis, digital trace data, biases in CCS, and digital journalism.
Damian Trilling
Damian Trilling is professor of journalism studies at Vrije Universiteit Amsterdam. He is an expert on computational social science and co-authored (with Wouter van Atteveldt and Carlos Arcila calderón) a textbook on "Computational Analysis of Communication" (https://cssbook.net/). His research interests center around the question how news and information is consumed and spread in the contemporary media environment. For this, he uses a wide range of innovative methods. In the context of COST OPINION, he is especially interested in how more subtle constructs (like opinions voiced in texts) can be measured in a reliable and scalable way. He has been teaching courses on automated content analysis using Python for more than 10 years and regularly gives guest lectures, seminars, and courses on this at various institutions.
Mariken van der Velden
I am an Associate Professor of Political Communication in the Department of Communication Science at the Vrije Universiteit Amsterdam. I received my PhD in Political Science from the Vrije Universiteit Amsterdam. Before joining the Department of Communication Science, I was a postdoctoral researcher at the Institute of Political Science at the University of Zurich, and visiting researcher of the Departments of Political Science at the University of North Carolina, Chapel Hill and the University of Oxford. My research interest comprise the areas of political communication, political behavior, and computational social science. I am motivated by key societal challenges that face democracies today, such as the crisis of representative democracy and increasing political fragmentation. Specifically, I apply advanced computational approaches to study the communication and rhetoric of politicians, and how this affects political decision making and its electoral consequences in multi-party systems. In my current work, I examine the legitimacy of political decision-making.
Aleksandar Tomašević
Aleksandar Tomašević is an Assistant Professor at the Department of Sociology, University of Novi Sad in Serbia. He obtained his PhD in 2019 from the same university. His research interests are centered around applying and developing statistical and computational methods across different social sciences (psychology, communication science, political science, sociology). The majority of his published works belong to the field of network psychometrics or computational social science. He is proficient in both R and Python. In 2022, he was a Fulbright Visiting Scholar at the University of Virginia, where he worked on developing the transforEmotion R package for sentiment analysis and emotion recognition in images and video.
Johannes B. Gruber
I am a Post-Doc Researcher at the Department of Communication Science at the ~~University of Amsterdam~~ Vrije Universiteit Amsterdam working on the NEWSFLOWS project (the project was recently moved to the VU). Previously, I worked at the Department of Communication Science at Vrije Universiteit Amsterdam within the OPTED project and a focus on text as data methods and creating open source software tools to make these methods easily accessible and reproducible. Previously, I worked as Post-Doc Researcher at the Chair for Digital Democracy at the European New School of Digital Studies (ENS), European University Viadrina Foundation Frankfurt (Oder). In 2021, I passed my PhD in Politics at the University of Glasgow. In my PhD project, I scrutinised how the media in the UK portrays protest events. Most literature about the topic assumes that the messages of protests are delegitimised by the media through routinised framing, i.e. a focus on disruption by and deviance of protesters. In my project, I collected all newspaper articles published in selected UK newspaper outlets that mention a protest in the UK over a 26 year period (1992-2017; N > 27,000) and analysed the content using an innovative approach to framing analysis that combines best-practice manual coding techniques with supervised machine learning. After a detour that included a Master on Political Theory, I realised during my Master in Political Communication — which was originally planned as a semester abroad — how much I love working with data. Especially R, the free software environment for statistical computing and graphics, is captivating much of my attention nowadays and has helped me to combine my two most long-standing passions: Political Science and fiddling with computers. I’m using R to do nearly everything.
