In my current position, I am heading the Social Computing & Finance Research Group at the Chair of Information Systems at the University of Freiburg in Freiburg. Previously, I obtained my Ph.D. in Information Systems from the same research institution. My research primarily focuses on data science methods and computational techniques for understanding human decision-making in the digital age. Current projects examine, for example, the role of social media (e.g. Twitter) in shaping public opinions regarding businesses and products. Related studies apply data mining techniques and quantitative text analysis to a broad selection of topics, including financial markets and recommender systems. Apart from these projects, I am a passionate programmer and interested in developing novel data science methods with high business value.
My research focuses on multi-disciplinary projects at the intersection of computer science, economics, and social sciences. The activities are directed towards a broad selection of topics with societal relevance, including social networks, financial markets, and recommender systems. For this purpose, I develop and apply data science methods and other computational techniques to operationalize human decision-making.
Research Focus: Social Media
I conduct research to understand and predict the reception and dissemination of online news in all its forms. This research branch utilizes large-scale data sources to investigate how feedback, comments or reviews on social platforms affect the decision-making of individuals, businesses, and organizations. Individual research aspects also address the interplay between Tweets and the reception of products and firms.
Research Focus: Finance
The availability of information forms the basis for financial decision-making. This research branch thus studies the reception and processing of financial news as a primary source of information for investors before exercising ownership in stocks. Among others, I employ state-of-the-art text mining algorithms in combination with historic stock market data to study how financial news in various forms impact the price formation on stock markets.
Research Focus: Text Mining
My research heavily relies on the analytical capabilities of processing and textual materials in various forms. For this purpose, I actively develop novel text mining methods that allow to operationalize the semantic orientation of textual materials. I am confident that the methodological innovations in this research stream will become important tools for researchers and practitioners.
A list of further projects can be found here.
This package performs model-free reinforcement learning in R. The implementation enables the learning of an optimal policy based on sample sequences consisting of states, actions and rewards. In addition, it supplies multiple predefined reinforcement learning algorithms, such as experience replay.
ReinforcementLearning on CRAN: https://cran.r-project.org/web/packages/ReinforcementLearning/index.html
This package performs a sentiment analysis of textual contents in R. The implementation utilizes various existing dictionaries, such as Harvard IV, or finance-specific dictionaries. Furthermore, it can also create customized dictionaries. The latter uses LASSO regularization as a statistical approach to select relevant terms based on an exogenous response variable.
SentimentAnalysis on CRAN: