Document Actions

Research

Our research focuses on the application of computational techniques for understanding and predicting human behavior on digital platforms. Current research projects leverage data science methods, and machine learning to drive domain-specific decisions in a broad selection of business-relevant areas, including, but not limited to, data analytics for social media and electronic commerce, financial data science, and natural language processing for business applications.

Research Focus

Research Focus


Online Harms on Social Media

Social media is a fertile ground for misinformation and anti-social behavior, including online harassment, cyberbullying, and hate speech. Our research uses data science methods combined with large-scale datasets to better understand these phenomena and develop effective countermeasures.



Data Science for Business Applications 

We use state-of-the-art quantitative methods to understand and predict the dissemination and economic impact of news, comments, and reviews in financial markets and electronic commerce. Furthermore, we engineer tools that allow decision-makers to replace gut decisions with data-driven practices.



Data Science Methods for Unstructured Online Data 

Our research relies upon the ability to accurately process unstructured online data in various forms (e.g., text, images). For this purpose, we actively develop state-of-the-art data science methods (e.g., in the area of text mining and sentiment analysis) to derive actionable insights from unstructured online data.
Third-Party Projects

Funded Research Projects (ongoing)


Community-Based Fact-Checking on Social Media, Deutsche Forschungsgemeinschaft (DFG), 2022 — 2025.



Rumor Diffusion on Social Media During the COVID-19 Pandemic, Deutsche Forschungsgemeinschaft (DFG), 2021 — 2025.

R Packages

R-Packages


Package: ReinforcementLearning

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

 

Package: SentimentAnalysis

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