The power of words – A text-based analysis of companies' social media posts

Key Info

Basic Information

Lehrstuhl für Marketing
Bachelor; Master


In 2021, the global user base of social media was 4.2 billion (Statista, 2022). Companies have long recognized the potential of using social media to communicate with existing and potential customers and publish posts on their corporate social media accounts at regular intervals. The currency of social media posts is user engagement, i.e., the number of likes, shares or comments to a post. In addition to the content of the posts, the text-based language that companies consciously or unconsciously use in social media posts can also have a significant influence on user engagement, which in turn can affect the purchase of products or brand perception, for example.

The aim of the thesis is to analyze an existing dataset of Facebook posts from leading companies with regard to the language used and its impact on user engagement. This involves setting up a model and formulating hypotheses, which will then be tested using the data. The exact research question will be developed in the course of the thesis. Ideally, R or Python should be used for the statistical analysis of the data. Previous experience is advantageous, but not mandatory.

Please attach a short letter of motivation to your application (

Keywords: Keywords: social media marketing; natural language processing; user engagement; field data