Thesis

What did you tweet and who retweeted it? Text mining to understand the dynamics of communicating innovation

Every minute, every hour and every day, vast amounts of text are produced worldwide. Tweets via Twitter, meeting minutes from the last conference, reviews on Amazon or the latest New York Times article - all this text data can provide valuable information for science and industry. For this reason, research and industrial companies are increasingly recognising the potential that lies in the large amounts of text data.

This text data, can also be used for scientific questions in consumer and innovation research and can be used as a starting point for further quantitative analyses. Interesting questions about how society deals with new technologies or about corporate strategies in the public communication of innovative products can be examined in new ways through the analysis of textual data.

Your work will deal with the empirical investigation of socio-political questions (e.g. climate change and the morality of genetic engineering) using methods of automated text analysis. To do this, you will prepare a data set consisting of tweets or newspaper articles and then evaluate it using the latest methods of quantitative text analysis. You can work with Python or R and depending on your level of experience, different depths of analysis are possible. Initial knowledge of tidytext/ text2vec/ pandas is beneficial, but not essential.

If you are interested in applying this methodology to socio-political issues, please send your CV and a letter of motivation to holtz@time.rwth-aachen.de.

Keywords: Text mining; machine learning; text analytics; innovation research; legitimation