Talk title: Virtual Tribes: Analyzing Attitudes towards the LGBT Movement by Applying Machine Learn- ing on Twitter Data
Moritz Bittner, David Dettmar, Diego Morejon Jaramillo, Maximilian Johannes Valta
We investigate the application of machine learning techniques that allow conclusions from users’ behavior and language in Twitter about their attitudes towards the LGBT movement. By using an adjusted procedure of the CRISP-DM process (Cross Industry Standard Process for Data Mining) we create a prediction model and formulate step-by-step instructions for its deployment. We provide the reader with a theoretical background about our research do- main and precisely describe the methods that we use. Results show that there are two groups of contrary attitudes towards LGBT and that the language and behavior of users in the groups respectively differ from each other. Also, we identify word analyses as a valuable mean for prediction. We also apply our model on another dataset to investigate its interspersion of the previous identified groups and demonstrate its effectiveness for predicting attitudes of a single actor in Twitter. In the end we critically discuss our findings and recommend further fields of investigation that are related to our research.