You will be able to choose one of three types of projects, these will have different requirements regarding previous skills, and time commitment. In the past we have had teams with "free riders" who were not carrying their weight, leading to dissatisfaction and demotivation of contributing team members. We therefore encourage you to be upfront, and tell your colleagues how much work you want to invest in your project. The more you do, the more you will learn, but this also takes more time beyond the official requirements. Skills required for the different projects are:
Using the new tribefinder try to identify personal characteristics such as sexual orientiation, moral foundations, etc. based on individual language use, training the system with Twitter profiles
The famous five-thirty eight blog has provided 3 million Russian troll tweets. The full dataset has been published in github. Try to explore and understand the influence of these tweets on US and European politics and voters.
Two studies about an the impact of Russian trolls on the last US presidential elections:
Based on the seminal paper from Vosoughi, Roy, and Aral which has found that fake news spread faster on Twitter than real "true" news, explore if the same effect is true in mainstream media, i.e. measure on GDELT, a large open source repositor of news, if news about fake stories spread faster than real news stories.
Using our newly developed happimeter build a system that predicts individual mood based on body signals and body language, by sensors of the smartwatch, emotion detection in faces and in sound of voices, and other signals. You will have to use and learn tensorflow and other deep learning systems for this.
Using latest results from the International Laboratory in Plant Neurobiology, build a plant sensing system using electric sensors which is capable of tracking the perception of plants and their communication with their environment measuring their signaling in their chemical and physical communication gateways.
The final paper should be 10 to 20 pages, plus references, coolhunting results, and code snippets when appropriate. The total number of pages also depends on the type of project, for a coolhunting project, the paper is typically longer, for a system development project, it can be shorter and basically just describe the system, for a statistics project it should document the main insights. Paper writing tips are in the presentation just below.
Final presentations from Summer term 2017
Final papers Summer term 2017
Final presentations from Winter term 2016/17
Final papers Winter term 2016/17
Final Paper Structure: