ASSIGNMENT
Our research focuses on social media as an environment for social contact and information exchange in which individuals are increasingly targeted by misinformation, emotional narratives, AI-generated content, and other forms of strategic messaging with the goal of influencing their attitudes and behaviours. Specifically problematic seems to be the fact that there is an increasing amount of influential content spread by foreign actors around national and regional elections. The presence of this strategically placed, overly emotional, exaggerated, and often simply wrong information has the potential to threaten how responsible citizens shape their thinking about important political topics, leading them to make choices they would not otherwise make.
To protect our democracies as a whole, a better understanding of how this manipulation influences individuals is essential. In line with this, the goal of this research is to identify proxies in the complex data environment of social media, which can help the assessment and understanding of the influence these campaigns might have on individuals.
In this project, the student will have the opportunity to learn and apply quantitative text processing (natural language processing) with ongoing guidance on current, highly relevant topics in our society. While the method of investigation (quantitative text processing/natural language processing) as well as the broad scope of this project (strategic social media influencing) are set, the student has all the freedom to develop the project within these boundaries in a direction of their interest. Possible directions could be detecting polarisation from linguistic expressions, repetitive narrative framings, or echo chamber reinforcement.
This internship will be part of this larger project: https://www.utwente.nl/en/bms/pcrs/research/research-projects/Cognitive%20Warfare/
BACKGROUND INFORMATION ORGANIZATION
The section Psychology of Conflict, Risk and Safety at the University of Twente has a distinctive and unique profile in the areas of risk perception and risk communication, conflict and crisis management and the antecedents of risky, antisocial, and criminal behaviour. It currently includes 16 research staff members and 8 PhD students. We work from both a psychology and an engineering perspective and cooperate with other scientific disciplines, based on the “high tech, human touch” profile of the University of Twente.
AVAILABILITY
Flexible. This internship is a recommended precursor for the master's project on the same topic. Thus, the student can here set up their MSc study and pilot it. This project can be done by one (or multiple) students.
INTERESTED?
Please contact the PCRS internship coordinator Miriam Oostinga (m.s.d.oostinga@utwente.nl).
LITERATURE
- Aldera, S., Emam, A., Al-Qurishi, M., Alrubaian, M., & Alothaim, A. (2021). Online Extremism Detection in Textual Content: A Systematic Literature Review. IEEE Access, 9, 42384–42396. https://doi.org/10.1109/ACCESS.2021.3064178
- Bail, C. A., Guay, B., Maloney, E., Combs, A., Hillygus, D. S., Merhout, F., Freelon, D., & Volfovsky, A. (2020). Assessing the Russian Internet Research Agency’s impact on the political attitudes and behaviors of American Twitter users in late 2017. Proceedings of the National Academy of Sciences, 117(1), 243–250. https://doi.org/10.1073/pnas.1906420116
- Das, S. D., Basak, A., & Dutta, S. (2021). A Heuristic-driven Uncertainty based Ensemble Framework for Fake News Detection in Tweets and News Articles (No. arXiv:2104.01791). arXiv. https://doi.org/10.48550/arXiv.2104.01791
- Eady, G., Paskhalis, T., Zilinsky, J., Bonneau, R., Nagler, J., & Tucker, J. A. (2023). Exposure to the Russian Internet Research Agency foreign influence campaign on Twitter in the 2016 US election and its relationship to attitudes and voting behavior. Nature Communications, 14(1), 62. https://doi.org/10.1038/s41467-022-35576-9
- Rastogi, S., & Bansal, D. (2022). Disinformation detection on social media: An integrated approach. Multimedia Tools and Applications, 81(28), 40675–40707. https://doi.org/10.1007/s11042-022-13129-y