Multimodal Computational Methods in Political Science
MA seminar · Summer semester 2026 · LMU Munich, Geschwister-Scholl-Institut
Course overview
This MA seminar introduces students to computational methods for analyzing multimodal political data — text, images, video, and audio. The course is organized in two blocks. The first half covers text-as-data methods, from classical preprocessing and supervised classification through word embeddings, topic models, sequence models, and modern Transformer-based approaches such as BERT. The second half extends these ideas to visual, video, and audio data, covering the methodological and substantive challenges of analyzing non-textual political content.
Instructors
Block I — Text analysis (Lectures 1–7): Tamara Grechanaya · Tamara.Grechanaya@lmu.de
Block II — Visual / video / audio (Lectures 8–14): Clara Fochler · clara.fochler@gsi.lmu.de
General resources
- Grimmer, Roberts & Stewart (2022). Text as Data. Princeton University Press. The political-science perspective on text analysis methods.
- Jurafsky & Martin. Speech and Language Processing (3rd ed., draft). Free at web.stanford.edu/~jurafsky/slp3. Comprehensive NLP reference.
Block I — Text analysis
Lecture 1 — Text as Data: Foundations & Preprocessing
14 April 2026
Materials
Required reading
- Grimmer, J., & Stewart, B.M. (2013). "Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts." Political Analysis 21(3), 267–297.
- Grimmer, J., Roberts, M. E., & Stewart, B.M. (2022). Text as Data, Chapters 1 to 5.
Lecture 2 — Classical Text Classification: Logistic Regression & Naive Bayes
21 April 2026
Materials
Required reading
- Jurafsky, D. & Martin, J.H. (2024). Speech and Language Processing Chapter 4: Naive Bayes, Text Classification, and Sentiment.
- Hopkins, D. & King, G. (2010). "A Method of Automated Nonparametric Content Analysis for Social Science." American Journal of Political Science, 54(1), 229--247.
Lecture 3 — Word Embeddings & Vector Spaces
28 April 2026
Materials
Required reading
- Jurafsky, D. & Martin, J.H. (2024). Speech and Language Processing Chapter 5: Embeddings.
- Rodriguez, P. L., & Spirling, A. (2022). "Word embeddings: What works, what doesn’t, and how to tell the difference for applied research." The Journal of Politics, 84(1), 101--115.
- Grimmer, J., Roberts, M. E., & Stewart, B.M. (2022). Text as Data, Chapters 6 to 7.
Lecture 4 — Document Representations & Topic Models
5 May 2026
Materials
Required reading
- Blei, D. M. (2012). "Probabilistic topic models." Communications of the ACM, 55(4), 77-84.
- Grimmer, J., Roberts, M. E., & Stewart, B.M. (2022). Text as Data, Chapters 12 to 13.
- Roberts, M. E., Stewart, B. M., & Tingley, D. (2019). "Stm: An R package for structural topic models." Journal of statistical software, 91, 1-40.
- Grimmer, J. (2010). "A Bayesian hierarchical topic model for political texts: Measuring expressed agendas in Senate press releases." Political analysis, 18(1), 1-35.
Lecture 5 — Neural Networks & Sequence Models
12 May 2026
Materials
Required reading
- Jurafsky, D. & Martin, J.H. (2024). Speech and Language Processing Chapter 6: Neural Networks
- Jurafsky, D. & Martin, J.H. (2024). Speech and Language Processing Chapter 13: RNNs and LSTMs
- Olah, C. (2015). “Understanding LSTM Networks.”
- PyTorch official tutorials
Lecture 6 — Attention & the Transformer Architecture
19 May 2026
Materials
Required reading
- Jurafsky, D. & Martin, J.H. (2024). Speech and Language Processing, Chapter 8: Transformers
- Vaswani, A., Shazeer, N., Parmar, N., et al. (2017). "Attention Is All You Need." Advances in neural information processing systems, 30.
- Alammar, J. (2018). The Illustrated Transformer.
Lecture 7 — Transfer Learning & Fine-Tuning BERT
26 May 2026
Required reading
- Jurafsky, D. & Martin, J.H. (2024). Speech and Language Processing, Chapter 10: Masked Language Models
- Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding." NAACL 2019.
- Hugging Face NLP Course, Chapter 3: Fine-tuning a pretrained model. (Hands-on introduction to fine- tuning BERT with the transformers library).
Block II — Visual, video & audio analysis
Lectures 8–14 are taught by Clara Fochler, clara.fochler@gsi.lmu.de.
Lecture 8 — Images and Convolutional Neural Networks
9 June 2026
Materials
Required reading
- Webb Williams, N., Casas, A., & Wilkerson, J. D. (2020). Ch. 1.1: Three applications of computer vision for social scientists; Ch. 5: Political science working example: Images related to a Black Lives Matter protest. In Images as data for social science research: An introduction to convolutional neural nets for image classification. Cambridge University Press. https://doi.org/10.1017/9781108860741
Lecture 9 — CNN fine-tuning and Vision Transformers
16 June 2026
Materials
Required reading
- Webb Williams, N., Casas, A., & Wilkerson, J. D. (2020). Fine-tuning a CNN. In Images as data for social science research: An introduction to convolutional neural nets for image classification. Cambridge University Press. https://doi.org/10.1017/9781108860741
- Zhang, A., Lipton, Z. C., Li, M., & Smola, A. J. (2023). Vision transformer. In Dive into deep learning. https://d2l.ai/chapter_attention-mechanisms-and-transformers/vision-transformer.html
- de-Lima-Santos, M. F., Gonçalves, I., Quiles, M. G., et al. (2024). Visual political communication on Instagram: A comparative study of Brazilian presidential elections. EPJ Data Science, 13(72). https://doi.org/10.1140/epjds/s13688-024-00502-0
- Girbau, A., Kobayashi, T., Renoust, B., Matsui, Y., & Satoh, S. (2024). Face detection, tracking, and classification from large-scale news archives for analysis of key political figures. Political Analysis, 32(2), 221–239. https://doi.org/10.1017/pan.2023.33
- Scholz, S., Weidmann, N. B., Steinert-Threlkeld, Z. C., Keremoğlu, E., & Goldlücke, B. (2025). Improving computer vision interpretability: Transparent two-level classification for complex scenes. Political Analysis, 33(2), 107–121. https://doi.org/10.1017/pan.2024.18
Lecture 10 — Video Analysis
23 June 2026
Materials
Required reading
- Nyhuis, D., Ringwald, T., Rittmann, O., Gschwend, T., & Stiefelhagen, R. (2021). Automated video analysis for social science research. In Handbook of computational social science, Vol. 2: Data science, statistical modelling, and machine learning methods. Routledge. PDF
- Dietrich, B. J. (2021). Using motion detection to measure social polarization in the U.S. House of Representatives. Political Analysis, 29(2), 250–259. https://doi.org/10.1017/pan.2020.25
Lecture 11 — CNNs for Video Analysis and Video Vision Transformers
30 June 2026
Materials
Required reading
- Rittmann, O., Ringwald, T., & Nyhuis, D. (2025). Public opinion and emphatic legislative speech: Evidence from an automated video analysis. British Journal of Political Science, 55, e165. https://doi.org/10.1017/S0007123425100872
Lecture 12 — Audio Analysis
7 July 2026
Materials
Required reading
- Mestre, R., & Ryan, M. (2026). Potential and pitfalls of audio as data for political research: Alignment, features, and classification models. Political Analysis, 1–17. https://doi.org/10.1017/pan.2025.10031