Monday, 10th of July 10:00 to 13:00
Place: Center for Advanced Internet Studies (Fully online)
In this workshop, participants will take part in exercises to explore one of the most widely used Natural Language Processing (NLP) techniques in the fields of Digital Humanities and Computational Social Science. We are going to cover the history of Sentiment Analysis, how it has changed over time, how it can be applied to research in the humanities & social sciences, and, most importantly, what its potentials as well as its limitations are.
The workshop targets especially researchers and students in the Humanities and Social Sciences with interest in automated text analysis. Knowledge of coding is not a prerequisite. As an introductory course, it will use code but the focus is instead on the critical analysis of the method and its usability.
-
Caio Mello
Caio is a Fellow at the Center for Advanced Internet Studies, where he conducts research on sentiment analysis applied to news articles. He is also a PhD candidate at the School of Advanced Study (University of London) in Digital Humanities. -
Dr. Gaurish Thakkar
Gaurish Thakkar is a research fellow at the University of Zagreb (Faculty of Humanities and Social Sciences), where he works on cross-lingual sentiment analysis for under-resourced languages. -
Dr. Johannes Breuer
Dr. Breuer is a senior researcher in the team Survey Data Augmentation at GESIS - Leibniz Institute for the Social Sciences (Department Survey Data Curation) in Cologne, Germany, and (co-)leads the team Research Data & Methods at the Center for Advanced Internet Studies (CAIS).
Schedule
- 10:00 - Round of introductions
- 10:15 - Session 1 (part one) - What’s sentiment analysis?
- 11:00 - 11:10 Break
- 11:10 - Session 1 (part two) & Session 2 - Case-study & Emotion Analysis
- 12:00 - 12:10 Break
- 12:10 - Session 3 - Sentiment analysis beyond text: The curious case of emojis
- 13:00 - Conclusion
- Sentiment Analysis
- What's sentiment analysis
- How's it been developed?
- Applications in research
- Hands-on: Classifying text using Asent
- Hands-on: Analysing limitations and complex examples
- Aspect-based sentiment analysis
- Multilinguality: challenges of working beyond English language
- Explainability: what's behind the black-boxes?
- Case-study: Is sentiment in the news becoming more negative over time?
- Temporal sentiment analysis of news headlines of BBC articles
- Task: Data Analysis
- Emotion Analysis
- Experimenting with Emotion Analysis
- Sentiment analysis beyond text: The curious case of emojis
- Emojis
- Example of sentiment analysis with emojis
- Limitations and possible next steps
- Practical: Sentiment analysis with ChatGPT
- Jennifer Isasi, "Sentiment Analysis with 'syuzhet' using R," translated by Adam Crymble, Programming Historian 12 (2023), https://doi.org/10.46430/phen0110.
- Arturo Soberón, Interpreting Machine Learning models using LIME and SHAP (2023). Available on Medium.
- Zoë Wilkinson Saldaña, "Sentiment Analysis for Exploratory Data Analysis," Programming Historian 7 (2018), https://doi.org/10.46430/phen0079.
- Dashtipour, Kia, Soujanya Poria, Amir Hussain, Erik Cambria, Ahmad Y. A. Hawalah, Alexander Gelbukh, and Qiang Zhou. 2016. ‘Multilingual Sentiment Analysis: State of the Art and Independent Comparison of Techniques’. Cognitive Computation 8 (4): 757–71. https://doi.org/10.1007/s12559-016-9415-7.
- Feldman, Ronen. 2013. ‘Techniques and Applications for Sentiment Analysis’. Communications of the ACM 56 (4): 82. https://doi.org/10.1145/2436256.2436274.
- Nandwani, P., Verma, R. A review on sentiment analysis and emotion detection from text. Soc. Netw. Anal. Min. 11, 81 (2021). https://doi.org/10.1007/s13278-021-00776-6
- Patel, Sangita N, and Jignya B Choksi. 2013. ‘A Survey of Sentiment Classification Techniques’ 01 (01). https://dl.acm.org/doi/10.1145/2436256.2436274
- Puschmann, Cornelius, and Alison Powell. 2018. ‘Turning Words Into Consumer Preferences: How Sentiment Analysis Is Framed in Research and the News Media’. Social Media + Society 4 (3): 205630511879772. https://doi.org/10.1177/2056305118797724.
- Rathje, Steven, Dan-Mircea Mirea, Ilia Sucholutsky, Raja Marjieh, Claire E. Robertson, and Jay J. Van Bavel. ‘GPT is an effective tool for multilingual psychological text analysis‘. PsyArXiv. https://doi.org/10.31234/osf.io/sekf5
- Watson, D., & Tellegen, A. 1985. Toward a consensual structure of mood. Psychological bulletin, 98(2), 219.
- Living with Machines | Exhibition 'Visualising Victorian News', British Library (2022) Designer: Ciaran Hughes
