XAI in Computational Linguistics: Understanding Political Leanings in the Slovenian Parliament
This work provides a tool for interdisciplinary qualitative analysis in political science by explaining model predictions, though it is incremental as it applies existing explainability techniques to a new dataset.
The researchers developed machine learning models to predict political leanings from parliamentary speeches on the European migrant crisis in Slovenia from 2014 to 2020, achieving high predictive success and identifying key phrases like 'people' and 'unity' for left-leaning and 'nationality' and 'illegal migrants' for right-leaning parliamentarians.
The work covers the development and explainability of machine learning models for predicting political leanings through parliamentary transcriptions. We concentrate on the Slovenian parliament and the heated debate on the European migrant crisis, with transcriptions from 2014 to 2020. We develop both classical machine learning and transformer language models to predict the left- or right-leaning of parliamentarians based on their given speeches on the topic of migrants. With both types of models showing great predictive success, we continue with explaining their decisions. Using explainability techniques, we identify keywords and phrases that have the strongest influence in predicting political leanings on the topic, with left-leaning parliamentarians using concepts such as people and unity and speak about refugees, and right-leaning parliamentarians using concepts such as nationality and focus more on illegal migrants. This research is an example that understanding the reasoning behind predictions can not just be beneficial for AI engineers to improve their models, but it can also be helpful as a tool in the qualitative analysis steps in interdisciplinary research.