New Impact Story: Explainable AI - Understanding Political Orientations in Slovenian Parliament


2023-11-16 22:50 CLARIN


阅读模式 切换至中文

Based on ParlaMint data, researchers Bojan Evkoski and Senja Pollak developed and then explained machine learning models in order to understand the language used by Slovenian members of parliament associated with different political leanings during the migrant crisis from 2014-2020. With the models showing great predictive success, the researchers then used explainability techniques in order to identify the key words and phrases that have the strongest influence on predicting the political leaning on the topic. The researchers argue that understanding the reasoning behind predictions can be helpful as a tool for qualitative analysis in interdisciplinary research.
根据ParlaMint的数据,研究人员Bojan Evkoski和Senja Pollak开发并解释了机器学习模型,以了解2014年至2020年移民危机期间斯洛文尼亚议会议员使用的与不同政治倾向相关的语言。 随着模型显示出巨大的预测成功,研究人员随后使用可解释性技术来确定对预测该主题的政治倾向影响最大的关键词和短语。研究人员认为,理解预测背后的推理可以作为跨学科研究中定性分析的工具。