Incorporating Linguistic Normalization in Croatian NLP: Evaluating the Impact of Lemmatization on Disinformation Detection Performance
TL;DR
It is demonstrated that lemmatization does not produce uniform gains across architectures: while linear models and croBERT display small but measurable improvements from morphological normalization, non-linear models such as RBF SVM and neural networks experience substantial declines in performance.
Abstract
Detecting disinformation in morphologically rich and under-resourced languages remains a significant challenge in natural language processing. This paper examines the role of lemmatization as a preprocessing strategy for disinformation detection in Croatian. Building on previous work and extending the evaluation to a newly collected dataset of nearly 25,000 social media comments, we systematically compare traditional machine learning classifiers (SVM, Random Forest, and neural networks) and a transformer-based model (croBERT) on both original and lemmatized text. Our findings demonstrate that lemmatization does not produce uniform gains across architectures: while linear models and croBERT display small but measurable improvements from morphological normalization, non-linear models such as RBF SVM and neural networks experience substantial declines in performance. These results indicate that lemmatization interacts differently with model inductive biases and feature extraction mechanisms. Overall, the study provides a detailed empirical assessment of preprocessing choices for low-resource, morphologically complex languages and offers practical guidance for developing disinformation detection systems in Croatian and similar contexts.
