Albanian Sentiment Analysis: Exploring Machine and Deep Learning Techniques
Albanian Journal of Natural and Technical Sciences · 30.06.2025 · 30 (1) · 123-132
DOI: 10.67537/ajnts3001006 ↗Kurz gefasst
Fachartikel in der Zeitschrift Albanian Journal of Natural and Technical Sciences, online erschienen am 30.06.2025. Verfasst von Alba Haveriku und 1 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study presents a comparative analysis of machine learning (ML) and deep learning (DL) algorithms for sentiment analysis in Albanian, a low-resource and morphologically rich language that poses distinctive challenges for natural language processing (NLP). This study explored the effectiveness of both traditional ML classifiers and neural network approaches, such as Long Short-Term Memory (LSTM) models. Experiments were conducted on two datasets: the AlbMoRe corpus and the Multilingual Twitter Sentiment Classification corpus. Given the complexity of Albanian, we examined how linguistic features influence algorithmic performance, noting that conventional ML models struggle to capture contextual sentiment effectively. We also performed a series of hyperparameter tuning experiments within the LSTM architecture, focusing on network depth, dropout rates, and embedding dimensions. These findings contribute to the advancement of NLP tools and resources for the Albanian language.
Zitieren
APA
Haveriku, A., & Meçe, E. K. (2025). Albanian Sentiment Analysis: Exploring Machine and Deep Learning Techniques. Albanian Journal of Natural and Technical Sciences, 30(1), 123-132. https://doi.org/10.67537/ajnts3001006
Vancouver
Haveriku A, Meçe EK. Albanian Sentiment Analysis: Exploring Machine and Deep Learning Techniques. Albanian Journal of Natural and Technical Sciences. 2025;30(1):123-132. doi:10.67537/ajnts3001006
BibTeX
@article{Haveriku2025,
author = {Haveriku, Alba and Meçe, Elinda Kajo},
title = {Albanian Sentiment Analysis: Exploring Machine and Deep Learning Techniques},
journal = {Albanian Journal of Natural and Technical Sciences},
year = {2025},
volume = {30},
number = {1},
pages = {123--132},
doi = {10.67537/ajnts3001006}
}
EUVIMED