Twitter Sentiment Analysis for Albanian Language
Albanian Journal of Natural and Technical Sciences · 30.04.2023 · 28 (1) · 63-74
DOI: 10.67537/ajnts2801006 ↗Kurz gefasst
Fachartikel in der Zeitschrift Albanian Journal of Natural and Technical Sciences, online erschienen am 30.04.2023. Verfasst von Alba Haveriku und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben.
Abstract (Originalsprache)
The large amount of data generated in social media platforms has unavoidably become an important source of understanding human opinions and behaviors. Models of sentiment analysis and tools to process social media data have been developed in English, German, Italian etc., but studies related to the Albanian language remain limited. The present paper aims to: i) provide a better understanding of the steps needed in a sentiment analyzer and, ii) present a model to automatically process tweets in Albanian language. The process starts with the cleaning and classification are the first steps of this process, while the generation of meaningful results is the final one. Entity and text analysis are used to provide the best insights and a better understanding of humans’ opinion about different trending topics. The comparison between three machine learning classifiers (Naïve Bayes, SVM, Logistic Regression) is here made to address the best classification method. The performance of these classifiers is evaluated based on statistical accuracy tests.
Zitieren
APA
Haveriku, A., & Frashëri, N. (2023). Twitter Sentiment Analysis for Albanian Language. Albanian Journal of Natural and Technical Sciences, 28(1), 63-74. https://doi.org/10.67537/ajnts2801006
Vancouver
Haveriku A, Frashëri N. Twitter Sentiment Analysis for Albanian Language. Albanian Journal of Natural and Technical Sciences. 2023;28(1):63-74. doi:10.67537/ajnts2801006
BibTeX
@article{Haveriku2023,
author = {Haveriku, Alba and Frashëri, Neki},
title = {Twitter Sentiment Analysis for Albanian Language},
journal = {Albanian Journal of Natural and Technical Sciences},
year = {2023},
volume = {28},
number = {1},
pages = {63--74},
doi = {10.67537/ajnts2801006}
}
EUVIMED