Sentiment Polarity Detection in Azerbaijani Social News Articles

Abstract

Text classification field of natural language processing has been experiencing remarkable growth in recent years. Especially, sentiment analysis has received a considerable attention from both industry and research community. However, only a few research examples exist for Azerbaijani language. The main objective of this research is to apply various machine learning algorithms for determining the sentiment of news articles in Azerbaijani language. Approximately, 30.000 social news articles have been collected from online news sites and labeled manually as negative or positive according to their sentiment categories. Initially, text preprocessing was implemented to data in order to eliminate the noise. Secondly, to convert text to a more machine-readable form, BOW (bag of words) model has been applied. More specifically, two methodologies of BOW model, which are tf-idf and frequency-based model have been used as vectorization methods. Additionally, SVM, Random Forest, and Naive Bayes algorithms have been applied as the classification algorithms, and their combinations with two vectorization approaches have been tested and analyzed. Experimental results indicate that SVM outperforms other classification algorithms.

The Language Model, Resources, and Computational Pipelines for the Under-Resourced Iranian Azerbaijani

“…Almost the entire NLP pipeline for Turkish exists in a toolkit, called TurkishDelightNLP (Alecakir et al, 2022). Text classification studies can also be observed for Turkish and Azerbaijani languages e.g., sentiment of social news articles in Azerbaijani (Mammadli et al, 2019), tweet topic classification (Yüksel et al, 2019) and sentiment analysis (Mutlu and Özgür, 2022) in Turkish. (ii) Cross/multi-lingual models: this track of research includes efforts on aligning monolingual embedding spaces of various Turkic languages, which are often affected by low-resource constraints (Kuriyozov et al, 2020).…”

Artificial News Popularity Detection Based on Telegram Channels in Azerbaijan

“…Although there are few researches in the field of text classification in Azerbaijani language, one of the research projects shows that it is possible to achieve excellent result in this field. The research [7] aimed to determine the sentiment of news articles in Azerbaijani language where researchers obtained 96.79% f1-score by using SVM classifier with TF-IDF vectorization technique. The results revealed that neglecting topic domain-defining terminology was more appropriate in the context of news opinion mining, and techniques that took this into account performed better.…”