EUVIMEDEUVIMED entdecken
Crossref

A Machine Learning Framework for Sentiment Classification in the Kashmiri Language

Sheezan Farooq, Rumaan Bashir

Indian Journal Of Science And Technology · 21.11.2026 · 19 (41) · 2824-2831

DOI: 10.17485/ijst/v19i41.85 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Indian Journal Of Science And Technology, online erschienen am 21.11.2026. Verfasst von Sheezan Farooq und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Sentiment analysis in low-resource languages like Kashmiri is underexplored due to the lack of annotated datasets and computational tools. This study investigates sentiment analysis on Kashmiri sentences using machine learning classifiers: ‘Random Forest, Support Vector Machine (SVM), Logistic Regression, Naive Bayes, and K-Nearest Neighbours (KNN)’.

Method

A manual Kashmiri sentiment dataset was constructed and preprocessed using TFF-IDF vectorization. Standard classifiers ‘Support Vector Machine (SVM), Random Forest, Logistic Regression, Naive Bayes and K-Nearest Neighbours (KNN)’ were trained and compared with their performance metrics such as accuracy, precision-recall and F1-score.

Findings

SVM and Random Forest are the top two best performing classifiers, have a reported average accuracy of about 80% and 79%, respectively. With an accuracy of 78%, logistic regression comes in second, while KNN and naive bayes do slightly worse at 74% and 73%, respectively. Classification of neutral sentiments was relatively lower for all models, suggesting that it is one of the main challenges in Kashmiri sentiment analysis. Novelty: This study contributes a structured comparison of multiple machine learning classifiers on a dedicated Kashmiri sentiment dataset, offering empirical insights into their strengths and limitations in a low-resource setting. The findings establish a baseline for future research and provide guidance for improving sentiment classification in Kashmiri and similar under-resourced languages. Keywords: Sentiment Analysis, Natural Language Processing (NLP), Machine Learning, Kashmiri Language, TF-IDF Vectorization

Zitieren

APA

Farooq, S., & Bashir, R. (2026). A Machine Learning Framework for Sentiment Classification in the Kashmiri Language. Indian Journal Of Science And Technology, 19(41), 2824-2831. https://doi.org/10.17485/ijst/v19i41.85

Vancouver

Farooq S, Bashir R. A Machine Learning Framework for Sentiment Classification in the Kashmiri Language. Indian Journal Of Science And Technology. 2026;19(41):2824-2831. doi:10.17485/ijst/v19i41.85

BibTeX
@article{Farooq2026,
  author = {Farooq, Sheezan and Bashir, Rumaan},
  title = {A Machine Learning Framework for Sentiment Classification in the Kashmiri Language},
  journal = {Indian Journal Of Science And Technology},
  year = {2026},
  volume = {19},
  number = {41},
  pages = {2824--2831},
  doi = {10.17485/ijst/v19i41.85}
}
Kostenlos starten →