Jaumin Ajdari

Jaumin Ajdari

Auto-generated profile, based on publicly available information

Jaumin Ajdari

South East European University, Tetovo, North Macedonia

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 September 2020
Verified
Conference Paper
Closed access
ARAmarildo Rista
Amarildo Rista
JAJaumin Ajdari
Jaumin Ajdari
XZXhemal Zenuni
Xhemal Zenuni

17 December 2024 in International Journal of Interactive Mobile Technologies (iJIM)
Verified
Journal Article
Open access
PDF file
EFEndrit Fetahi
Endrit Fetahi
MHMentor Hamiti
Mentor Hamiti
ASArsim Susuri
Arsim Susuri
JAJaumin Ajdari
Jaumin Ajdari
XZXhemal Zenuni
Xhemal Zenuni
This paper aims to advance AI-based hate speech (HS) detection in the Albanian language, which is resource-limited in natural language processing (NLP). Addressing the challenge of limited data, we developed a human-annotated dataset of over 11,000 comments, carefully curated from various Albanian social media platforms, containing a substantial number of HS instances. The dataset was annotated using a detailed two-layer taxonomy to capture the complex dimensions of HS. To ensure high-quality annotations, three expert annotators applied a majority voting system, achieving a substantial Fleiss’s kappa coefficient of 0.62, underscoring the reliability and consistency of the annotations. We conducted a comparative analysis of several machine learning (ML) algorithms, including support vector machine (SVM), Naïve Bayes (NB), XGBoost, and random forest (RF), paired with various text vectorisation techniques and pre-processing methods. In binary classification, the NB model with term frequencyinverse document frequency (TF-IDF) vectorization achieved the highest performance, with an F1 score of 0.80. For multiclass classification, XGBoost outperformed other models, achieving an F1 score of 0.77. Interestingly, our experiments revealed that pre-processing steps generally reduced model performance, suggesting that raw text inputs work better for the Albanian language. Through error analysis using local interpretable model-agnostic explanations (LIME), we identified key challenges, such as polysemy and irony, which contributed to misclassifications. To demonstrate the practical applicability of our work, we developed a user-friendly mobile web application based on the best-performing model, providing realtime HS detection with the potential for integration into social media platforms.

15 November 2023 in International Journal of Interactive Mobile Technologies (iJIM)
Verified
Journal Article
Open access
PDF file
JFJakup Fondaj
Jakup Fondaj
MHMentor Hamiti
Mentor Hamiti
SKSamedin Krrabaj
Samedin Krrabaj
XZXhemal Zenuni
Xhemal Zenuni
JAJaumin Ajdari
Jaumin Ajdari
This paper compares predictive algorithms for smart agriculture sensor data in Internet of Things (IoT) applications. The main objective of IoT in agriculture is to improve productivity and reduce production costs using advanced technology and artificial intelligence. In this study, we compared various predictive algorithms for analyzing IoT smart agriculture sensor data. Specifically, we evaluated the performance of NeuralProphet, Random Forest Regression, SARIMA, and Artificial Neural Networks (ANN) by KERAS algorithms on a dataset containing temperature, humidity, and soil moisture data. The dataset was collected using IoT sensors in a smart agriculture system. The results showed that Random Forest Regression, Seasonal ARIMA, and Artificial Neural Networks by KERAS algorithms outperformed NeuralProphet algorithm in terms of accuracy and computational efficiency.

26 July 2019 in Turkish Journal of Electrical Engineering and Computer Sciences
Verified
Journal Article
Open access
Bujar RaufiBujar Raufi
Bujar Raufi
FIFlorije Ismaili
Florije Ismaili
JAJaumin Ajdari
Jaumin Ajdari
XZXhemal Zenuni
Xhemal Zenuni