In a recent development, attention has shifted to the application of artificial intelligence for the optimization of wastewater treatment processes. This research compared the performances of the machine learning (ML) model: random forest, decision tree, support vector machine, artificial neural network, convolutional neural network, long-short term memory, and multiple linear regressors for optimization in effluent treatment. The training, testing, and validation datasets were obtained via the design of an experiment conducted on the removal of total dissolved solids (TDS) from pharmaceutical effluent. The breadfruit-activated carbon (BFAC) adsorbent was characterized using scanning electron microscopy and X-ray diffraction techniques. The predictive capacity of an ML algorithm, and neural network architecture implemented to optimize the treatment process using statistical metrics. The results showed that MSE ≤ 1.68, MAE ≤ 0.95, and predicted-R² ≥ 0.9035 were recorded across all ML. The ML output with minimum error functions that satisfied the criterion for clean discharge was adopted. The predicted optimum conditions correspond to BFAC dosage, contact time, particle size, and pH of 2.5 mg/L, 10 min, 0.60 mm, and 6, respectively. The optimum transcends to a reduction in TDS concentration from 450 mg/L to a residual ≤ 40 mg/L and corresponds to 90% removal efficiency, indicating ± 1.01 standard deviation from the actual observation practicable. The findings established the ML model outperformed the neural network architecture and affirmed validation for the optimization of the adsorption treatment in the pharmaceutical effluent domain. Results demonstrated the reliability of the selected ML algorithm and the feasibility of BFAC for use in broad-scale effluent treatment.

Automatic authorship identification is a challenging task that has been the focus of extensive research in natural language processing. Regardless of the progress made in attributing authorship, the need for corpora in under-resourced languages impedes advancing and examining present methods. To address this gap, we investigate the problem of authorship attribution in Albanian. We introduce a newly compiled corpus of Albanian newsroom columns and literary works and analyze machine-learning methods for detecting authorship. We create a set of hand-crafted features targeting various categories (lexical, morphological, and structural) relevant to Albanian and experiment with multiple classifiers using two different multiclass classification strategies. Furthermore, we compare our results to those obtained using deep learning models. Our investigation focuses on identifying the best combination of features and classification methods. The results reveal that lexical features are the most effective set of linguistic features, significantly improving the performance of various algorithms in the authorship attribution task. Among the machine learning algorithms evaluated, XGBoost demonstrated the best overall performance, achieving an F1 score of 0.982 on literary works and 0.905 on newsroom columns. Additionally, deep learning models such as fastText and BERT-multilingual showed promising results, highlighting their potential applicability in specific scenarios in Albanian writings. These findings contribute to the understanding of effective methods for authorship attribution in low-resource languages and provide a robust framework for future research in this area. The careful analysis of the different scenarios and the conclusions drawn from the results provide valuable insights into the potential and limitations of the methods and highlight the challenges in detecting authorship in Albanian. Promising results are reported, with implications for improving the methods used in Albanian authorship attribution. This study provides a valuable resource for future research and a reference for researchers in this domain.

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.

Air pollution continues to be a critical public health and environmental challenge, particularly in fast-growing urban areas. This study presents an interpretable, multi-horizon forecasting framework for PM2.5 concentrations in Prishtina, the capital of Kosovo. Using hourly observations from 2018...