Social media platforms like X (formerly Twitter) generate vast volumes of user-generated content that provide real-time insights into public sentiment. Despite the widespread use of traditional machine learning methods, their limitations in capturing contextual nuances in noisy social media text remain a challenge. This study leverages the Sentiment140 dataset, comprising 1.6 million labeled tweets, and develops predictive models for binary sentiment classification using Naive Bayes, Logistic Regression, and the transformer-based BERT model. Experiments were conducted on a balanced subset of 12,000 tweets after comprehensive NLP preprocessing. Evaluation using accuracy, F1-score, and confusion matrices revealed that BERT significantly outperforms traditional models, achieving an accuracy of 89.5% and an F1-score of 0.89 by effectively modeling contextual and semantic nuances. In contrast, Naive Bayes and Logistic Regression demonstrated reasonable but consistently lower performance. To support practical deployment, we introduce SentiFeel, an interactive tool enabling real-time sentiment analysis. While resource constraints limited the dataset size and training epochs, future work will explore full corpus utilization and the inclusion of neutral sentiment classes. These findings underscore the potential of transformer models for enhanced public opinion monitoring, marketing analytics, and policy forecasting.

Frequent consumption of aflatoxins-contaminated spices has been linked to serious adverse health effects among consumers. The likelihood of exposure to these toxins is influenced by the level of public awareness. Controlling aflatoxins contamination throughout the food chain is critical for public health. This study aimed to assess the handling practices and awareness of aflatoxin contamination among micro- and small-scale spice processors. A total of 60 processors from 4 districts of two regions of Tanzania were interviewed. The results showed that while 56.7% of interviewed processors were aware of aflatoxin contamination in spices primarily through training (38.3%) and mass media (30%). However, there were still misconceptions regarding the causes and effects of aflatoxins to human health. It was observed that, poor drying and storage practices, inadequate monitoring of processors aggravated the situation. Nonetheless, all interviewed processors expressed willingness to participate in training programs to ensure quality and safety along the chain. The study findings underscore the necessity for targeted interventions to reduce aflatoxin risks in the spice value chain. These should include strengthened food safety inspections and enforcement, as well as tailored training and support for micro and small-scale spice processors. Enhancing their knowledge and ability to adopt proper handling, drying and storage practices is critical for enhancing food safety and safeguarding public health.

Objective: To identify and evaluate the main functional assessment tools applied in the postoperative monitoring of patients undergoing total knee arthroplasty (TKA), and to synthesize the functional outcomes reported through these instruments in the current scientific literature. Methodology: A structured review was conducted following PRISMA 2020 guidelines. Thirty-one peer-reviewed studies were selected through a targeted manual search based on predefined eligibility criteria. Included studies evaluated functional recovery following TKA using validated outcome measures such as the WOMAC, KSS, KOOS, IKDC, SF-36, and SANE. Data extraction focused on the instruments used, patient population characteristics, and reported outcomes. A descriptive synthesis was compiled in Table 1. Additionally, 15 studies with quantitative data were analyzed using a forest plot to illustrate risk ratios (RR) and 95% confidence intervals (CI) for functional improvement. Risk of bias was assessed qualitatively based on methodological rigor, clarity of reporting, and validation of the outcome tools. Results: All included studies reported improvements in functional status following TKA. Most risk ratios ranged from 0.66 to 0.85, indicating a consistent reduction in the risk of postoperative functional limitation. High-quality studies demonstrated more precise effect estimates and greater internal validity. The SANE scale emerged as a valid and practical tool with high responsiveness, including in its culturally adapted Brazilian version. Despite heterogeneity in study design, the direction of effect remained consistent across all included studies. Conclusion: Validated functional assessment tools are essential for monitoring recovery after total knee arthroplasty. Instruments such as WOMAC and SANE demonstrate strong clinical utility and psychometric validity. Their systematic use enhances outcome comparability, supports individualized rehabilitation planning, and improves decision-making in orthopedic care.

The integration of LiDAR and Artificial Intelligence (AI) has revolutionized feature detection in urban environments. LiDAR systems, which utilize pulsed laser emissions and reflection measurements, produce detailed 3D maps of urban landscapes. When combined with AI, this data enables accurate identification of urban features such as buildings, green spaces, and infrastructure. This synergy is crucial for enhancing urban development, environmental monitoring, and advancing smart city governance. LiDAR, known for its high-resolution 3D data capture capabilities, paired with AI, particularly deep learning algorithms, facilitates advanced analysis and interpretation of urban areas. This combination supports precise mapping, real-time monitoring, and predictive modeling of urban growth and infrastructure. For instance, AI can process LiDAR data to identify patterns and anomalies, aiding in traffic management, environmental oversight, and infrastructure maintenance. These advancements not only improve urban living conditions but also contribute to sustainable development by optimizing resource use and reducing environmental impacts. Furthermore, AI-enhanced LiDAR is pivotal in advancing autonomous navigation and sophisticated spatial analysis, marking a significant step forward in urban management and evaluation. The reviewed paper highlights the geometric properties of LiDAR data, derived from spatial point positioning, and underscores the effectiveness of machine learning algorithms in object extraction from point clouds. The study also covers concepts related to LiDAR imaging, feature selection methods, and the identification of outliers in LiDAR point clouds. Findings demonstrate that AI algorithms, especially deep learning models, excel in analyzing high-resolution 3D LiDAR data for accurate urban feature identification and classification. These models leverage extensive datasets to detect patterns and anomalies, improving the detection of buildings, roads, vegetation, and other elements. Automating feature extraction with AI minimizes the need for manual analysis, thereby enhancing urban planning and management efficiency. Additionally, AI methods continually improve with more data, leading to increasingly precise feature detection. The results indicate that the pulse emitted by continuous wave LiDAR sensors changes when encountering obstacles, causing discrepancies in measured physical parameters.