Rising electricity demand and the need to reduce pollutant emissions highlight the importance of renewable energy, especially solar power. While most studies on photovoltaic (PV) integration focus on developed countries, least developed and developing countries such as the Democratic Republic of Congo (DRC) face particular challenges due to fragile grid infrastructure. This work evaluates the technical and operational impacts of PV integration into the western grid of the DRC using DIgSILENT PowerFactory 2021 SP2 simulations. It examines penetration levels from 10% to 50% based on a 2012 MW baseline, and evaluates power losses, short-circuit ratios (SCRs), grid stability, harmonic distortions, and voltage oscillations. Results reveal that moderate penetration levels (10–20%) reduce active power losses by 25% while maintaining stability. However, above 30% penetration, critical challenges arise, including a drop of the SCR below the minimum recommended value of 3, prolonged voltage oscillations, and increased harmonic distortions, resulting from the reduced overall inertia of the grid following the increase in PV power from inverters without inertia. These findings emphasize the need for targeted solutions like Battery Energy Storage Systems (BESSs), Static Synchronous Compensators (STATCOMs), and harmonic filters. This work provides foundational insights for PV integration in fragile grids of LDCs and developing countries.

Sentiment analysis is vital for evaluating user feedback in drug reviews because understanding patient experiences leads to more personalized treatment recommendations by providing insights into the real-world effectiveness and tolerability of medications, which are often overlooked in clinical trials. This study evaluates the effectiveness of word-level and sentence-level embeddings for feature extraction in sentiment analysis. These embeddings are used in sequential models (Bi-LSTM, CNN) and non-sequential models (Random Forest, DNN, ExtraTreesClassifier). The Random Forest model with LLM2Vec achieves the best performance, with 0.93 accuracy, F1-scores of 0.95 (positive) and 0.88 (negative), and precision scores of 0.93 (positive) and 0.94 (negative). This approach detects subtle negative feedback often missed by standard models. To capture social consensus in patient feedback, we introduce Adaptive Confidence-Weighted Scoring. This method leverages social validation as an implicit confidence signal, enabling sentiment scores to reflect both individual experiences and community agreement. It enhances trust and interpretability while standardizing sentiment polarity on a $[-5, +5]$ scale. Clinically validated drug-related information, scraped from trusted sources, is encoded using the Llama-3.2-3B-Instruct model to extract context-aware representations. Features derived from this external medical knowledge improve semantic understanding, ensure grounding and safety, and enhance robustness even when reviews are sparse or noisy. The final vectors are employed within a cosine similarity framework to recommend relevant drugs, aligning recommendations with user satisfaction. This work demonstrates how LLM-based feature engineering can advance clinically valid, patient-aligned healthcare recommender systems informed by real-world feedback.