BCLSA: Advancing Bangla sentiment analysis with concept-level reasoning and efficiency

• Introduces BCLSA, the first unified concept-level sentiment analysis framework for Bangla, combining syntactic, semantic, and affective knowledge. • Proposes the CLSA-Bn algorithm, which models negation, modifiers, and concept polarity for explainable sentiment classification. • Proposes a Bangla-specific concept extraction algorithm using syntactic patterns, multiword expressions, and affective lexicon mapping. • Achieves state-of-the-art results on large formal (10K+) and informal (12K+) Bangla datasets, outperforming Bi-LSTM and SVM baselines. • Ensures accuracy (up to 90.2%) and efficiency (5 ms inference, 50 MB model size), enabling deployment in real-time, low-resource settings. • Introduces the Concept-Level Polarity Accuracy (CLPA) metric for evaluating semantic fidelity Accurate sentiment analysis in Bangla remains a significant research challenge due to limited annotated corpora, complex morphology, insufficient linguistic resources, and the absence of interpretable concept-level knowledge bases. Existing approaches often struggle to capture context-dependent sentiment, idiomatic expressions, and domain adaptability, further constrained by the low-resource nature of the language. To address these limitations, this study proposes the Bangla Concept-Level Sentiment Analysis (BCLSA) framework, introducing two dedicated algorithms: a Bangla-specific concept extraction method and the Concept-Level Sentiment Analysis for Bangla (CLSA-Bn) weighted scoring algorithm. The first extracts sentiment-bearing concepts through syntactic pattern recognition, multiword expression detection, and affective lexicon mapping, while the second refines polarity estimation via negation handling, modifier scaling, and weighted aggregation for interpretable classification. To mitigate data scarcity and morphological variation, BCLSA applies language-specific preprocessing, including Unicode normalization, phonetic correction, and lemmatization. Evaluations on 10,243 formal news articles and 12,084 informal social media comments show that CLSA-Bn outperforms the Bi-LSTM and SVM baselines, achieving 90.2% Accuracy, 90% Macro-F1, 85% Matthews Correlation Coefficient (MCC), and 94% Area Under the Curve (AUC) for formal text, and 86.8% Accuracy, 86% Macro-F1, and 91% AUC for informal text. The proposed Concept-Level Polarity Accuracy (CLPA) metric confirmed semantic fidelity above 88%. Efficiency analysis revealed that CLSA-Bn requires only 30 s initialization, 5 ms inference, and a 50 MB model. Error rate analysis further confirmed robustness with the lowest misclassification ratios (9.8% formal, 13.2% informal), demonstrating balanced improvement in performance and error minimization.