The COVID-19 pandemic overwhelmed social media platforms with many discussions, requiring detailed research of the tweets connected to it. Nevertheless, existing techniques frequently struggle to rectify the disparity between useful and uninformative tweets in the training dataset, compromising the categorization’s precision. This study presents ICNM-BERT, a hybrid model that combines Convolutional Neural Networks (CNNs) with Bidirectional Encoder Representations from Transformers (BERT). ICNM-BERT seeks to improve the classification of tweets by categorizing COVID-19-related tweets into awareness, irrelevant, report, and treatment categories. Combining Convolutional Neural Networks (CNNs) with BERT can generate bidirectional encoder representations, enhancing the capabilities of text analysis and Natural Language Processing (NLP) applications. By utilizing Hybridized Deep Learning, the model efficiently combines the advantages of both architectures to handle heterogeneous data. ICNM-BERT effectively tackles socioeconomic difficulties related to tweet analysis using deep ensemble learning, as confirmed through experimental validation on real-world datasets.