Deep learning-based methodologies are significant to perform sentiment analysis on social media data. The valuable insights of social media data through sentiment analysis can be employed to develop intelligent applications. Among many networks, convolution neural networks (CNNs) are widely used in many conventional text classification tasks and perform a significant role. However, to capture long-term contextual information and address the detail loss problem, CNNs require stacking multiple convolutional layers. Also, the stacking of convolutional layers has issues requiring massive computations and the tuning of additional parameters. To solve these problems, in this paper, a contextualized concatenated word representation (CCWRs) is initialized from social media data based on text which is essential to misspelled and out of vocabulary words (OOV). In CCWRs, different word representation models, for example, Word2Vec, its optimized version FastText and Global Vectors, and GloVe, collectively create contextualized representations upon the sequence of input. Second, a three-layered dilated convolutional neural network (3D-CNN) is proposed that places dilated convolution kernels instead of conventional CNN kernels. Incorporating the extension in the receptive field’s size successfully solves the detail loss problem and achieves long-term context information with different dilation rates. Experiments on datasets demonstrate that the proposed framework achieves reliable results with the selection of numerous hyperparameter tuning and configurations for improved optimization leads to reduced computational resources and reliable accuracy.