Text-driven sentiment analysis has been widely studied in the past decade, on both random and benchmark textual Twitter datasets. Few pertinent studies have also reported visual analysis of images to predict sentiment, but much of the work has analyzed a single modality data, that is either text or image or GIF video. More recently, as the images, memes and GIFs dominate the social feeds; typographic/infographic visual content has become a non-trivial element of social media. This multimodal text combines both text and image defining a novel visual language which needs to be analyzed as it has the potential to modify, confirm or grade the polarity of the sentiment. We propose a multimodal sentiment analysis model to determine the sentiment polarity and score for any incoming tweet, i.e., textual, image or info-graphic and typographic. Image sentiment scoring is done using SentiBank and SentiStrength scoring for Regions with convolution neural network (R-CNN). Text sentiment scoring is done using a novel context-aware hybrid (lexicon and machine learning) technique. Multimodal sentiment scoring is done by separating text from image using an optical character recognizer and then aggregating the independently processed image and text sentiment scores. High performance accuracy of 91.32% is observed for the random multimodal tweet dataset used to evaluate the proposed model. The research further demonstrates that combining both textual and image features outperforms separate models that rely exclusively on either images or text analysis.