Hybrid context enriched deep learning model for fine-grained sentiment analysis in textual and visual semiotic modality social data

Highlights：

• Expounds the aesthetics of sentiments in social psychology.

• A Context-aware decision level fusion model for multimodal sentiment analysis in multimodal text, m, where m ε {text, image, info-graphic} is proposed.

• The textual modality sentiment is determined using a convolution neural network (ConvNet) enriched with the contextual semantics of SentiCircle.

• Support vector machine (SVM) classifier trained using bag-of-visual-words (BoVW) for predicting the visual content sentiment.

• A Boolean system with a logical OR operation is augmented to the architecture for multi-class sentiment classification into five fine-grain levels, namely, highly positive, positive, neutral, negative and highly negative.