Intelligent sentinet-based lexicon for context-aware sentiment analysis: optimized neural network for sentiment classification on social media

In the modern era, lack of adequate training data requires lexicon-based models. The lexicon scoring model was extensively deployed as an effective and convenient substitute by the majority of practitioners and researchers. Usually, the entire sentiment of the document is portrayed by leading polarity (i.e., negative or positive) among the indicators. The efficiency of the conventional lexicons is however quite imperfect when employed to novel issues. This paper intends to propose a new “Intelligent Senti-net based lexicon generation method,” which guarantees the classification of sentiments in social media. The proposed sentiment classification model is performed through certain steps (i) pre-processing (ii) keyword extraction (iii) holoentropy-based lexicon construction (iv) feature extraction (semantic similarity) (v) classification (vi) feedback process and (vii) sentiment classification from Int SentiNet. For classification purposes, neural network (NN) is used. To make the classification more accurate, the training of NN is carried out using a new Improved Sealion (SLnO) algorithm named Self-Improved SLnO via optimizing the weights. In the end, simulation is done to validate the enhancement of the presented scheme over traditional schemes.