Enhanced weight based convolutional neural network (EWCNN) and fuzzy clustering for semantically rich multi-label social emotion classification

Abstract

In Recent Years, Social Emotion In Recent Years Acquires Natural Language Processing Researchers’ Attention, Because Of Analyzing User-Generated Emotional Documents On The Web. But, These Emotions Has Noisy Instance Mixed And It Is Great Dispute To Acquire The Textual Meaning Of Short Messages. Definition: In General, Large-Scale Datasets Will Have Many Noisy Data, Which Can’t Be Used Readily And Also It Is Costly, Because Of Ambiguity Of Various Informal Expressions In User-Generated Comments. It Is Very Tedious One To Recognize The Similar User Documents From The Entire Social Media Text Message. Furthermore, Online Comments Are Characteristically Categorized By A Sparse Feature Space, Which Makes The Respective Emotion Classification Task A Complex One. Methodology: Three Major Contributions Were Done In This Work In Order To Rectify These Problems, They Are: Development Of A Novel Mutation Bat Optimization Based Sparse Encoding (MBO-SC) Which Transforming The Sparse Low-Level Features Into Dense High-Level Features, Was The 1st Contribution, Next Is, An Enhanced Weight Based Convolutional Neural Network (EWCNN) To Target-Specific Layer. It Influences The Semantically EWCNN Classifier To Include Semantic Domain Knowledge Into The Neural Network To Bootstrap Its Inference Power And Interpretability. Fuzzy Clustering Algorithm Is Proposed To Minimize The Similarity Among Two Documents. Uses: It Is Quite Constructive In Recommending Products, Collecting Public Opinions, And Predicting Election Results. Proposed Work Is Distinguished With The Existing Methods, With The Metrics Such As: Precision, Recall, Sensitivity, Specificity, F-Measure And Accuracy. From The Experimental Result It Is Confirmed That The Quality Of Learned Semantic Vectors And The Performance Of Social Emotion Classification Can Be Enhanced By Proposed Models.