SentiNeural: A Depression Clustering Technique for Egyptian Women Sentiments

Abstract

Online Sentiments Analysis is a trending research domain of study which is based on natural language processing, artificial intelligence, and computational linguistics. Negation sentiments usually are not included in sentiment’s analysis process. The depression analysis can be improved by negative sentiments processing. The negation sentiments may contribute to classify the depression problems and its causes. The proposed clustering technique can detect female sentiments from the sentiment’s text through cause’s classification, and the written sentiment style. The combination of sentiment analysis and neural network is a promising solution for creating a new clustering algorithm. According to Egypt Independent Journal in 2018, 7% of Egyptians suffer from mental illness reported by the Public Health Ministry in Egypt. But the real statistics is more than the mentioned percentage which causes major social problems such as divorce, avoiding responsibilities, or non-marriage. This paper will address the real statistics and cluster the depression causes and social status for each sentiment. Online women sentiments are the essential focus of this research. The proposed technique consists of two algorithms clustering for user’s sex and classification algorithm for causes and responsibilities of women. The proposed clustering algorithm can recognize automatically for the sentiments user sex (females or males) and the level of depression automatically. The neural network clustering approach will produce accurate analysis results. The hardness of depression analysis implicitly and explicitly demonstrated in the different classifications for sentiments. This paper introduces a new technique for clustering sentiments and evaluating Egyptian women depression based on social sentiments.