Advocacy Monitoring of Women and Children Health through Social Data

Background/Objective: To classify the extracted women and children health data from the social media and to utilize it for advocacy monitoring. Methods/Statistical Analysis: Advocacy monitoring can be performed by extracting the social data related to women and children health. A keyword based search technique is used for this purpose. The children health details like the nutrition deficiencies, lack of vaccination, diseases like pneumonia, diarrhea and malaria that affect new born children and the women health data like maternal weight loss, maternal mortality rate, sanitation and antenatal care during maternity can be gathered from the social media using keyword based search technique. The extracted data are needed to be analyzed and classified into related data groups using Decision tree C4.5 and Support Vector Machine (SVM). Findings: Decision tree C4.5 algorithm classifies the data based on the concept of information entropy. The data are classified at each node of the tree after analyzing the attribute of the data. SVM analyzes the extracted data and uses the health parameters listed to group the related data. The approach is of two stages: training and testing. The training dataset is build using the health data representing the listed search words. This training set is used to classify the test data. The data are tested with the training set and only women and child health data are stored in classes that help in advocacy monitoring in an efficient way. Applications/Improvements: Advocacy monitoring is required to define the socio-economic status of a region. The proposed approach efficiently classifies the extracted social data of women and children health and aids in effective advocacy monitoring.