Development of Novel Classifying System to Identify the Right Sense of Image Sharing in Social Networks Using Deep Convolution Neural Network

The use of social networks differs according to the socio-cultural, demographic and psychological aspects of individuals. People share photos and feel that they satisfy their needs of belonging along with the groups they have joined. Social media is not only a domain of freedom where individuals express themselves overtly or secretly, but also an area where several ways of violence emerge or even a means used for some aspects of violence.

Being an interactive medium and addressing quite a large number of users, social media issue has become rather sophisticated and problematic. Developed a system to identify abusing images shared/posted by an individual on a people/group based on common language, race, sexual preferences, religion, or nationality.

We investigate a new paradigm from machine learning, namely deep machine learning by examining design configurations of deep Convolutional Neural Networks (CNN) and the impact of different hyper-parameter settings towards identifying the negative aspects in social networks.

Deep CNN automatically generate powerful features by hierarchical learning strategies from massive amounts of training data with a minimum of human interaction or expert process knowledge.