5 - Depression discovery in cancer communities using deep learning

Abstract

We are said to be living in the “information age,” and data are the capital of the new economy. With the continuous explosion in the extent of data being created every day on online portals and social networking websites, industries today are collecting and analyzing more data than ever before. Data are readily available, finding valuable insights are the struggle. The easy accessibility of data, new cutting-edge technologies, and a cultural shift toward data-driven decision-making drive the demand for sentiment analysis (SA) and make it relevant in each and every domain such as politics, marketing, healthcare, and so on. In the healthcare domain, cancer is a deadly disease that claims almost 10 million lives every year. The alarming numbers of fatalities are caused due to privation of timely cancer detection, tardy medical attention, or in some cases from patients losing the will to live due to a protracted and unending treatment procedure. Governments across the world are taking steps to ensure timely cancer detection and treatment. However, little attention is being paid to the seemingly unending treatment course taking a toll on the patient's mental health, thus crushing the patient's spirit to continue. In this chapter, we investigate the use of different deep neural network architectures and natural language processing for depression detection in cancer communities. Depression detection using SA can be of great assistance to the doctors treating cancer patients and aid them in deciding whether along with the cancer treatment their patients need help from psychologists or psychiatrists.