Abstract

Facebook, Twitter, Instagram, and other social media have emerged as excellent platforms for interacting with friends and expressing thoughts, posts, comments, images, and videos that express moods, sentiments, and feelings. With this, it has become possible to examine user thoughts and feelings in social network data to better understand their perspectives and attitudes. However, the analysis of depression based on social media has gained widespread acceptance worldwide, other verticals still have yet to be discovered. The depression analysis uses Twitter data from a publicly available web source in this work. To assess the accuracy of depression detection, long-short-term memory (LSTM) and convolution neural network (CNN) techniques were used. This method is both efficient and scalable. The simulation results have shown an accuracy of 86.23%, which is reasonable compared to existing methods.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call