TY - JOUR AU - R. Sathish Kumar PY - 2022/10/06 Y2 - 2024/03/28 TI - New Modern Approach to Predict Users’ Sentiment Using CNN and BLSTM JF - International Journal of Informatics, Information System and Computer Engineering (INJIISCOM) JA - INJIISCOM VL - 3 IS - 2 SE - Articles DO - 10.34010/injiiscom.v3i2.8452 UR - https://ojs.unikom.ac.id/index.php/injiiscom/article/view/8452 AB - In Today’s world social network play a vital role and provides relevant information on user opinion. This paper presents emotional health monitoring system to detect stress and the user mood. Depending on results the system will send happy, calm, relaxing or motivational messages to users with phycological disturbance. It also sends warning messages to authorized persons in case a depression disturbance is detected by monitoring system. This detection of sentence is performed through convolution neural network (CNN) and bi-directional long-term memory (BLSTM). This method reaches accuracy of 0.80 to detect depressed and stress users and also system consumes low memory, process and energy. We can do the future work of this project by also including the sarcastic sentences in the dataset. We can also predict the sarcastic data with the proposed algorithm  ER -