@article{MAKHILLAJIT202120106847,
    title = {An Improved CNN and BLSTM Based Method to Perceive Mood of Patients in Online Social
Networks},
    journal = {Asian Journal of Information Technology},
    volume = {20},
    number = {10},
    pages = {199-209},
    year = {2021},
    issn = {1682-3915},
    doi = {ajit.2021.199.209},
    url = {https://makhillpublications.co/view-article.php?issn=1682-3915&doi=ajit.2021.199.209},
    author = {R.},
    keywords = {Sentimental analysis,recommendation system,deep learning,CNN,BLSTM,social networks},
    abstract = {In today’s world social network play a vital
role and provides relevant information on user opinion.
This study presents emotional health monitoring system
to detect stress and the user mood. While it has often been
difficult for those outside a network of family and friends
to identify persons who may be at risk of suicide, we can
turn to Web2.0 and the blogs hosted on social networking
sites to give a helping hand. Blogs such as those on my
space have been the focus of many high-profile youth
suicide cases in recent years, where suicidal youth have
posted messages prior to taking their own lives. This
problem is traditionally solved by using machine learning
approaches. For instance, sentences can be classified
according to their readability, using pre-built features and
classification algorithms like SVM, Random Forest and
others. Depending on results the system will send happy,
calm, relaxing or motivational messages to users with
psychological disturbance. It also sends warning messages
to authorized persons incase 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.}
    }