Scribd
Upload
36 views

E

Uploaded by

Vikas Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
36 views

E

Uploaded by

Vikas Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 1

such an environment, researchers are presented with a wealth of information

regarding one’s life. In addition to the level of complexity in identifying mental


illnesses through social media platforms, adopting supervised machine learning
approaches such as deep neural networks have not been widely accepted due to the
difficulties in obtaining sufficient amounts of annotated training data. Due to
these reasons, we try to identify the most effective deep neural network
architecture among a few of selected architectures that were successfully used in
natural language processing tasks. The chosen architectures are used to detect
users with signs of mental illnesses (depression in our case) given limited
unstructured text data extracted from the Twitter social media platform.
In the fast-paced modern world, psychological health issues like anxiety,
depression and stress have become very common among the masses. In this paper,
predictions of anxiety, depression and stress were made using machine learning
algorithms. In order to apply these algorithms, data were collected from employed
and unemployed individuals across different cultures and communities through the
Depression, Anxiety and Stress Scale questionnaire (DASS 21). Anxiety, depression
and stress were predicted as occurring on five levels of severity by five different
machine learning algorithms – because these are highly accurate, they are
particularly suited to predicting psychological problems. After applying the
different methods, it was found that classes were imbalanced in the confusion
matrix. Thus, the f1 score measure was added, which helped identify the best
accuracy model among the five applied algorithms as the Random Forest classifier.
Furthermore, the specificity parameter revealed that the algorithms were also
especially sensitive to negative results.
Humans are, by nature, becoming ambitious nowadays and seek every possible
opportunity to

You might also like