Psychotherapy Chatbot For Mental Illness

Psychotherapy chatbot attempts to help individuals overcome sadness and anxiety by conversing with them and asking psychological and emotion-related questions to allow them to express their feelings and thoughts. The bot will diagnose mental diseases and store all conversations to deliver

Project Title

Psychotherapy Chatbot For Mental Illness

Project Area of Specialization

Artificial Intelligence

Project Summary

Psychotherapy chatbot attempts to help individuals overcome sadness and anxiety by conversing
with them and asking psychological and emotion-related questions to allow them to express their
feelings and thoughts. The bot will diagnose mental diseases and store all conversations to deliver
the most effective treatment for the patient. The proposed system will interact with the user by
keeping the track of the state of interaction and recollecting the preceding commands to give
functionality by keeping the patients previous mental condition saved in database and can be
developed by using artificial algorithms that scrutinize user's queries and recognize them and give
replies to related queries.

Project Objectives

The main objective of this project is to build up chatbot system for psychotherapy for mental illness
using machine learning, AI and Natural Language Processing (NLP). It is aimed to provide the
screening, diagnosis, and treatment of mental illnesses. This work focused on machine learning
approach for the semantic interpretation which uses knowledge of word meaning from the user's
sentence and determine the patient's current mental situation and provide the most effective brain
training techniques to cope with the current mental illness situation. The conversational chatbot
will be capable of storing the patient's current mental illness and brain training techniques to use
it later, to improve mental health through summarizing and pooling the results of previously saved
records.

Project Implementation Method

Dataset
It's a dataset with intent. A tag (a unique name), patterns (sentence patterns for our neural network text
classifier), and responses are all included in each conversational intent (one will be used as a response).
Preprocessing
We began by categorizing the dataset into documents, words, and classification classes using a process
called tokenization
Data Pre-Processing
Data Pre-processing includes tokenization and stemming.

Tokenization: Splitting words into meaningful units.

Then we made a list of documents (sentences), each of which is a list of stemmed words, and each of
which is associated with an intent (a class).

Stemming: Generate the root form of the words.

TensorFlow
TensorFlow is a free and open-source software library for machine learning and artificial intelligence. It
can be used across a range of tasks but has a particular focus on training and inference of deep neural
networks.
We used TensorFlow to make sequential neural network model and used SGD (Stochastic gradient
descent) as optimizer, which is an iterative method for optimizing an objective function with suitable
smoothness properties.
NumPy
The purpose of using NumPy was to convert English words or sentences to numerical arrays.
Natural Language Toolkit NLTK
NLTK, is a suite of libraries and programs for symbolic and statistical natural language processing for
English written in the Python programming language.
In NTLK we performed Stemming which is defined as to generate the root from of the words and we
also used it for Tokenization in which we each word is separated in the dataset from other words and
then making it a set of them.
Sklearn
We used Sklearn for the various purposes. For instance:
• To training, testing, and splitting the data.
• To build the Accuracy Graph.
• To make Confusion matrix
• To find out Precision, Recall or F1 score.
Matplotlib
In Matplotlib, the data that we retrieved from the Sklearn is used to plot the graph.

Flask
Flask is a micro web framework written in Python. It is classified as a microframework because it does
not require tools or libraries. It has no database abstraction layer, form validation, or any other
components where pre-existing third-party libraries provide common functions.
We used Flask for making web applications and HTTP request management.

Calling Service (URI Launcher)
By using URI Launcher, you will need no call permissions in your app, as URI Launcher opens the
dialer with the number already entered to mental health care center, and further allows the user to
decide whether to make the call before calling or not call at all.

Benefits of the Project

Psychotherapy chatbots can effectively assist even the most remote people in need of support and
de-stigmatize the concept of seeking treatment by allowing them to call out for help from the
comfort of their own homes. Human therapists are in short supply, and they are not available 24
hours a day, seven days a week. They're also not readily available in rural regions, and people are
often hesitant to seek mental health treatment due to the stigma attached to it. For these reasons,
using a psychotherapy chatbot has advantages since it is always available, regardless of where you
are, and it has no stigma. People are more willing to provide information with an AI than they are
with an internet form.

Technical Details of Final Deliverable

A fully functional application with firebase integration/ pretrained chatbot model in Android/IOS platform.

Final Deliverable of the Project

Software System

Core Industry

Health

Other Industries

Education , IT , Medical

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com