VISVESVARAYA TECHNOLOGICAL UNIVERSITY

BELAGAVI, KARNATAKA- 590018

Technical seminar report on

“Chat bot therapy for patients with mental health”

Submitted in partial fulfillment of the requirement for the award of the degree

Bachelor of Engineering
in
ELECTRICAL AND ELECTRONICS ENGINEERING
Prescribed by
Visvesvaraya Technological University

By
Md Tabish Wijdan
1BY19EE026

Under the guidance of

Dr. N Ramarao
Associate Professor, Dept. of EEE, BMSIT&M

DEPARTMENT OF ELECTRICAL AND ELECTRONICS ENGINEERING

BMS INSTITUTE OF TECHNOLOGY AND MANAGEMENT

Avalahalli, Yelahanka, Bengaluru-560064
2022-2023
 B.M.S. INSTITUTE OF TECHNOLOGY AND MANAGEMENT
Yelahanka, Bengaluru-560064

DEPARTMENT OF ELECTRICAL AND ELECTRONICS ENGINEERING

Vision
To emerge as one of the finest Electrical and Electronics Engineering departments facilitating
the development of competent professionals, contributing to the betterment of society.
Mission

Create a motivating environment for learning Electrical Science through teaching, research,
effective use of state of the art facilities and outreach activities.

Program Outcomes (POs)

1. Engineering knowledge: Apply the knowledge of Mathematics, Science, Engineering
fundamentals and an engineering specialization to the solution of complex engineering problems

2. Problem analysis: Identity, formulate, review research literature, and analyze complex
Engineering problems reaching substantiated conclusions using the first principles of mathematics,
Natural sciences and engineering sciences

3. Design/development of solutions: Design solutions for complex engineering problems and

design system components or processes that meet the specified needs with appropriate consideration
for public health and safety, and cultural, societal, and environmental considerations.

4. Conduct investigations of complex problems: Use research-based knowledge and research

methods including design of experiments, analysis and interpretation of data, and synthesis of the
Information to provide valid conclusions.
 5. Modern tool usage: Create, select, and apply appropriate techniques, resources, and modern
Engineering and IT tools including prediction and modelling to complex engineering activities with
an understanding of the limitations.

6. The engineer and society: Apply reasoning informed by the contextual knowledge to assess
societal, health, safety, legal and cultural issues and the consequent responsibilities relevant to the
professional engineering practice.

7. Environment and sustainability: Understand the impact of the professional engineering

solutions in societal and environmental contexts, and demonstrate the knowledge of, and need for
Sustainable development

8. Ethics: Apply ethical principles and commit to professional ethics and responsibilities and norms
of the engineering practice.

9. Individual and team work: Function effectively as an individual, and as a member or leader in
diverse teams, and in multidisciplinary settings

10. Communication: Communicate effectively on complex engineering activities with the

engineering Community and with society at large, such as, being able to comprehend and write
effective reports and design documentation, make effective presentations, and give and receive clear
instructions.

11. Project management and finance: Demonstrate knowledge and understanding of the
Engineering and management principles and apply these to one’s own work, as a member and
Leader in a team, to manage projects and in multidisciplinary environments.

12. Life-long learning: Recognize the need for, and have the preparation and ability to engage in
independent and life-long learning in the broadest context of technological

Program Educational Objectives (PEOs)

Our Graduates will be able to

PEO–1: Work as Professionals in the area of Electronics, Electrical, and Allied

Engineering fields.
PEO–2: Pursue Higher studies and involve in Interdisciplinary research work.
PEO--3: Exhibit Ethics, Professional skills and Leadership qualities in their profession.
 Program-Specific Outcomes (PSOs)

PSO – 1: Demonstrate the knowledge of electronic devices, circuits, micro-nano electronics,

and other fundamental courses to exhibit competency in the domain of VLSI design.
PSO – 2: Comprehend the gathered knowledge and technological advancements in the field
of communication and signal processing.
PSO – 3: Exhibit the skills gathered to analyse, design, develop software applications and
hardware products in the field of embedded systems and allied areas.
 B.M.S. INSTITUTE OF TECHNOLOGY AND MANAGEMENT
Avalahalli, Yelahanka, Bengaluru-560064

DEPARTMENT OF ELECTRICAL AND ELECTRONICS

ENGINEERING

CERTIFICATE
Certified that the technical seminar entitled “CHAT BOT THERAPY FOR PATIENTS WITH
MENTAL HEALTH” presented by MD TABISH WIJDAN (1BY19EE026), a bonafide student
of BMS Institute of Technology and Management in partial fulfillment for the award of
bachelor of engineering in Electrical and Electronics under Visvesvaraya Technological
University, Belagavi during the year 2022-2023. It is certified that all corrections/suggestions
indicated for internal assessment have been incorporated in the report deposited in the
department library.

The seminar report has been approved as it satisfies the academic requirement in respect of
seminarwork prescribed for the said degree.

Signature of Guide Signature of HOD

Dr. N Ramarao Dr. Prashant Athavale
BMSIT&M Dept. of EEE BMSIT&M Dept. of EEE

i
 ACKNOWLEDGEMENT

The satisfaction and euphoria that accompany the successful completion of any task would be
incomplete without the mention of the people who made it possible and whose constant guidance
and acknowledgement crowned our effort with success.

We express our profound gratitude to our Principal, Dr. Mohan Babu G. N, BMS Institute of
Technology and Management for providing all the facilities and encouragement.
We would like to thank our HOD, Dr. Prashant Athavale. for the inspiration, guidance and
valuable suggestions.
Our sincere gratitude to our seminar coordinators, Mrs. Suma Umesh and Dr. N Ramarao for
their valuable time, suggestions, and technical support in conducting the seminar presentation and
writing the report.

Our sincere gratitude to our guide, Dr. N Ramarao for his valuable time, patience, suggestion
and periodic evaluation that was conducive to the project.

We would also like to thank all the teaching and non-teaching staff of the Department of
Electrical and Electronics Engineering for their cooperation and motivation.

Finally, we express our cordial thanks to our parents and friends for their support and guidance
throughout the project preparation.

Md Tabish Wijdan

ii
 ABSTRACT
Recent research from the World Health Organization has shown that over 264 million people
suffer from depression, which can even lead to suicide in severe cases. Stress and anxiety are
particularly prevalent among individuals aged 15-29, with various sources of depression
affecting this age group. Unfortunately, many people suffering from mental illness do not seek
help, either due to lack of resources or the belief that their condition is just a phase.
This is especially true for those in low-middle income countries, where trained healthcare
providers may be scarce. Chatbots can be a valuable resource for these individuals, providing
real- time support to anyone with an internet connection. While they cannot replace human
health practitioners, chatbots are an accessible and cost-effective means of addressing mental
health issues, particularly for students who may face financial and logistical barriers to
traditional therapy. These chatbots use Natural Language Processing to analyze a user's mood
and provide appropriate resources and guidance. In this study, we explore the benefits of chatbot
therapy and its use of cognitive-behavioral techniques.

iii
 CONTENTS

Certificate i
Acknowledgement ii
Abstract iii
Contents iv
List of Figures v

CHAPTER 1 : INTRODUCTION 1-2

1.1 OVERVIEW 1
1.2 PROBLEM STATEMENT 2
1.3 MOTIVATION 2

CHAPTER 2 : LTERATURE SURVEY 3-4

CHAPTER 3 : METHADOLOGY 5-6

CHAPTER 4 : ADVANTAGES 7
AND DISADVANTAGES
4.1 BENEFITS 7
4.2 LIMITATIONS 7

CHAPTER 5 : FUTURE SCOPE 8

CHAPTER 6 : CONCLUSION 9

CHAPTER 7 : REFERNCES 10

iv
 LIST OF FIGURES

Fig 3.1: The counseling chatbot architecture. 5

Fig 3.2: An example of spatial-temporal context analysis. 6

v
Chat bot therapy for patients with mental health 2022-2023

CHAPTER 1

INTRODUCTION
1.1 OVERVIEW

According to the World Health Organization (WHO), emotional well-being or mental health
refers to a state of prosperity in which an individual can utilize their abilities, recover from daily
stress, be productive, and contribute to society. Depression is one of the most common mental
health disorders, affecting 10-15% of the working-age population. India is on the brink of a
mental health epidemic, with a general weighted prevalence of any mental health-related distress
at 13.7%. The overall treatment gap for mental disorders ranges from 70% to 92% across
different disorders. Developed nations suggest that the ideal number of mental health
professionals should be 1 per 10,000 people. However, in India, the current figures are much
lower, with 0.2 psychologists, 0.03 psychiatrists, 0.03 mental social workers, and 0.05 mental
health nurses per 100,000 people. To bridge this gap, innovative solutions are required, and one
such solution could be the use of chat bot.
It enables computers to imitate human thinking and behavior, and chatbots are a type of
computer program that uses natural language to interact with users. Digital interfaces and
chatbots have emerged as viable alternatives to traditional psychiatric diagnosis and treatment,
making mental healthcare more accessible and affordable. There is still a stigma associated with
psychiatric disorders that often prevents people from seeking help. In addition, young adults or
college students may hesitate to seek treatment or may lack the time to fulfill their mental health
needs. Chat bot has helped develop in various fields of psychiatry, including the prediction and
prevention of suicide, the identification of the most suitable drug for a patient, and more.
Chatbots initiate conversations that can be conducted on different platforms, such as messaging
or voice chat. Some chatbots are fully automated, while others use human interfaces. Chatbots
have already gained popularity in customer service, addressing basic customer issues 24/7 at a
lower cost than customer service agents. Gartner predicts that by 2020, 25% of customer care and
support operations will use some form of chatbot, and by 2020, 85% of all customer care
interactions will be handled by a chatbot. In mental health, chatbots can provide support, therapy,
and companionship, reducing the burden on therapists and making mental healthcare more
affordable and accessible. However, there are concerns about privacy, monitoring, lack of
standardization, overdependence on chatbots, and the risk of missing severe mental health issues.

BMSIT&M, Department of EEE 1

Chat bot therapy for patients with mental health 2022-2023

1.2 PROBLEM STATEMENT

Mental health is a complex and multifaceted issue that affects individuals, families, and
communities. It can manifest in various ways, including anxiety, depression, substance abuse,
bipolar disorder, schizophrenia, and other mental illnesses. The problem of mental health is
compounded by the stigma surrounding mental illness, lack of access to mental health services,
and inadequate funding for research and treatment. The consequences of untreated mental illness
can be severe, including reduced quality of life, increased risk of suicide, and negative impacts on
physical health. To address the problem of mental health, it is necessary to increase public
awareness and education, reduce stigma, improve access to mental health services, and increase
funding for research and treatment.

1.3 MOTIVATION
Mental health is not much encouraged in majority of the population, due to which person with
mental illness won’t be getting enough support and guidance. Person with mental health
conditions won’t feel comfortable in opening up their problems. Chatbot therapy is a growing
field in which chatbots are trained to provide support, guidance, and motivation to individuals
seeking mental health care. This type of therapy is designed to supplement traditional therapy and
can be accessed through mobile apps or websites.

BMSIT&M, Department of EEE 2

Chat bot therapy for patients with mental health 2022-2023

CHAPTER 2

LITERATURE SURVEY

Literature Survey is an important phase in the system development life cycle as we collect and
acquire the necessary information to handle or develop a project during this phase. A literature
review is a description of the literature relevant to a particular field or topic. It gives an overview
of what has been said, who the key writers are, what are the prevailing theories and hypothesis
and what methods and what methodologies are appropriate and useful.
Reference [1] proposed an unobtrusive emotion recognition approach for affective social
communication on mobile devices. They discovered 10 features related to the emotional state of
the human user; these features were mainly divided into user behavioral patterns (e.g., typing
speed) and the user context (e.g., location). The accuracy of emotional classification showed
67.52% on average for seven emotional states: happiness, surprise, anger, disgust, sadness, fear,
and neutral.
Reference [2] presented a framework based on committee machines of deep CNNs and its
application to robust FER. They demonstrate on the SFEW2.0 competition data released for the
EmotiW2015 challenge. Based on three level hierarchical committees of total 240 deep CNNs,
they achieved 61.6% test accuracy, greatly outperforming the baseline of 39.1 %.
Reference [3] utilized the soft attention mechanism to temporally align the audio and visual
streams and fuse these streams in the feature level. In addition, they added the emotion embedding
vectors in the output layer of RNN to locate and re-weight the perception attentions in the
audiovisual stream.
Reference [4] focused on automatically analyzing a speaker’s sentiment in online videos
containing movie reviews. They considered adding audio and video features for encoding valuable
valence information conveyed by the speaker. Recently, there were many studies on emotion
analysis based on multi-modal approaches. So far, there is a limitation of emotion recognition
technology using single information. Currently, most studies use only one type of data such as
voice, sound, image data, so those have limitations in performance. Human can infer the other’s
emotions from information such as voice dialogues, intonation, facial expression, gesture, age,
gender, and so on. Furthermore, it has the ability to recognize the degree of emotional stress and
respond to the situations. In intelligent assistant, a new model for emotional analysis is needed
using such multi-modal information. It is necessary to develop multi-modal method that can
obtains considering the strength of each modality, and various information at the same time. In
addition, bi-directional dialogue analysis is not applied. Until now, it is an initial stage in
emotion recognition, and there is a limitation of artificial intelligence model, which does not
utilize the dialogues. The level of applications has been limited because the user’s emotion and
BMSIT&M, Department of EEE Page 3
Chat bot therapy for patients with mental health 2022-2023
state.

BMSIT&M, Department of EEE Page 4

Chat bot therapy for patients with mental health 2022-2023

determine and deduced by one-time recognition from external factors such as speech recognition
of words and sentences, and image recognition of faces, peripheral, and location.

BMSIT&M, Department of EEE Page 5

Chat bot therapy for patients with mental health 2022-2023

CHAPTER 3

METHODOLOGY

the chatbot that provides conversational service for psychiatric counseling collect and
summarizes the dialogues of text, voice, and video information to recognize user’s emotions.
Based on the information, the purpose of the service is to develop a personalized dialog system
that communicate emotionally with the user through text, voice, and visual expression. For this,
we adopt follows approaches. It is distribution three parts: understanding conversation,
emotional recognition, and expression for communications. Figure 6 shows the architecture of the
chatbot to provide psychiatric counseling.
The conversational service is a type of counseling, so we should understand dialogues between
user and Chatbot based on various natural language understanding methods.
A. Defining Emotional Expression Model to Categorize
Most of all, we should determine a representative emotional model which can express more than
eight kinds of emotions for emotion recognition, learning, and inferencing [9]. The model should
be designed to reflect the features of eight types of emotions according to conversation, voice,
and image.
B. Collecting Training Data for Emotion Recognition
We should collect training data which contains emotional information from various media such
as dramas and radio and collects also actual dialogues containing emotions through the
community and SNS using emotional chat bots to construct corpuses.

Figure 3.1 The counseling chatbot architecture.

C. Emotion Recognition and Inference
In this part, a technique uses for judging and inferring the emotions of a user by fusing mutual

BMSIT&M, Department of EEE Page 6

Chat bot therapy for patients with mental health 2022-2023
utterance text, voice, and image information. In addition, additional user information such as facial
expression, age, and sex, spatial context, location context, and bio-signals collected via wearable
devices. It is possible to expand to various applications by improving emotional intelligence
technology based on such the user information.

Figure 3.2 An example of spatial-temporal context analysis.

D. Continuous Emotional Monitoring
Observations of persistent emotional changes are very important in psychiatric counseling to
improve the effectiveness of counseling. We apply the user emotion tracking method based on life
logging. The maintenance system should construct for continuous information collection. Through
this, it is possible to enhance emotional collection based on biological signal sensor and emotion
recognition model.

BMSIT&M, Department of EEE Page 7

Chat bot therapy for patients with mental health 2022-2023

CHAPTER 3

ADVANTAGES AND DISDAVANTAGES

4.1 BENEFITS OF CHATBOT THERAPY

1. Accessibility: Chatbot therapy is available 24/7, providing individuals with consistent

support and motivation whenever they need it.
2. Personalization: Chatbots can be tailored to the individual's needs, providing personalized
guidance and recommendations for mental health care.
3. Interactive: Chatbots can engage individuals in interactive activities such as breathing
exercises, mindfulness exercises, or cognitive-behavioural therapy exercises, which can help
boost motivation and engagement.
4. Accountability: Chatbots can help individuals set goals and provide reminders to stay on track
with their mental health care plan, promoting accountability and motivation.
5. Privacy: Chatbots provide a safe and private space for individuals to discuss their mental
health concerns without fear of judgment.

4.2 LIMITATIONS OF CHATBOT THERAPY

1. Lack of Human Connection: Chatbot therapy lacks the human connection that is often
necessary for effective mental health care.
2. Limited Scope: Chatbot therapy is limited in scope and may not be able to provide the depth
of treatment that traditional therapy can provide.
3. Technical Issues: Technical issues with the chatbot platform can hinder the effectiveness of
the therapy and may cause frustration for users.

BMSIT&M, Department of EEE Page 8

Chat bot therapy for patients with mental health 2022-2023

CHAPTER 4

FUTURE SCOPE

The future scope of chatbots is very promising as they continue to evolve and improve with
advancements in technology. Here are some potential areas where chatbots could be used in the
future:

1. Customer Service: Chatbots are already being used in customer service to provide quick
and efficient responses to customer inquiries. In the future, chatbots could become even
more sophisticated and capable of handling more complex queries.

2. Healthcare: As mentioned earlier, chatbots have great potential in the field of mental
health. They could also be used in other areas of healthcare, such as providing medical
advice and answering common health-related questions.

3. Education: Chatbots could be used in education to provide personalized learning

experiences to students. They could also be used to answer questions and provide support
to students who are struggling.

4. Finance: Chatbots could be used in the finance industry to provide financial advice and
answer questions about banking, investments, and other financial matters.

5. E-commerce: Chatbots could be used in e-commerce to provide product

recommendations, answer questions about products, and help customers complete their
purchases.

6. Personal Assistant: Chatbots could be used as personal assistants to help people manage
their schedules, make appointments, and complete tasks.

Overall, chatbots have the potential to be used in a wide range of industries and applications. As
they continue to improve and become more advanced, it is likely that we will see chatbots being
used in more and more areas of our lives.

BMSIT&M, Department of EEE Page 9

Chat bot therapy for patients with mental health 2022-2023

CHAPTER 5

CONCLUSION

In conclusion, chatbot therapy has great potential in providing mental health support to patients.
It offers a convenient and accessible way for patients to receive mental health treatment in the
comfort of their own homes. The chatbot therapy can use evidence-based therapies, such as
cognitive-behavioral therapy (CBT), to provide personalized treatment plans to patients. The data
collection capabilities of chatbots can be used to monitor patient progress and make adjustments
to the treatment plan accordingly.

Chatbot therapy can also address some of the challenges that traditional therapy faces, such as
the lack of mental health professionals, long wait times, and stigma associated with seeking
treatment. With chatbot therapy, patients can receive treatment without feeling judged or
stigmatized.

However, there are still challenges that need to be addressed in the development of chatbot
therapy, such as ensuring that the chatbot is user-friendly, interactive, and empathetic. It is also
important to consider the ethical implications of using chatbots for mental health treatment and
ensure that patient privacy and confidentiality are protected.

Overall, chatbot therapy offers a promising future in providing accessible, affordable, and
personalized mental health treatment to patients. As the technology continues to evolve and
improve, we can expect to see chatbot therapy being used in more areas of mental health
treatment, including anxiety, depression, and other mental health conditions.

BMSIT&M, Department of EEE Page

10
Chat bot therapy for patients with mental health 2022-2023

CHAPTER 7

REFERENCE
[1] Ly, K. H., Ly, A. M., Andersson, G., & Lichtenstein, L. (2020). Engagement and therapeutic
alliance in digital mental health interventions for anxiety and depression: A systematic review.
Journal of Medical Internet Research, 22(4), e13213.
[2] Fulmer, R., Joerin, A., Gentile, B., & Lakerink, L. (2018). Using psychological artificial
intelligence (Tess) to relieve symptoms of depression and anxiety: Randomized controlled trial.
Journal of Medical Internet Research, 20(8), e216. h
[3] Fitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017). Delivering cognitive behavior therapy to
young adults with symptoms of depression and anxiety using a fully automated conversational
[4] Torous, J., Chan, S. R., Tan, S. Y., Behrens, J., Mathew, I., Conrad, E. J., & Hilty, D. M. (2018).
Patient smartphone ownership and interest in mobile apps to monitor symptoms of mental health
conditions: A survey in four geographically distinct psychiatric clinics. JMIR Mental Health, 5(1),
e14.
[5] van Ballegooijen, W., Riper, H., Cuijpers, P., van Oppen, P., Smit, J. H., & Riper, H. (2016).
Validation of online psychometric instruments for common mental health disorders: A systematic
review. BMC Psychiatry, 16(1), 1-10.

BMSIT&M, Department of EEE Page