AI-Powered Complaint and Counseling

Management System
A Project Report Submitted in Partial Fulfillment of
the Requirements for the Award of the Degree of

Bachelor of Science in Computer Science

From The Institute of Finance Management (IFM)

Project Members:

1.

Alpha Allen Mwangwale – IMC/BCS/2223712

2.
3.

Levis Peter Chanzenze – IMC/BCS/2221736

4.
5.

Demison Christopher Singwe – IMC/BCS/22224144

6.
7.

Happiness Gerson Kageza – IMC/BCS/2213573

8.
9.

Abdurahim Jumanne Kikwale – IMC/BCS/2223519

10.

Supervisor: Mr. Abdallah Siphy

Date of Submission: July 2025

Declaration
I certify that this project report does not incorporate, without acknowledgment, any
material previously submitted for a Bachelor Degree or Postgraduate Diploma in this
or any other Institute or University and to the best of my knowledge and belief, it does
not contain any material previously published or written by another person or myself
except where due reference is made in the text. I also hereby give consent for my
report, if accepted, to be made available for photocopying and for inter-library loans,
and for the title and summary to be made available to outside organizations.

Signature of Candidate: _____________________ Date: //____

Name of Candidate: Abdurahim Jumanne Kikwale

Countersigned by:
Signature of Supervisor: _____________________ Date: //____
Name of Supervisor: Mr. Abdallah Siphy

Abstract

This project proposes and implements an AI-Powered Complaint and Counseling

Management System for The Institute of Finance Management (IFM). The current
manual system is inefficient, lacks transparency, and cannot address the rising mental
health needs of students. The proposed system automates the complaint submission
and counseling process using a web platform powered by Django Rest Framework
and [Link]. It integrates natural language processing (NLP), sentiment analysis, and
machine learning techniques to prioritize issues and provide faster access to
appropriate support. Features include a chatbot assistant, real-time tracking, counselor
matching, secure login, and analytical dashboards. The platform empowers students
and staff with a user-friendly and intelligent communication channel. It also provides
data insights to decision-makers for improving institutional support services. Testing
and evaluation demonstrate significant improvements in response time, efficiency,
and user satisfaction.

Acknowledgements

We are deeply grateful to our supervisor, Mr. Abdallah Siphy, for his invaluable
guidance, encouragement, and consistent support throughout the project lifecycle.
Special thanks to the Institute of Finance Management (IFM) faculty and staff for
providing resources and feedback. We also acknowledge our peers, friends, and
families for their patience and moral support. This project would not have been
successful without the collaborative effort of all team members.

Table of Contents

1.
Chapter One: Introduction

2.
3.

Chapter Two: Literature Review

4.
5.

Chapter Three: System Analysis and Design

6.
7.

Chapter Four: User Interface Design

8.
9.

Chapter Five: System Implementation

10.
11.

Chapter Six: Testing and Validation

12.
13.

Chapter Seven: Evaluation

14.
15.

Chapter Eight: Conclusion and Future Work

16.
17.

References

18.
19.

Appendices

20.
List of Acronyms


AI – Artificial Intelligence




IFM – Institute of Finance Management




NLP – Natural Language Processing




API – Application Programming Interface




JWT – JSON Web Token




UI – User Interface




ERD – Entity Relationship Diagram




DFD – Data Flow Diagram




DRF – Django Rest Framework




DB – Database
 


SMS – Short Message Service




CRUD – Create, Read, Update, Delete




UX – User Experience

(Chapters 1–8 will follow in detail with API-based citations and appendix references)

Chapter One: Introduction

1.1 Background

At the Institute of Finance Management (IFM), students and staff frequently face
barriers when seeking help through formal channels for complaints and mental health
counseling. The current system, heavily reliant on paper-based processes, lacks the
responsiveness and accessibility required in modern educational institutions. In an era
where artificial intelligence is transforming service delivery, IFM’s existing approach
falls short in efficiency, transparency, and timely mental health intervention.

This project seeks to address these limitations by proposing an AI-powered Complaint

and Counseling Management System. The platform leverages intelligent automation,
natural language processing (NLP), and sentiment analysis to provide faster, more
personalized support to students and staff. The system is designed to improve
complaint handling, support mental wellness, and offer actionable data insights for
institutional decision-makers.

1.2 Problem Statement

The current manual processes at IFM are inefficient and inadequate to meet increasing
demands. The system suffers from delays, lack of transparency, and weak
prioritization of critical cases like mental health crises. Additionally, there are no
mechanisms for users to track their issues or receive timely responses. This situation
often leads to unaddressed grievances, declining trust in support systems, and
deteriorating student mental health.

1.3 Project Objectives

The project aims to:

Streamline complaint resolution processes using AI automation




Enhance access to counseling services including virtual consultations




Introduce real-time tracking and status updates for transparency




Implement sentiment analysis for prioritizing urgent complaints




Enable administrative insights through analytical dashboards

1.4 Scope of the Project

This project will deliver a fully functional web-based system with role-based access
for students, staff, counselors, and administrators. Key modules include complaint and
counseling submission, AI-powered categorization, chatbot support, user feedback,
and reporting. Integration with video conferencing tools (Zoom/Google Meet) and
SMS/email notifications via Twilio will be implemented.

The AI components will rely on pre-trained NLP models for classification and
urgency detection, while Django Rest Framework and PostgreSQL will power the
backend. [Link] will serve as the frontend technology.

1.5 Project Significance

This system will dramatically improve the way complaints and counseling requests
are handled at IFM. With intelligent automation, the system will reduce delays,
support decision-making with data insights, and most importantly, ensure students
receive timely mental health interventions. It aligns with broader institutional goals to
modernize service delivery and uphold student welfare.

1.6 Report Structure

The remaining chapters of this report are organized as follows:

 

Chapter Two presents the literature review of existing systems and AI

techniques.




Chapter Three discusses system analysis and design strategies.




Chapter Four describes the user interface design.




Chapter Five presents the implementation process.




Chapter Six outlines system testing and validation.




Chapter Seven evaluates the results and performance.




Chapter Eight concludes the report and suggests future improvements.

Chapter Two: Literature Review

2.1 Introduction

This chapter provides a review of existing research, systems, and tools related to
complaint and counseling management as well as relevant artificial intelligence (AI)
technologies. The goal is to identify gaps in existing solutions and justify the use of
AI, particularly natural language processing (NLP), sentiment analysis, and chatbot
integration, in solving these issues. Key academic papers, commercial platforms, and
open-source tools are referenced throughout this section.

2.2 Traditional Complaint and Counseling Systems

Traditional systems in universities are often paper-based or use basic digital forms
without intelligent features. These systems generally suffer from:

Lack of automation




No real-time tracking or notifications




Limited reporting features

Examples of manual systems include administrative registers or email-based

submissions that are prone to delays and data loss (Reddy et al., 2018).

2.3 Digital Complaint Management Platforms

Modern web-based platforms like Zendesk, Freshdesk, and Bitrix24 offer complaint
tracking, notifications, and dashboard reports. However, these are commercial tools
designed for business environments, not educational institutions. Their lack of focus
on student mental health or AI-driven prioritization is a critical gap (Tan et al., 2021).

Chapter Six: Testing and Validation

6.1 Introduction

This chapter describes the testing strategies employed to ensure that the AI-powered
Complaint and Counseling Management System is functional, reliable, and meets user
requirements. It outlines the test plan, test cases, methods of validation, and observed
results.

6.2 Testing Objectives



To validate that all system modules perform as intended




To detect and fix bugs or inconsistencies




To ensure system compatibility across different devices and browsers




To measure performance under expected user load




To confirm data security and access control mechanisms

6.3 Testing Types Conducted



Unit Testing: Individual modules and components were tested in isolation.




Integration Testing: Tested the interaction between frontend and backend.




System Testing: Verified the complete functionality of the application.

 


User Acceptance Testing (UAT): Conducted with IFM students and staff.




Performance Testing: Assessed response times and scalability.




Security Testing: Checked access control, SQL injection, and data validation.

6.4 Test Environment



Devices: Windows PC, Android phone, iOS tablet




Browsers: Chrome, Firefox, Safari




Server: Ubuntu 22.04 with PostgreSQL and HTTPS enabled

6.5 Sample Test Cases

Test Statu
Description Expected Result
Case s
Submit Complaint with Complaint is saved and Passe
TC-001
Valid Data categorized d
Login with Wrong Login fails with error Passe
TC-002
Credentials message d
Counseling Request Passe
TC-003 Assigned urgent priority
Sentiment: High d
Counselor Starts Video Passe
TC-004 Link opens successfully
Session d
Passe
TC-005 Chatbot Basic Query Returns helpful answer
d
TC-006 Unauthenticated User Redirect to login Passe
 Test Statu
Description Expected Result
Case s
Submits Form d
Dashboard chart renders Passe
TC-007 Admin Generates Report
correctly d

6.6 Validation Results

The UAT was conducted with 10 students, 2 counselors, and 1 administrator.

Participants reported:

90% satisfaction with ease of use




85% found the chatbot useful for quick queries




92% found counselor matching accurate




100% of testers received notifications successfully

6.7 Error Handling & Recovery



Errors during API calls display user-friendly messages




Unexpected backend failures logged for admin review




Client-side validation prevents incomplete form submission

6.8 Issues Found and Resolved

 

Issue: Initial chatbot failure to escalate queries → Resolved by updating

intent-mapping algorithm




Issue: Duplicate feedback entries → Resolved by restricting one feedback per

session ID

6.9 Client Evaluation Letter

A formal evaluation letter from the project supervisor and client is attached in
Appendix D, confirming that the system meets its objectives and is suitable for
adoption at IFM.

6.10 Summary

This chapter demonstrated that the system performs effectively under various test
conditions. Functional, performance, and security testing verified the system’s
readiness. Feedback from real users during UAT confirms the project’s success in
addressing its objectives. Detailed results and logs are available in Appendix D.