Background of the Study
In today’s digital age, university email systems serve as a primary mode of communication between students, faculty, and administrative staff. However, with the increased use of email comes the challenge of spam, which can clutter inboxes, reduce productivity, and increase the risk of phishing attacks. Traditional methods of filtering spam are often inadequate due to their inability to adapt to evolving spam tactics. Artificial Intelligence (AI) has emerged as a promising solution, with machine learning models capable of classifying emails as spam or legitimate based on various features such as email content, sender information, and user interaction. This study aims to evaluate AI-based email spam detection models at Federal Polytechnic, Mubi, Adamawa State, to enhance email system efficiency and security.
Statement of the Problem
Spam emails in university systems are a persistent problem, resulting in wasted time, security risks, and decreased productivity for both students and faculty. Traditional spam filters based on predefined rules and keyword matching are limited in their ability to detect more sophisticated spam messages. AI-based email spam detection systems, which utilize machine learning algorithms to classify emails based on complex patterns, offer a potential solution. However, there is a need to evaluate the effectiveness of these AI models in the context of university email systems, especially in institutions like Federal Polytechnic, Mubi, where the challenges of spam are becoming increasingly prevalent.
Objectives of the Study
1. To design and implement an AI-based email spam detection system for Federal Polytechnic, Mubi.
2. To assess the accuracy and efficiency of the AI-based model in detecting spam emails compared to traditional methods.
3. To evaluate the user experience and satisfaction with the AI-based spam detection system.
Research Questions
1. How accurate is the AI-based email spam detection system in identifying spam messages compared to traditional methods?
2. What machine learning techniques are most effective in detecting spam emails in a university environment?
3. How does the implementation of AI-based spam detection impact the productivity and security of email users at Federal Polytechnic, Mubi?
Research Hypotheses
1. The AI-based spam detection system will outperform traditional spam filters in terms of accuracy and efficiency.
2. Machine learning algorithms, such as support vector machines and neural networks, will provide the best results in detecting spam emails.
3. The AI-based system will enhance user experience by reducing email clutter and improving security.
Significance of the Study
This research will contribute to the improvement of email system management in universities by demonstrating the effectiveness of AI-based spam detection. By ensuring that legitimate emails are prioritized and spam is filtered out, the study will promote a more productive and secure communication environment for students and faculty.
Scope and Limitations of the Study
The study will focus on evaluating AI-based spam detection models specifically for Federal Polytechnic, Mubi, Adamawa State. Limitations include the availability of email data for training and testing the AI model, as well as potential challenges in integrating the AI system into the existing email infrastructure.
Definitions of Terms
• AI-Based Spam Detection: The use of artificial intelligence techniques, such as machine learning, to automatically classify emails as spam or legitimate.
• Machine Learning: A subset of AI that involves training algorithms to recognize patterns in data and make predictions based on that data.
• Spam Email: Unsolicited, often irrelevant or harmful emails sent to a large number of recipients.
Chapter One: Introduction
1.1 Background of the Study
Political ideologies are fundamental in shaping the direction of policy-m...
Background of the Study:
Work-life balance refers to the equilibrium between professional responsibilities and personal lif...
INTRODUCTION
Every government, particularly those in developing countries, is worried about their country&...
Chapter One: Introduction
1.1 Background of the Study
Climate change poses a significant threat to rural livelihoods, particula...
Background of the Study
Financial inclusion strategies are crucial for integrating rural farmers into the formal financial system and enh...
Background of the Study
The registration process for examinations in secondary schools is often fraught with administrativ...
Background of the study
Plagiarism detection is critical in maintaining academic integrity, and AI-driven...
Background of the Study
Strategic repositioning involves redefining an organization’s strategic focus and market appr...
Chapter One: Introduction
1.1 Background of the Study
Jalin...
ABSTRACT
Statistics is playing an important role in virtually all aspect of human life. This role is used to analyze a p...