AI-Based Email Sorting and Summarization

Abstract

The rapid growth of digital communication has resulted in a significant increase in the volume of emails received by individuals and organizations. Managing large numbers of emails often leads to reduced productivity and information overload. This paper proposes an Artificial Intelligence (AI) based email management system that automatically categorizes, summarizes, prioritizes, and schedules emails using Natural Language Processing (NLP) techniques. The system integrates machine learning models with Gmail API and Google Calendar API to provide automated inbox organization and productivity support. Emails are categorized into predefined groups such as work, personal, spam, and promotions. Long email messages are summarized using the Bidirectional and Auto-Regressive Transformer (BART) model to extract the most relevant information and present it in concise form. The system also identifies meeting schedules in emails and automatically creates reminders in the user\'s calendar to ensure important events are not missed. The proposed architecture is implemented using Python and Flask as the backend framework. Experimental observations indicate that the proposed system significantly improves email readability and reduces the time required to process large volumes of messages. The system demonstrates the potential of AI-powered solutions in improving digital communication efficiency.

Introduction

Email is a widely used communication tool, but the large number of daily messages—such as work emails, promotions, spam, and personal messages—makes inbox management difficult and time-consuming. Traditional email systems rely on simple rule-based filters and folders, which require manual setup and cannot understand the actual meaning of email content.

Recent advancements in Artificial Intelligence (AI) and Natural Language Processing (NLP) enable intelligent systems that can automatically analyze and manage textual data. This research proposes an AI-based Email Sorting and Summarization System that automates inbox management by classifying emails into categories such as work, spam, promotions, and personal messages. It also generates summaries of long emails to help users quickly understand the main information. Additionally, the system detects meeting-related details in emails and automatically schedules reminders using Google Calendar.

The system integrates multiple technologies including machine learning models, Gmail API, transformer-based summarization (BART), and Flask for the web interface. The architecture consists of layers for data collection, processing, summarization, scheduling, and user interaction. Emails are retrieved securely using OAuth authentication, processed with NLP techniques, categorized, summarized, and analyzed for meeting information.

The system was implemented in Python and tested using emails retrieved through the Gmail API. Results show that the classification module accurately categorized emails, the summarization module reduced long messages into concise summaries, and the meeting detection feature successfully created calendar reminders.

Overall, the proposed system improves email management efficiency, reduces inbox overload, and enhances productivity by automating tasks such as email sorting, summarization, prioritization, and meeting scheduling.

Conclusion

This research presented an AI-based email sorting and summarization system designed to reduce email overload and improve productivity. The system integrates machine learning, natural language processing, and Gmail services to provide intelligent inbox management. The proposed system demonstrates the potential of AI technologies in improving digital communication systems by automating repetitive tasks and organizing large volumes of information. Future work may include integrating voice-based interaction systems similar to digital assistants, implementing smart reply generation for automated responses, and extending the system to support multilingual email processing. Additional improvements may include mobile application integration and enhanced machine learning models for improved classification accuracy.

References

[1] T. Ayodele, R. Khusainov, and D. Ndzi, “Email Classification and Summarization: A Machine Learning Approach.” [2] T. Ayodele, Z. Zhou, and R. Khusainov, “Email Grouping and Summarization: An Unsupervised Learning Technique. [3] I. Alsmadi and I. Alhami, “Clustering and Classification of Email Contents. [4] T. Oya and G. Carenini, “Summarization and Dialogue Act Modeling on Email Threads. [5] E. G. Dadaa, J. Bassia, H. Chiroma, S. Muhammad, and A. Adetunmbi, “Machine Learning for Email Spam Filtering: Review, Approaches and Open Problems. [6] Y. Zhang et al., “EMAILSUM: Abstractive Email Thread Summarization. [7] K. Zhang, J. Chen, and D. Yang, “Focus on the Action: Learning to Highlight and Summarize Jointly for Email To-Do Items Summarization. [8] F. Zhu, “Automatic Classification for Unlabeled Email Messages into Folder. [9] N. S. Khedkar, P. Kumar, and A. K. E. Rojas, “Email Intelligence: An AI-Driven Framework for Context-Aware Office Communication Management.

Copyright

Copyright © 2026 Ashna Rachel Mathew , Gayathri Suri Varrier , Neeraj S, Tia Bobby. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.