SumUp : Text Summarization App

Moey, Ryan Kai Xiang (2026) SumUp : Text Summarization App. Final Year Project (Bachelor), Tunku Abdul Rahman University of Management and Technology.

Text RSW_Ryan Moey Kai Xiang_Fulltext.pdf Restricted to Registered users only Download (6MB)

Abstract

In today’s digital era, students are often exposed to massive amounts of text information like lecture notes, academic papers, and reports, rendering them frequently in a state of information overload and cognitive fatigue. Limited time and rising academic expectations place additional constraints on students as they search for effective means to read, process, comprehend, and memorize significant content. This project aims to help solve this problem with SumUp, a mobile application for text summarization developed for helping students summarize lengthy documents more efficiently. SumUp applies techniques of Natural Language Processing (NLP) based on an abstractive text summarization mechanism to produce short but meaningful summaries from user input text/documents, in PDF, DOCX, and TXT formats. It integrates a Transformer-based model (T5) with the Hugging Face framework for producing human-like summaries that respect the context and meaning of the original text. Additionally, SumUp offers learning-supporting features, including quizzes and flashcards. A history module is installed from which a user can retrieve past summaries and a chat and sharing feature, both in real-time, further help facilitate collaborative learning among users. The application uses Kotlin with Jetpack Compose for the Android frontend and is backed purely in Python under FastAPI for NLP processing. Firebase services are used for authentication, chat real-time data exchange, and data storage. The system was evaluated via unit testing, integration testing, and user acceptance testing to guarantee functionality, usability, and performance. The results show that SumUp reduces the time spent reading and cognitive load and thus their accompanying distractions toward a more enhanced learning experience. The project proposes that blending AI-backed text summarization with interactive learning features strongly enhances students' academic productivity and learning experience.