Barrios, Armand Angelo C. <br/><br/>
Summpy:   development of an optimized summarization framework for thesis into structured imrad format utilizing the bart large language model and textrank algorithms for enhanced academic writing and research efficiency/ 
Armand Angelo C. Barrios, Sophia Mer C. Enriquez, Almira Jill O. Garcia, Janna Rose V. Herrera, and Andrew R. Oloroso.-- 
 - Manila:  Technological University of the Philippines,  2025. 
 - ix, 142pages:  29cm. 
<br/><br/> Bachelor's thesis<br/><br/><br/> 
<br/><br/>College of Science.--<br/> 
<br/><br/>Includes bibliographic references and index. 
<br/><br/> This study presents SummPy, a web-based application designed to generate structured<br/>summaries of academic theses using the IMRaD format that includes Introduction, Methods,<br/>Results, and Discussion. With the increasing volume and complexity of academic research,<br/>students and professionals often face challenges in efficiently digesting and summarizing<br/>lengthy documents. SummPy addresses this by leveraging advanced Natural Language<br/>Processing (NLP) techniques and Large Language Models (LLMs), specifically BART for<br/>abstractive summarization and TextRank for extractive summarization. The system processes<br/>the uploaded PDF files of the users, the system uses hierarchical multi-threading for<br/>efficiency, and evaluates the coherence and accuracy of generated summaries using<br/>DistilBERT for semantic similarity analysis.<br/>The project followed a systematic methodology involving document segmentation,<br/>parallel processing, summarization, and evaluation. Results demonstrate that SummPy<br/>effectively produces accurate, well-structured summaries that maintain the original research's<br/>context and key insights. The tool significantly reduces the time and effort required for<br/>manual summarization, offering a practical solution for academic and professional use.<br/>Evaluation metrics indicate high usability, security, and portability, affirming its adaptability<br/>across various environments. In conclusion, SummPy emerges as a valuable resource for<br/>enhancing academic productivity, understanding, and knowledge dissemination. 
<br/><br/><label>Subjects--Topical Terms: </label><br/>IMRAD format<br/>Abstractive summarization<br/>Semantic similarity analysis
<br/><br/><label>LC Class. No.: </label>BTH T 58.5  / B37 2025