D'Aniello, Luca (2024) From Scientific Knowledge Synthesis to Cutting-Edge Discovery: The Innovative Potential of Automatic Text Summarization in Scientific Literature. [Tesi di dottorato]
![[thumbnail of Phd_thesis_LucaDAniello.pdf]](https://www.fedoa.unina.it/style/images/fileicons/other.png "Phd_thesis_LucaDAniello.pdf") |
Documento PDF
Phd_thesis_LucaDAniello.pdf Visibile a [TBR] Amministratori dell'archivio Download (2MB) | Richiedi una copia |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | From Scientific Knowledge Synthesis to Cutting-Edge Discovery: The Innovative Potential of Automatic Text Summarization in Scientific Literature |
| Autori: | Autore Email D'Aniello, Luca luca.daniello@unina.it |
| Data: | 11 Dicembre 2024 |
| Numero di pagine: | 145 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dipartimento: | Scienze Sociali |
| Dottorato: | Scienze sociali e statistiche |
| Ciclo di dottorato: | 37 |
| Coordinatore del Corso di dottorato: | nome email Amaturo, Enrica enrica.amaturo@unina.it |
| Tutor: | nome email Cataldo, Rosanna [non definito] Savonardo, Raffaele [non definito] |
| Data: | 11 Dicembre 2024 |
| Numero di pagine: | 145 |
| Parole chiave: | Automatic Text Summarization; Information retrieval; Knowledge extraction; Information overload; Integrated Text Summarization |
| Settori scientifico-disciplinari del MIUR: | Area 13 - Scienze economiche e statistiche > SECS-S/05 - Statistica sociale |
| Informazioni aggiuntive: | APPARTENGO AL 37 CICLO DI DOTTORATO IN SCIENZE SOCIALI E STATISTICHE. |
| Depositato il: | 23 Ott 2025 09:31 |
| Ultima modifica: | 09 Ago 2026 05:59 |
| URI: | https://www.fedoa.unina.it/id/eprint/16447 |
Abstract
Researchers have extensively studied the mechanisms that drive the expansion and progression of scientific knowledge. The field of the science of science examines how scientific knowledge grows and evolves, primarily through disseminating research articles. However, as understanding these mechanisms has deepened, a significant new challenge has emerged: an information overload generated by the rapid surge in scientific publications. Automatic Text Summarization (ATS) arose as a crucial tool for addressing this challenge, offering concise, relevant summaries by reducing redundancy in large text corpora. This thesis introduces the Integrated Text Summarization (ITS), a novel ATS approach explicitly designed for the scientific domain. The ITS framework harnesses the distinct characteristics of scientific texts and bibliographic metadata, including their structured format, author-provided keywords, and algorithmically identified key terms, to generate precise and informative summaries. The research evaluates ITS by comparing its performance in extracting relevant sentences from scientific articles against traditional summarization methods and summaries generated by Large Language Models. This comparison not only explores the potential of ITS and AI-driven summarization to enhance the precision and efficiency of managing and synthesizing scientific knowledge, but also highlights the significant progress and evolution in the field of information science and technology. The thesis advances ATS research by addressing theoretical and practical dimensions, offering an innovative framework to improve access to scientific content rapidly and effectively in an era of exponential information growth.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
