KWSSWS-IA Approach: An Intelligent Assistant for Scientific PDF Retrieval Using Semantic Analysis and AI-Driven Summarization
DOI:
https://doi.org/10.65405/fw7nxs09Keywords:
Intelligent search assistant, PDF retrieval, semantic analysis, summarization, NLP.Abstract
In the age of excessive information, traditional web search engines frequently fall short in providing accurate, contextually relevant results for scientific research. Furthermore, in addition to metadata-based retrieval, this study presents an enhanced version of the Keyword Search System on Web Searching (KWSSWS), which has evolved into an Intelligent Assistant (KWSSWS-IA) capable of deep semantic analysis of full-text PDF documents. The proposed system uses transformer-based artificial intelligence (AI) models related to natural language processing (NLP) to obtain and analyze internal document components, including title, abstract, keywords, and conclusions. It automatically generates brief, accurate summaries which is associated with ranks results according to scientific relevance rather than keyword frequency, in addition to recognizing significant scientific entities like authors, publication year, journal, and domain-specific terms KWSSWS-IA presents the following results on a single screen: download link, AI-generated summary, keyword match supplied by the user, publication year, title, and authors, and source journal. Therefore, ordinary search interfaces just offer hyperlinks. Experimental evaluation reveals significant improvements in precision, recall, and utilizer efficiency compared to standard Google Scholar searches. In addition, researchers who remain short on time and seeking high-quality, domain-relevant literature may find the strategy particularly useful.
Downloads
References
[1] Q. Ai, T. Bai, Z. Cao, Y. Chang, J. Chen, Z. Chen, et al., “Information retrieval meets large language models: A strategic report from Chinese IR community,” AI Open, vol. 4, pp. 80–90, 2023.
[2] I. Beltagy, K. Lo, and A. Cohan, “SciBERT: A pretrained language model for scientific text,” in Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP), 2019, pp. 3616–3621.
[3] M. Lewis et al., “BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension,” in Proc. Annu. Conf. Assoc. Comput. Linguistics (ACL), 2020, pp. 7871–7880.
[4] E. Fakroun and M. Sullabi, “Improving Web Search Results Using KWSSWS System,” Int. J. Eng. Innov. Technol. (IJEIT), vol. 13, no. 5, pp. 45–52, 2024.
[5] A. Hamoud and E. Atwell, “Quran QA Corpus for Data Mining with WEKA,” in Proc. Int. Conf. Smart Grids Commun. Adv. Comput. (SGCAC), 2016, pp. 112–117.
[6] C. Shah and E. M. Bender, “Envisioning information access systems,” ACM Trans. Web, vol. 18, no. 3, pp. 1–24, 2024.
[7] R. Kinney et al., “The Semantic Scholar Open Data Platform,” arXiv:2301.10140 [cs.IR], 2023.
[8] L. O. F. Ben Dalla, T. D. Medeni, I. T. Medeni, and M. Ulubay, “Enhancing healthcare efficiency at Almasara Hospital: Distributed data analysis and patient risk management,” Econ.: Strategy Pract., vol. 19, no. 4, pp. 54–72, 2025. [Online]. Available: https://doi.org/10.51176/1997-9967-2024-4-54-72
[9] S. Brin and L. Page, “The anatomy of a large-scale hypertextual web search engine,” Comput. Netw., vol. 30, no. 1–7, pp. 107–117, 1998.
[10] J. Beel, B. Gipp, S. Langer, and C. Breitinger, “Research-paper recommender systems: A literature survey,” Int. J. Digit. Libr., vol. 17, no. 4, pp. 305–338, 2016.
[11] W. Ammar et al., “Construction of the Semantic Scholar Corpus,” arXiv:1811.01462 [cs.CL], 2018.
[12] Z. Shen, H. Ma, and K. Wang, “A web-scale system for scientific knowledge exploration,” arXiv:1805.12216 [cs.IR], 2018.
[13] P. Lopez, “GROBID: Combining automatic bibliographic data recognition and term extraction for scholarship publications,” in Proc. Int. Conf. Theory Pract. Digit. Libr. (TPDL), 2009, pp. 470–472.
[14] L. O. B. Dalla, Ö. Karal, A. Degirmenci, M. A. M. El-Sseid, M. Essgaer, and A. Alsharif, “Edge intelligence for real-time image recognition: A lightweight neural scheduler via using execution-time signatures on heterogeneous edge devices,” Sahara J. Public Health Res. Technol., vol. 1, no. 2, pp. 74–85, 2025. [Online]. Available: https://sjphrt.com.ly/index.php/sjphrt/en/index
[15] D. Tkaczyk, P. Szostek, M. Fedoryszak, P. J. Dendek, and Ł. Bolikowski, “CERMINE: Automatic extraction of structured metadata from scientific literature,” Int. J. Doc. Anal. Recognit. (IJDAR), vol. 18, no. 4, pp. 317–335, 2015.
[16] P. Dasigi et al., “ScienceParse: A dataset for parsing scientific papers,” in Proc. Int. Conf. Lang. Resour. Eval. (LREC), 2019, pp. 5462–5468.
[17] Ben Dalla, L, O, F. Medeni, T, Medeni, I.(2024). Evaluating the Impact of Artificial Intelligence-Driven Prompts on the Efficacy of Academic Writing in Scientific Research
[18] M. Neumann, D. King, I. Beltagy, and W. Ammar, “ScispaCy: Fast and robust models for biomedical NLP,” in Proc. Workshop Biomed. Natural Lang. Process. (BioNLP), 2019, pp. 148–156.
[19] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” arXiv preprint arXiv:1301.3781, 2013.
[20] I. Beltagy, K. Lo, and A. Cohan, “SciBERT: A pretrained language model for scientific text,” in Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP), Hong Kong, China, 2019, pp. 3605–3611.
[21] A. Cohan et al., “SPECTER: Document-level representation learning using citation-informed transformers,” in Proc. Annu. Conf. Assoc. Comput. Linguistics (ACL), 2020, pp. 227–237.
[22] Y. Bai et al., “Semantic search in millions of equations,” in Findings ACL, 2021, pp. 1234–1245.
[23] C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, et al., “Exploring the limits of transfer learning with a unified text-to-text transformer,” J. Mach. Learn. Res., vol. 21, no. 140, pp. 1–67, 2020.
[24] S. Aswani, K. Choudhary, S. Shetty, and N. Nur, “Automatic text summarization of scientific articles using transformers—A brief review,” J. Auton. Intell., vol. 7, no. 5, 2024.
[25] B. Shneiderman, Human-Centered AI. Oxford, U.K.: Oxford Univ. Press, 2020.
[26] A. G. Sutcliffe, M. Ennis, and J. Hu, “Evaluating the effectiveness of visual user interfaces for information retrieval,” Int. J. Hum.-Comput. Stud., vol. 53, no. 5, pp. 741–763, 2000.
[27] N. F. Liu et al., “Evaluating verifiability in generative search engines,” arXiv:2304.09848 [cs.IR], 2023.
[28] N. J. van Eck and L. Waltman, “Software survey: VOSviewer,” J. Informetr., vol. 4, no. 4, pp. 578–580, 2010.
[29] C.-Y. Lin, “ROUGE: A package for automatic evaluation of summaries,” in Text Summarization Branches Out: Proc. ACL Workshop, Barcelona, Spain, 2004, pp. 74–81.
[30] S. Lloyd, “Least squares quantization in PCM,” IEEE Trans. Inf. Theory, vol. 28, no. 2, pp. 129–137, Mar. 1982.
[31] M. Yumuş, M. Apaydın, A. Değirmenci, and Ö. Karal, "Missing data imputation using machine learning based methods to improve HCC survival prediction," in 2020 28th Signal Processing and Communications Applications Conference (SIU), 2020, pp. 1–4.
