App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 7

Leveraging LLM-enhanced PageRank with forward-backward recommendation for identifying key class in software systems

Liu Huihui1,2,3
Liu Chenyu1
Wang Zhenzhen1,2
Chen Wenjun1
Qian Yang1
1. School of Software Engineering, Jinling Institute of Technology, Nanjing 211169, China
2. Jiangsu Province Software Testing Engineering Research Center, Jinling Institute of Technology, Nanjing 211169, China
3. State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093, China
DOI: 10.19734/j.issn.1001-3695.2025.11.0479

Abstract

Accurately identifying key classes is an effective strategy to improve the comprehension efficiency for complex software systems. However, existing PageRank-based identification methods suffer from two main limitations: first, conventional dependency models often ignore potential semantic relationships, compromising the accuracy of network construction; second, the voting mechanism lacks backward recommendation, making it difficult to identify key classes that serve control or management functions. To address these issues, this paper introduces PageRank with Forward-Backward Recommendation (shortly named as PageRankFBR) , a novel algorithm enhanced by a Large Language Model (LLM) that integrates both forward and backward recommendations. Our method first employs LLM along with the Software Network Construction and Measurement (SNCM) tool to extract semantic and structural dependencies between classes, thereby constructing a more comprehensive software dependency network. PageRankFBR is then applied to compute importance score for each node (class) . Experimental results on 11 open-source projects demonstrate that: a) PageRankFBR significantly outperforms baseline metrics across the dataset in terms of Precision (improved by 34%–87%) , Recall (7%–19%) , Accuracy (2%–22%) , and F1-Score (7%–43%) in most cases; b) the average ranking of correctly identified key classes is superior to that of baseline metrics, with an improvement of 50%–71%. These results confirm that combining semantic information with forward-backward recommendation mechanism enables more accurate key class identification, thereby providing a more reliable starting point for software comprehension.

Foundation Support

金陵科技学院高层次人才科研启动基金资助项目(jit-b-202007)
金陵科技学院校级教育教学改革课题研究成果(JYJG202506)
国家自然科学基金资助项目(42101476)
江苏省高校自然科学研究重大项目(22KJA520002)
江苏省高等学校基础科学(自然科学)研究项目(25KJD510002)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.11.0479
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 7

Publish History

[2026-03-24] Accepted Paper

Cite This Article

刘辉辉, 刘晨雨, 王蓁蓁, 等. 基于LLM增强的前后向推荐PageRank算法识别软件系统关键类 [J]. 计算机应用研究, 2026, 43 (7). (2026-03-24). https://doi.org/10.19734/j.issn.1001-3695.2025.11.0479. (Liu Huihui, Liu Chenyu, Wang Zhenzhen, et al. Leveraging LLM-enhanced PageRank with forward-backward recommendation for identifying key class in software systems [J]. Application Research of Computers, 2026, 43 (7). (2026-03-24). https://doi.org/10.19734/j.issn.1001-3695.2025.11.0479. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)