Identification of Responsibility-Skill Coupling Patterns in Embodied Intelligent Manufacturing Driven by Improved BERTopic and Association Rules
DOI:
https://doi.org/10.4108/eetsis.14410Keywords:
Embodied Intelligence (EI), Smart Manufacturing, Job Advertisement Text Analysis, BERTopic, GSDMM, Association Rule MiningAbstract
INTRODUCTION: Embodied Intelligence (EI) is rapidly penetrating industrial manufacturing, yet the interdisciplinary nature of EI systems makes it challenging for enterprises to precisely identify evolving talent demands.
OBJECTIVES: This study aims to identify responsibility topics and responsibility–skill coupling patterns in embodied intelligent manufacturing, thereby providing a theoretical basis for talent demand analysis.
METHODS: A total of 749 job advertisements were scraped and an improved BERTopic method integrating GSDMM topic similarity with semantic representation was proposed, identifying 14 responsibility topics (10 domain-specific) across four clusters. The Apriori algorithm was then applied to mine association rules between responsibility topics and skill keywords, with thresholds determined by the elbow method.
RESULTS: GSDMM-BERTopic consistently outperformed classic BERTopic and Gibbs-BERTopic, achieving average CV coherence of 0.5477, silhouette score of 0.6737, and outlier ratio of 0.1662. The selected configuration yielded 14 responsibility topics (10 domain-specific) across four clusters. Association rule mining produced 128 filtered rules. Notable topic–skill couplings include 3D Perception Modeling with Detection and Segmentation (lift 9.015), Motion Control with Reinforcement Learning and ROS (lift 2.277), and Frontier Technology Tracking with Ph.D. (lift 2.605). Cross-category analysis reveals Python and PyTorch as the common skill substrate, C++ as critical in hardware-adjacent domains, and the ROS/ROS2 ecosystem as the central middleware.
CONCLUSION: The findings reveal a T-shaped skill profile in embodied intelligent manufacturing and provide practical guidance for enterprises to optimize workforce allocation and talent cultivation strategies.
References
[1] .Zhu, J., S. Huang, P. Wang, et al., A review on large language models for industrial embodied intelligence. Advanced Engineering Informatics, 2026. 73: p. 104602.
[2] Fang, L., J. Shi, L. Wu, et al., Perspectives and Prospects on Embodied Intelligence-Empowered Smart Manufacturing. Journal of Intelligent Manufacturing, 2026: p. 1-20.
[3] Xu, J., Q. Sun, Q.-L. Han, et al., When Embodied AI Meets Industry 5.0: Human-Centered Smart Manufacturing. Ieee-caa Journal of Automatica Sinica, 2025. 12(3): p. 485–501.
[4] Al-Asfour, A. and Y. Zhao, Bridging the skills gap divide in manufacturing: perspectives from industry leaders. Industrial and Commercial Training, 2024. 56(1): p. 78–90.
[5] Menezes, P.C., K.M. Sakiyama, R.M. Marcacini, et al., SKORE: Skill-oriented extraction engine from job advertisements using large language models. MethodsX, 2026. 16: p. 103907.
[6] Gurcan, F., A. Soylu, and A.Q. Khan, Towards a Sustainable Workforce in Big Data Analytics: Skill Requirements Analysis from Online Job Postings Using Neural Topic Modeling. Sustainability, 2025. 17(20).
[7] Kang, P.S., R. Enstroem, B. Bhawna, et al., A text mining study of competencies in modern supply chain management with skillset mapping. Supply Chain Analytics, 2025. 10: p. 100117.
[8] Gavrilescu, M., F. Leon, and A.-A. Minea, Techniques for Transversal Skill Classification and Relevant Keyword Extraction from Job Advertisements. Information, 2025. 16(3): p. 167.
[9] Grootendorst, M., BERTopic: Neural topic modeling with a class-based TF-IDF procedure. CoRR, 2022. abs/2203.05794.
[10] Yin, J. and J. Wang, A Dirichlet Multinomial Mixture Model-based Approach for Short Text Clustering, in Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2014, ACM: New York, NY, USA. p. 233–242.
[11] Xia, D., P. Xu, G. Han, et al., Emerging Perspectives on Embodied Intelligence in Future Smart Manufacturing. Journal of Industrial Information Integration, 2026. 50: p. 101020.
[12] Li, S., C. Liu, J. Zhao, et al., Physics-informed embodied intelligence in the foundation model era: Advancing robot manipulation for smart manufacturing. Advanced Engineering Informatics, 2026. 71: p. 104370.
[13] Ding, K., Q. Mao, Y. Zhang, et al., Review and perspectives on multimodal perception, mutual cognition, and embodied execution for human–robot collaboration in Industry 5.0. Robotics and Computer-Integrated Manufacturing, 2026. 101: p. 103280.
[14] Pejic-Bach, M., T. Bertoncel, M. Meško, et al., Text mining of industry 4.0 job advertisements. International Journal of Information Management, 2020. 50: p. 416-431.
[15] Schedlbauer, J., G. Raptis, and B. Ludwig, Medical informatics labor market analysis using web crawling, web scraping, and text mining. Int J Med Inform, 2021. 150: p. 104453.
[16] Verma, A., K. Lamsal, and P. Verma, An investigation of skill requirements in artificial intelligence and machine learning job advertisements. Industry and Higher Education, 2022. 36(1): p. 63-73.
[17] Wang, R., Q. Chen, Y. Wang, et al., JobViz: Skill-driven visual exploration of job advertisements. Visual Informatics, 2024. 8(3): p. 18-28.
[18] Chaturvedi, S., K. Mahajan, and Z. Siddique, Gendered language in job ads and applicant behavior: Evidence from India. Labour Economics, 2025. 96: p. 102726.
[19] Hu, S., J.A. Al-Ani, K.D. Hughes, et al., Balancing Gender Bias in Job Advertisements with Text-Level Bias Mitigation. FRONTIERS in BIG DATA, 2022. 5.
[20] Zhong, A., R. Qiu, X. Zhang, et al., Characterizing the Job-task-skill Pattern of Job Requirements with Job Advertisement Mining, in Proceedings of the 2023 6th International Conference on Computers in Management and Business. 2023. p. 139-147.
[21] Zhu, Y. and Y. Liu, Gibbs-BERTopic: A Hybrid Approach for Short Text Topic Modeling. IEEE Access, 2025. 13: p. 49162–49173.
[22] Bylina, B. and A. Antończak, Analysis of end-to-end test automation tools based on the examples of Selenium WebDriver and Playwright, in Position Papers of the 19th Conference on Computer Science and Intelligence Systems. 2024. p. 1–8.
[23] QwenTeam. Qwen3.7. 2026; Available from: https://qwen.ai/blog?id=qwen3.7.
[24] DeepSeek-AI. DeepSeek-V3. 2024; Available from: https://api-docs.deepseek.com/news/news1226/.
[25] QwenLM. Qwen3-Embedding. 2025; Available from: https://github.com/QwenLM/Qwen3-Embedding.
[26] Agrawal, R. and R. Srikant. Fast Algorithms for Mining Association Rules in Large Databases. in Proceedings of the 20th International Conference on Very Large Data Bases. 1994. Morgan Kaufmann Publishers Inc.
[27] Satopaa, V., J.R. Albrecht, D.E. Irwin, et al., Finding a "kneedle" in a Haystack: Detecting Knee Points in System Behavior. ICDCS Workshops, 2011: p. 166-171.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Anyuan Zhong
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
