An AI-based Personalised Job Recommendation and Application Assistant Agent for Enhanced Employment Matching: A Scrapus Use Case

Abstract

The complexity and inefficiencies inherent in job search processes significantly impact both job seekers and employers. This study introduces a sophisticated artificial intelligence (AI) agent designed to deliver personalised job recommendations tailored to individual career profiles, experiences, and preferences. The proposed AI agent automates and customises job searches using natural language processing (NLP) techniques and personalised keyword analysis. Additionally, it autonomously generates individualised cover letters and application emails, streamlining repetitive tasks. Our experiments demonstrate that this agent significantly improves the job-matching accuracy, reduces the time-to-employment, and enhances the overall hiring experience for both candidates and employers.

Keywords

• Artificial Intelligence
• Job Matching
• Natural Language Processing
• Multi-Agent Systems
• Employment Automation
• Personalised Recommendation

References

1. Aggarwal, C. C. 2016. Recommender Systems: The Textbook. Springer International Publishing. https://doi.org/10.1007/978-3-319-29659-3 google scholar
2. Al-Otaibi, S. T. and Ykhlef, M. 2012. A survey of job recommender systems. International Journal of Physical Sciences, 7, 29, 5127– 5142. https://doi.org/10.5897/IJPS12.482 google scholar
3. Amazon Reviews. 2024. Amazon Reviews for Sentiment Analysis. Kaggle. Retrieved from https://www.kaggle.com/datasets/ bittlingmayer/amazon-reviews (Erişim tarihi: 9 Temmuz 2025). google scholar
4. Brown, T. B., Mann, B., Ryder, N., et al. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 1877–1901. https://doi.org/10.48550/arXiv.2005.14165 google scholar
5. Bubeck, S., Chandrasekaran, V., Eldan, R., et al. 2023. Sparks of artificial general intelligence: Early experiments with GPT-4. arXiv preprint arXiv:2303.12712. https://doi.org/10.48550/arXiv.2303.12712 google scholar
6. Burke, R. 2002. Hybrid recommender systems: Survey and experiments. User Modeling and User-Adapted Interaction, 12, 4, 331– 370. https://doi.org/10.1023/A:1021240730564 google scholar
7. Chala, S. A. and Ansari, F. 2022. Semantic matching of job seeker to vacancy: A digital twin-based approach. IEEE Transactions on Engineering Management, 70, 3, 781–793. https://doi.org/10.1109/TEM.2022.3208294 google scholar
8. DBpedia. 2024. DBpedia Knowledge Base. Retrieved from https://dbpedia.org/ (Erişim tarihi: 9 Temmuz 2025). google scholar

9. DeepSeek AI. 2023. DeepSeek: Advanced contextual understanding in AI language models. Retrieved from https://deepseek.com/ (Erişim tarihi: 9 Temmuz 2025). google scholar
10. Dettmers, T., Pagnoni, A., Holtzman, A., and Zettlemoyer, L. 2023. QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314. https://www.google.com/search?q=https://doi.org/10.48550/arXiv.2305.14314 google scholar
11. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 4171-4186. https://doi.org/10.18653/v1/N19-1423 google scholar
12. El Naqa, I. and Murphy, M. J. 2022. GPT-3 and the future of natural language processing. In Artificial Intelligence in Radiation Oncology. Springer, Cham, 325–335. https://doi.org/10.1007/978-3-030-94206-8_19 google scholar
13. EMSI. 2021. EMSI Job Posting Dataset. Retrieved from https://www.economicmodeling.com/ (Erişim tarihi: 9 Temmuz 2025). google scholar
14. Floridi, L. and Chiriatti, M. 2020. GPT-3: Its nature, scope, limits, and consequences. Minds and Machines, 30, 4, 681–694. https:// doi.org/10.1007/s11023-020-09548-1 google scholar
15. Google DeepMind. 2023. Gemini: Multimodal AI models for next-generation applications. Retrieved from https://deepmind. google.com/ (Erişim tarihi: 9 Temmuz 2025). google scholar
16. Gulli, A. and Signorini, A. 2005. The indexable web is more than 11.5 billion pages. In Proceedings of the 14th International Conference on World Wide Web (WWW ’05). ACM, New York, 902–903. https://doi.org/10.1145/1062745.1062789 google scholar
17. Hu, E. J., Shen, Y., Wallis, P., et al. 2021. LoRA: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685. https://www.google.com/search?q=https://doi.org/10.48550/arXiv.2106.09685 google scholar
18. Indeed Dataset. 2024. Real or Fake Job Posting Dataset. Kaggle. Retrieved from https://www.kaggle.com/datasets/shivamb/real-or-fake-fake-jobposting (Erişim tarihi: 9 Temmuz 2025). google scholar
19. Jannach, D., Zanker, M., Ge, M., and Gröning, M. 2013. Recommender systems in computer science and information systems – A landscape of research. In Proceedings of the 15th International Conference on Enterprise Information Systems, Vol. 3, 5–14. https://www.google.com/search?q=https://doi.org/10.5220/0004439100050014 google scholar
20. Javed, H., Awan, M., and Maqbool, B. 2022. Artificial intelligence and recruitment processes: A comprehensive review. IEEE Access, 10, 12432–12451. https://doi.org/10.1109/ACCESS.2022.3146350 google scholar
21. Javed, H., Liu, H., and Tang, H. 2022. Enhancing job recommendation systems using artificial intelligence: A systematic review. IEEE Access, 10, 10423–10437. https://doi.org/10.1109/ACCESS.2022.3141216 google scholar
22. Kaggle. 2024. Glassdoor Reviews and Ratings. Retrieved from https://www.kaggle.com/datasets/andradaolteanu/glassdoor-review (Erişim tarihi: 9 Temmuz 2025). google scholar
23. Kenthapadi, K., Le, B., and Venkataraman, G. 2017. Personalized job recommendation system at LinkedIn: Practical challenges and lessons learned. In Proceedings of the 11th ACM Conference on Recommender Systems (RecSys ’17), 346–347. https://doi.org/ 10.1145/3109859.3109910 google scholar
24. Lewis, P., Perez, E., Piktus, A., et al. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 9459–9474. https://doi.org/10.48550/arXiv.2005.11401 google scholar
25. Liu, H., Xu, Y., and Tang, H. 2022. Adapter-tuning for efficient and effective transformer fine-tuning. arXiv preprint arXiv:2203.06878. https://www.google.com/search?q=https://doi.org/10.48550/arXiv.2203.06878 google scholar
26. Malinowski, J., Keim, T., and Weitzel, T. 2006. Analyzing the impact of IS support on recruitment processes: An e-recruitment phase model. Journal of Decision Systems, 15, 4, 381–402. https://doi.org/10.3166/jds.15.381-402 google scholar
27. Monster Job Listings Dataset. 2024. Job Listings Dataset. Data.world. Retrieved from https://data.world/keshav/monster-job-portal-dataset (Erişim tarihi: 9 Temmuz 2025). google scholar
28. Olston, C. and Najork, M. 2010. Web crawling. Foundations and Trends in Information Retrieval, 4, 3, 175–246. https://doi.org/10. 1561/1500000017 google scholar
29. ONET. 2024. ONET Online Occupational Database. Retrieved from https://www.onetonline.org/ (Erişim tarihi: 9 Temmuz 2025). google scholar
30. OpenAI. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774. https://doi.org/10.48550/arXiv.2303.08774 google scholar
31. Rácz, G., Sali, G., and Scheidl, S. 2023. Semantic matching strategies for job recruitment: A comparison of new and known approaches. Computers in Industry, 147, Article 103883. https://doi.org/10.1016/j.compind.2023.103883 google scholar
32. Shaikym, A., Zhalgassova, Z., and Sadyk, U. 2023. Design and evaluation of a personalized job recommendation system for computer science students using hybrid approach. In Proceedings of the 17th International Conference on Electronics Computer and Computation (ICECCO), 1–6. https://www.google.com/search?q=https://doi.org/10.1109/ICECCO59515.2023.10289452 google scholar
33. Wei, J., Bosma, M., Zhao, V., et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903. https://doi.org/10.48550/arXiv.2201.11903 google scholar
34. xAI. 2023. Grok: Real-time knowledge and dynamic internet content integration. Retrieved from https://x.ai/ (Erişim tarihi: 9 Temmuz 2025). google scholar
35. Yao, S.-Y., Yang, Y., Zhang, J., et al. 2023. Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601. https://doi.org/10.48550/arXiv.2305.10601 google scholar
36. Ni, J., Li, J., and McAuley, J. 2019. Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, 188–197. https://doi.org/10.18653/v1/D19-1018 google scholar