Open Access Open Access  Restricted Access Subscription Access

AI-Driven Personal Branding System for Freelancers

Satish Chadokar, Deepika Malviya, Aastha Sonakpuriya, Muskan Sahu, Fiza Khan, Nikita Khakre

Abstract


The sustained growth of platform-based freelancing has produced a digital marketplace characterised by intense competition, where the ability to articulate a coherent professional identity constitutes a decisive advantage. Constructing high-quality bios, gig descriptions, taglines, and content strategies, however, demands expertise that the majority of independent workers—particularly those entering the field—do not yet possess. This paper introduces SheCraft AI, a web-based platform that integrates transformer-based generative language models with a structured input pipeline to automate the production of personalised branding artefacts. The system accepts information about a user's skills, industry niche, and intended audience, and subsequently produces platform-optimised profile content, portfolio narratives, and actionable content strategies. A cryptographic authentication module, an iterative recommendation engine, and a React.js-driven interface complement the generation core. User trials involving 42 freelancers across multiple professional domains confirm significant reductions in content-creation effort alongside measurable improvements in profile completeness and perceived professionalism.


Full Text:

PDF

References


Statista Research Department, "Number of Freelancers in the United States from 2017 to 2028," Statista, 2024. [Online]. Available: https://www.statista.com

A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, "Attention Is All You Need," in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017, pp. 5998–6008.

T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan et al., "Language Models Are Few-Shot Learners," in Advances in Neural Information Processing Systems (NeurIPS), vol. 33, 2020, pp. 1877–1901.

D. Jurafsky and J. H. Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, 3rd ed. Upper Saddle River, NJ: Pearson, 2023.

D. Mehta and K. Rathi, "AI-Driven Content Generator for Professionals: Design, Evaluation, and Human-Likeness Metrics," IEEE Access, vol. 12, pp. 34210–34225, 2024.

P. Aggarwal, V. Murahari, T. Rajpurohit, A. Kalyan, K. Narasimhan, and A. Deshpande, "GEO: Generative Engine Optimisation," in Proc. 30th ACM SIGKDD Conf. Knowledge Discovery and Data Mining (KDD), Barcelona, Spain, 2024, pp. 104–115.

M. Havia, "Generative AI in Content SEO Processes," M.Sc. Thesis, Aalto University School of Business, Espoo, Finland, 2024.

V. C. C. Putri, "AI-Driven Personal Branding for Female Entrepreneurs: Bias Mitigation, Tone Adaptation, and Cultural Sensitivity," MDPI Information, vol. 16, no. 3, pp. 112–129, 2025.

A. Kumar and P. Jain, "Smart Portfolio Generator Using Machine Learning: Template Selection and Automated Project Highlight Extraction," Journal of Computer Applications in Technology (Springer), vol. 71, no. 2, pp. 198–214, 2025.

D. Grewal, A. Roggeveen, T. Hariharan, and A. Bhagat, "How Generative AI Is Shaping the Future of Marketing: Applications, Ethics, and Engagement," Journal of the Academy of Marketing Science, vol. 52, no. 4, pp. 901–922, 2024.

S. Ghosh, "Machine-Generated Product Advertisements: Benchmarking Large Language Models Against Human Copywriters on Creativity and Conversion Metrics," arXiv preprint arXiv:2403.07152, 2024.


Refbacks

  • There are currently no refbacks.