SMARTFEED: A LOW-CODE TOOL FOR AUTOMATED CONTENT GENERATION ON LINKEDIN USING ARTIFICIAL INTELLIGENCE
DOI:
https://doi.org/10.56238/arev7n10-094Keywords:
Artificial Intelligence, Content Automation, LinkedIn, Low Code, PLNAbstract
This article presents the development of the smartFEED system, a web application built with low-code tools to automate strategic content creation on LinkedIn, especially aimed at micro and small businesses (SMBs) and content creators. The goal is to democratize access to high-quality digital communication, promoting greater efficiency, visibility, and professional authority. The article outlines the main requirements and functionalities of the system, designed to meet different user profiles with varying needs for digital positioning. The data modeling adopts relational structures and use-case-oriented flows, covering operations such as registration, topic input, tone selection, and automatic generation of text, hashtags, and visual scripts. Technologies such as FlutterFlow, Figma, and the OpenAI GPT API were integrated to ensure stability, customization, and accessibility. Content generation is based on artificial intelligence and structured into reusable blocks, allowing users to maintain a consistent presence on the platform without needing advanced technical knowledge. Digitizing the content creation process reduces errors, standardizes communication, and speeds up strategic personal marketing decisions. The system also promotes user autonomy and contributes to digital inclusion in a professional context. As a future improvement, integration with engagement metric systems and other social networks is planned. The article highlights the strategic role of technology in building digital reputation and strengthening professional presence in algorithm-driven environments.
Downloads
References
ALALWAN, A. A. et al. Social media in marketing: a review and analysis of the existing literature. Telematics and Informatics, v. 34, n. 7, p. 1177–1190, 2017.
BROWN, T. B. et al. Language models are few-shot learners. In: ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS, 33., 2020. Anais [...]. [S.l.]: Curran Associates, 2020.
CULLUM, B. Low-code platforms: democratizing app development and bridging the digital divide. London: TechPolicy Press, 2022.
DAVENPORT, T. H.; BECK, J. C. The attention economy: understanding the new currency of business. Boston: Harvard Business Press, 2001.
FLORIDI, L.; CHIRIATTI, M. GPT-3: its nature, scope, limits, and consequences. Minds and Machines, v. 30, n. 4, p. 681–694, 2020.
GARTNER. Forecasts worldwide low-code development technologies market to grow 23% in 2021. 2021. Disponível em: https://www.gartner.com/en/newsroom. Acesso em: 10 jun. 2025.
INTERNATIONAL ORGANIZATION FOR STANDARDIZATION. ISO/IEC/IEEE 29148:2018: systems and software engineering — life cycle processes — requirements engineering. Geneva, 2018.
KOLOVOS, D. S.; ROSE, L. M.; PAIGE, R. F. Low-code engineering for digital transformation: opportunities and challenges. In: INTERNATIONAL CONFERENCE ON MODEL DRIVEN ENGINEERING LANGUAGES AND SYSTEMS (MODELS), 24., 2021, Fukuoka. Anais [...]. Fukuoka: ACM, 2021. p. 1–11.
LINKEDIN BUSINESS. The state of B2B marketing on LinkedIn. LinkedIn Marketing Solutions, 2023. Disponível em: https://business.linkedin.com/. Acesso em: 10 jun. 2025.
LINKEDIN ENGINEERING. How the LinkedIn feed works. LinkedIn Official Blog, 2023. Disponível em: https://engineering.linkedin.com. Acesso em: 10 jun. 2025.
MARRS, A. The science of building a personal brand that gets you hired. Fast Company, 2021. Disponível em: https://www.fastcompany.com. Acesso em: 10 jun. 2025.
NIELSEN, J. Usability engineering. San Francisco: Morgan Kaufmann, 1994.
OPENAI. Introducing GPT-5. 2025. Disponível em: https://openai.com/index/introducing-gpt-5/. Acesso em: 09 ago. 2025.
PARISER, E. The filter bubble: what the internet is hiding from you. New York: Penguin Press, 2011.
RADFORD, A. et al. Language models are unsupervised multitask learners. OpenAI, 2019. Disponível em: https://cdn.openai.com/language_models_are_unsupervised_multitask_learners.pdf.
SARSA, J. et al. Instruction tuning of pretrained language models. arXiv preprint, arXiv:2203.02155, 2022. Disponível em: https://arxiv.org/abs/2203.02155. Acesso em: 10 jun. 2025.
SEBRAE. Empreendedorismo e marketing digital: relatório de comportamento em redes sociais. Brasília: Sebrae Nacional, 2022.
SOMMERVILLE, I. Engenharia de software. 9. ed. São Paulo: Pearson, 2011.
WEIDINGER, J. L. et al. Ethical and social risks of harm from language models. arXiv preprint, arXiv:2112.04359, 2022. Disponível em: https://arxiv.org/abs/2112.04359.
