A methodology for analyzing financial needs hierarchy from social discussions using LLM

A team of researchers published a pioneering study on the arXiv preprint server in early February 2025 detailing a new methodology for mapping the hierarchy of financial needs using Large Language Models (LLMs) to analyze social media discourse. Developed to better understand how individuals prioritize economic goals, the study leverages generative AI to sift through massive datasets of public conversations, identifying patterns that range from basic financial survival to complex psychological fulfillment. The project was initiated to bridge the gap between theoretical economic models and the real-world financial anxieties expressed by the public in digital spaces. By applying advanced natural language processing techniques, the researchers were able to categorize financial needs into a structured hierarchy, similar to Maslow's hierarchy of needs but specifically tailored to monetary behavior. This approach allows for a more nuanced look at how people balance immediate necessities, such as paying for housing and food, against long-term aspirations like investment and wealth accumulation. The use of LLMs provided the scale and speed necessary to process diverse social media interactions, which traditional survey-based methods often struggle to capture accurately. The findings of this research have significant implications for both financial institutions and policymakers. By understanding the specific triggers and progressions of financial needs within the general population, organizations can develop more targeted educational resources and financial products. Additionally, the study highlights how psychological well-being is intrinsically linked to one's position within this financial hierarchy, suggesting that economic stress at the foundational level can severely hinder personal development and broader societal stability.