The field of natural language processing is rapidly advancing, with a growing focus on leveraging large language models (LLMs) to analyze social and political data. Recent research has highlighted the potential of LLMs to improve user profiling, financial sentiment analysis, and political rhetoric analysis. One of the key trends in this area is the development of novel LLM-based approaches that can adapt to different domains and tasks, reducing the need for large labeled datasets and improving the interpretability of results. Another notable direction is the application of LLMs to real-world problems, such as scaling parliamentary representatives' political issue stances and enhancing voting advice applications. These innovations have the potential to significantly impact various fields, from social media monitoring to political science. Noteworthy papers in this area include: KOKKAI DOC, which introduces an LLM-driven framework for scaling parliamentary representatives' political issue stances. The paper on Evaluating Financial Sentiment Analysis with Annotators Instruction Assisted Prompting, which presents a novel evaluation prompt designed to standardize the understanding of sentiment across both human and machine interpretations.