# From Millions of Tweets to Actionable Insights: Leveraging LLMs for User Profiling

arXiv: https://arxiv.org/abs/2505.06184 · HTML: https://mlsanity.com/paper/2505.06184/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 62 references that are in the map.
- First posted on arXiv 9 May 2025.

## Builds on (most cited first, 11 of 11)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Empowering News Recommendation with Pre-trained Language Models](https://mlsanity.com/paper/2104.07413/) (2021)
- [User Modeling and User Profiling: A Comprehensive Survey](https://mlsanity.com/paper/2402.09660/) (2024)
- [Unsupervised Extractive Opinion Summarization Using Sparse Coding](https://mlsanity.com/paper/2203.07921/) (2022)
- [Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study](https://mlsanity.com/paper/2404.07060/) (2024)
- [TookaBERT: A Step Forward for Persian NLU](https://mlsanity.com/paper/2407.16382/) (2024)
- [User Profiling Trends, Techniques and Applications](https://mlsanity.com/paper/1503.07474/) (2015)
- [TSSuBERT: Tweet Stream Summarization Using BERT](https://mlsanity.com/paper/2106.08770/) (2021)

## Built on by (most cited first, 3 of 3)

- [Exploiting contextual information to improve stance detection in informal political discourse with LLMs](https://mlsanity.com/paper/2602.04750/) (2026)
- [Synthia: Scalable Grounded Persona Generation from Social Media Data](https://mlsanity.com/paper/2507.14922/) (2025)
- [Bridging Textual Profiles and Latent User Embeddings for Personalization](https://mlsanity.com/paper/2605.06981/) (2026)

## Abstract (arXiv)

Social media user profiling through content analysis is crucial for tasks like misinformation detection, engagement prediction, hate speech monitoring, and user behavior modeling. However, existing profiling techniques, including tweet summarization, attribute-based profiling, and latent representation learning, face significant limitations: they often lack transferability, produce non-interpretable features, require large labeled datasets, or rely on rigid predefined categories that limit adaptability. We introduce a novel large language model (LLM)-based approach that leverages domain-defining statements, which serve as key characteristics outlining the important pillars of a domain as foundations for profiling. Our two-stage method first employs semi-supervised filtering with a domain-specific knowledge base, then generates both abstractive (synthesized descriptions) and extractive (representative tweet selections) user profiles. By harnessing LLMs' inherent knowledge with minimal human validation, our approach is adaptable across domains while reducing the need for large labeled datasets. Our method generates interpretable natural language user profiles, condensing extensive user data into a scale that unlocks LLMs' reasoning and knowledge capabilities for downstream social network tasks. We contribute a Persian political Twitter (X) dataset and an LLM-based evaluation framework with human validation. Experimental results show our method significantly outperforms state-of-the-art LLM-based and traditional methods by 9.8%, demonstrating its effectiveness in creating flexible, adaptable, and interpretable user profiles.