Traits of a Leader: User Influence Level Prediction through Sociolinguistic Modeling

2025-01-05

AI Summary

This paper addresses cross-domain online user influence prediction. We propose a multi-task deep learning framework that jointly incorporates sociolinguistic and personality-based features. Unlike conventional text-only approaches, we formally define influence as a function of community endorsement and, for the first time, integrate demographic attributes (age, gender) and Big Five personality traits as structured non-linguistic features to enhance interpretability and robustness in sociolinguistic modeling. The model jointly optimizes textual embeddings, structured attribute encodings, and RankDCG-based ranking loss, while leveraging domain-adversarial feature alignment to improve cross-domain generalization. Extensive experiments across eight domains—including politics, health, and technology—demonstrate an average 23.6% improvement in RankDCG over strong baselines. Results validate the effectiveness of the “language + personality” paradigm for cross-domain influence modeling, establishing a new direction for explainable and generalizable social influence prediction.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Machine Learning: Learning Preferences or Rankings
• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Application Category

• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Recognition of a user's influence level has attracted much attention as human interactions move online. Influential users have the ability to sway others' opinions to achieve some goals. As a result, predicting users' level of influence can help to understand social networks, forecast trends, prevent misinformation, etc. However, predicting user influence is a challenging problem because the concept of influence is specific to a situation or a domain, and user communications are limited to text. In this work, we define user influence level as a function of community endorsement and develop a model that significantly outperforms the baseline by leveraging demographic and personality data. This approach consistently improves RankDCG scores across eight different domains.

Problem

• Online Influence Prediction
• Leadership Traits Analysis
• Social Context

Innovation

• Speech and Writing Analysis
• Influence Prediction Model
• Improved Accuracy