Forecasting the Buzz: Enriching Hashtag Popularity Prediction with LLM Reasoning

2025-10-09

AI Summary

Predicting hashtag popularity is critical for舆情 analysis and targeted advertising, yet existing approaches face key limitations: traditional regression models neglect semantic context, while large language models (LLMs) lack precision in numerical forecasting. This paper proposes an interpretable hybrid framework: an instruction-tuned LLM serves as a contextual reasoner, generating human-readable rationales regarding topic relevance, audience reach, and temporal salience—these are then structured into enhanced features for a classical regression model to perform final popularity prediction. We introduce and publicly release HashView, the first large-scale benchmark dataset for hashtag popularity prediction, comprising 7,532 hashtags. Experiments demonstrate that our method achieves up to a 2.8% reduction in RMSE and a 30% improvement in Pearson correlation coefficient over state-of-the-art baselines, effectively balancing predictive accuracy with human-interpretable decision rationale.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Common-Sense Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Hashtag trends ignite campaigns, shift public opinion, and steer millions of dollars in advertising spend, yet forecasting which tag goes viral is elusive. Classical regressors digest surface features but ignore context, while large language models (LLMs) excel at contextual reasoning but misestimate numbers. We present BuzzProphet, a reasoning-augmented hashtag popularity prediction framework that (1) instructs an LLM to articulate a hashtag's topical virality, audience reach, and timing advantage; (2) utilizes these popularity-oriented rationales to enrich the input features; and (3) regresses on these inputs. To facilitate evaluation, we release HashView, a 7,532-hashtag benchmark curated from social media. Across diverse regressor-LLM combinations, BuzzProphet reduces RMSE by up to 2.8% and boosts correlation by 30% over baselines, while producing human-readable rationales. Results demonstrate that using LLMs as context reasoners rather than numeric predictors injects domain insight into tabular models, yielding an interpretable and deployable solution for social media trend forecasting.

Problem

• Predicting hashtag popularity using contextual reasoning
• Combining LLM insights with classical regression models
• Improving forecast accuracy for social media trends

Innovation

• LLM generates popularity rationales for hashtags
• Rationales enrich input features for regressors
• Combines LLM reasoning with numerical regression