Interpretable Random Forest Modeling of Fan-Circle Involvement and Online Collective Behavior Intention: A Survey-Based Machine Learning Study
Open Access
- 6 February 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 921-925
Abstract
Fan-circle involvement is increasingly associated with organized online collective actions, yet individual-level prediction and interpretable screening remain underdeveloped. Based on a national survey of Chinese fans (N = 435), we reformulate online collective behavior intention into an ordinal three-class classification task (Low/Mid/High) derived from training-set tertiles and propose a band-aware accuracy criterion for tier assignment. A Random Forest (RF) classifier is selected as the primary model and tuned with 5-fold cross-validation. Under the proposed evaluation, RF achieves Accuracy = 0.9318 on a held-out 10% test split, outperforming XGBoost and LightGBM baselines (Accuracy = 0.9091) and an MLP baseline (Accuracy = 0.8636). SHAP explanations identify a compact set of Top-10 item-level predictors for the High class, enabling interpretable identification of modifiable levers. The results complement a theory-driven serial mediation account (fan-circle involvement -> information narrowing -> emotional susceptibility -> collective intention) and provide a deployable, explainable pipeline for research and practice.Keywords
This publication has 10 references indexed in Scilit:
- An Exploratory Study on Information Cocoon in Recommender SystemsData Science and Engineering, 2025
- Observations of Chinese fandom: organizational characteristics and the relationships inside and outside the “Fan circle”The Journal of Chinese Sociology, 2023
- Emotional Contagion Ability Scale: Compilation and empirical validity for Chinese college studentsSocial Behavior and Personality: an international journal, 2023
- Civic Engagement Intention and the Data-Driven Fan Community: Investigating the Motivation Behind Chinese Fans’ Online Data-Making Behavior From a Collective Action PerspectiveSocial Media + Society, 2023
- Deep Neural Networks and Tabular Data: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2022
- From local explanations to global understanding with explainable AI for treesNature Machine Intelligence, 2020
- XGBoost2016
- Detecting and Deterring Insufficient Effort Responding to SurveysJournal of Business and Psychology, 2011
- Common method biases in behavioral research: A critical review of the literature and recommended remedies.Journal of Applied Psychology, 2003
- Random ForestsMachine Learning, 2001