A Study of Internet Users’ Heterogeneity Based on Large Language Models

The emergence of big events is frequently followed by the existence of online public opinion, and netizens’ emotional comments heighten the hazards associated with the process of online public opinion transmission, resulting in social instability. Netizens’ emotionality is inextricably linked to their personality traits, and it is necessary to analyze their personalities in order to determine the corresponding public opinion countermeasures of government departments; thus, this paper conducts a study on netizen heterogeneity. A Graph Neural Network (GNN) personality prediction model is built on the Big Five personality model and the BERT model. The BERT model encodes the comment data and converts it into a graph neural network model; the dual attention mechanism extracts the relationship between the user and his/her diction, diction, and psychological keywords; the graph convolutional neural network extracts the features; and finally, the personality scores of the five dimensions of the Big Five personality model of Internet users are calculated. The study demonstrates that the graph neural network Internet user personality prediction model based on the BERT model has some advantages in the personality prediction task and can give data support for future Internet public opinion analysis.

I. INTRODUCTORY

With the rapid development of the Internet and the widespread use of social media, particularly the popularization of self-media, cyberspace has gradually evolved into an important place for citizens to participate in social life, express their political views, and interact emotionally with one another. Whenever a major event occurs, it inevitably generates online public opinion, which affects the public’s perception and judgment of the event, as well as the government’s behavior and attitude, so online public opinion has emerged as an important factor influencing social stability [1]. As a result, Internet public opinion has emerged as a significant role in determining social stability. Netizens’ speech and communication have strong emotional features, and their emotionalization will make it more difficult to analyze and judge the trend of online public opinion, as well as control the follow-up, resulting in societal instability. Because Internet users’ emotionality is inextricably linked to their personality traits, it is critical to accurately analyze their personality traits, i.e., the study of Internet user heterogeneity, in order to understand their psychological state and then analyze and predict their online behaviors and performances, which is critical for analyzing Internet public opinion.