Abstract:

Analyzing the causes of criminal psychology is crucial for assessing criminal risks and develop psychological correction plans. Traditional models have limitations in comprehending criminal psychology texts， revealing correlations between prompt vectors and downstream tasks， and identifying the importance of key terms dynamically. Therefore， a CP-BERT （Criminal Psychology-Bidirectional Encoder Representations from Transformers）-based attribution classification model for criminal psychology was proposed， enabling four-class classification of psychological causes of crime. First， an 8.03-million-character criminal psychology corpus was constructed for domain-adaptive pre-training， and semantic modeling capability of the model was enhanced. Second， a hybrid prompt learning method was employed to divide prompt templates into prefix and suffix segments： highly relevant prior information was injected into the prefix segment during the initialization phase， while random initialization was performed on the suffix segment by using normal distribution to supplement information uncovered by the prefix segment， and optimal proportions were determined experimentally. Third， an improved TF-Chi （Term Frequency-Chi-Square） association probability feature method was proposed， in which numerical features were mapped to information relevance probability values dynamically， and feature fusion was achieved by constructing a weight matrix. Finally， an annotated dataset consisting of 3 484 personal and criminal histories was constructed for model training and evaluation. Experimental results demonstrate that this model has an accuracy of 91.25% and an F1 score of 91.56%， significantly outperforming multiple baseline models such as ChatGLM and DeepSeek in all metrics， verifying its effectiveness in criminal psychological attribution tasks.

Key words: criminal psychology, domain-adaptive pre-training, prompt learning, feature fusion, deep learning

摘要：

分析犯罪心理的成因对评估犯罪风险及制定心理矫治方案至关重要。传统模型在理解犯罪心理文本、揭示提示向量与下游任务的关联性，以及动态识别特征词重要性等方面仍存在局限。为此，提出一种基于CP-BERT（Criminal Psychology-Bidirectional Encoder Representations from Transformers）的犯罪心理归因分类模型，以实现对犯罪心理成因的四分类。首先，构建803万字符的犯罪心理语料库，进行领域自适应预训练，增强模型的语义建模能力。其次，设计混合提示（Hybrid Prompt）学习方法，将提示模板划分为前缀与后缀两部分：前缀在初始化阶段注入与归因任务高度相关的先验信息，后缀则采用正态分布随机初始化，用于补充前缀未覆盖的信息，并通过实验确定最优比例。再次，提出改进的TF-Chi（Term Frequency-Chi-Square）关联概率特征方法，将数值特征动态映射为信息关联性概率值，并通过构建权重矩阵实现特征融合。最后，构建一个包含3 484条成长史和犯罪史的标注样本数据集进行模型训练与评估。实验结果表明，该模型的准确率和F1值分别达到91.25%与91.56%，在所有指标上均显著优于ChatGLM、DeepSeek等基线模型，验证了它在犯罪心理归因任务中的有效性。

关键词: 犯罪心理, 领域自适应预训练, 提示学习, 特征融合, 深度学习