基于词嵌入技术的心理学研究:方法及应用

Using word embeddings to investigate human psychology:Methods and applications

词嵌入是自然语言处理的一项基础技术。其核心理念是根据大规模语料中词语和上下文的联系,使用神经网络等机器学习算法自动提取有限维度的语义特征,将每个词表示为一个低维稠密的数值向量(词向量),以用于后续分析。心理学研究中,词向量及其衍生的各种语义联系指标可用于探究人类的语义加工、认知判断、发散思维、社会偏见与刻板印象、社会与文化心理变迁等各类问题。未来,基于词嵌入技术的心理学研究需要区分心理的内隐和外显成分,深化拓展动态词向量和大型预训练语言模型(如GPT、BERT)的应用,并在时间和空间维度建立细粒度词向量数据库,更多开展基于词嵌入的社会变迁和跨文化研究。我们为心理学专门开发的R语言工具包PsychWordVec可以帮助研究者利用词嵌入技术开展心理学研究。

As a fundamental technique in natural language processing(NLP),word embedding quantifies a word as a low-dimensional,dense,and continuous numeric vector(i.e.,word vector).Word embeddings can be obtained by using machine learning algorithms such as neural networks to predict the surrounding words given a word or vice versa(Word2Vec and FastText)or by predicting the probability of co-occurrence of multiple words(GloVe)in large-scale text corpora.Theoretically,the dimensions of a word vector reflect the pattern of how the word can be predicted in contexts;however,they also connote substantial semantic information of the word.Therefore,word embeddings can be used to analyze semantic meanings of text.In recent years,word embeddings have been increasingly applied to study human psychology,including human semantic processing,cognitive judgment,divergent thinking,social biases and stereotypes,and sociocultural changes at the societal or population level.Future research using word embeddings should(1)distinguish between implicit and explicit components of social cognition,(2)train fine-grained word vectors in terms of time and region to facilitate cross-temporal and cross-cultural research,and(3)apply contextualized word embeddings and large pre-trained language models such as GPT and BERT.To enhance the application of word embeddings in psychology,we have developed the R package“PsychWordVec”,an integrated word embedding toolkit for researchers to study human psychology in natural language.