生成式人工智能主题演化与学科交叉研究  

Topic Evolution and Interdisciplinary of Generative Artifi cial Intelligence

作　　者：邓胜利[1] 向荣荣 Deng Shengli;Xiang Rongrong(School of Information Management,Wuhan University,Wuhan 430072,China)

机构地区：[1]武汉大学信息管理学院,武汉430072

出　　处：《文献与数据学报》2025年第1期18-32,共15页Journal of Library and Data

基　　金：国家社会科学基金重大项目“信息资源管理学科研究方法知识库构建及其应用研究”(项目编号:23&ZD229)的研究成果之一。

摘　　要：[目的/意义]生成式人工智能已成为新一轮科技革命和产业变革的重要驱动力量,探讨其主题演化及学科交叉趋势,可为科研工作者和相关产业领域未来发展提供借鉴。[方法/过程]本文基于Web of Science(WoS)核心合集2014—2024年生成式人工智能领域的文献数据,借助统计分析、共现网络分析、BERTopic主题聚类等方法,展开主题演化及学科交叉趋势分析。[结果/讨论]从整体来看,生成式人工智能领域研究规模在2022年后迅速变大,研究主题正在扩散,逐步覆盖几乎所有学科。在主题演化上,技术方法研究始终占据主导地位,Transformer出现后逐渐实现技术突破;ChatGPT迅速成长为热点主题,快速在医学与教育领域实现应用。在学科交叉上,生成式人工智能学科规模越来越大,研究论文呈现多学科融合发展态势;学科交叉网络以计算机科学、电气工程学为核心学科,逐步实现与医学、材料科学、物理学、化学、数学等学科的交叉融合。为实现生成式人工智能技术发展与应用,针对不同学科开展技术方法的原理、适用问题、应用场景研究成为必要。[Purpose/Significance]Generative Artificial Intelligence(GAI)has become an important driving force of the new round of scientific and technological revolution and industrial change,and exploring its theme evolution and discipline cross-fertilization trend provides a reference for the future development of scientific research workers and related industrial fields.[Method/Process]Based on the literature data of Web of Science(WoS)of GAI from 2014-2024,this paper develops the analysis of research theme evolution and discipline cross-integration trend with the help of statistical analysis,co-occurrence network,BERTopic theme clustering and other methods.[Result/Conclusion]Overall,the research scale in the field of GAI is rapidly increasing after 2022,and the research themes are proliferating,gradually covering all kinds of disciplines.Regarding topic evolution,research on technical methods always dominates,and technical breakthroughs are gradually realized after the emergence of Transformer;ChatGPT grows into a hot theme very fast,and rapidly realizes its application in the fields of medicine and education.Regarding interdisciplinarity,the GAI discipline scale is getting bigger and bigger,research papers show a trend of integrated development;the interdisciplinary network takes computer science and electrical engineering as the core disciplines,gradually realizes the crossover fusion with medical science,material science,physics,chemistry,mathematics and other disciplines.To realize the development and application of GAI technology,it has become necessary to research the principles,applicable problems,and application scenarios of technical methods for different disciplines.

关 键 词：生成式人工智能 主题演化 学科交叉 ChatGPT 

分 类 号：G250[文化科学—图书馆学]