Automatic synthesis of econometric empirical research results using large language model: A case study of digitalization-greening relationships

IF 13.3 1区管理学 Q1 BUSINESS

Technological Forecasting and Social Change Pub Date : 2025-10-11 DOI:10.1016/j.techfore.2025.124370

Zitong Guo , Guangfei Yang , Wenjun Wu

{"title":"Automatic synthesis of econometric empirical research results using large language model: A case study of digitalization-greening relationships","authors":"Zitong Guo , Guangfei Yang , Wenjun Wu","doi":"10.1016/j.techfore.2025.124370","DOIUrl":null,"url":null,"abstract":"<div><div>Econometrics is widely used in economics and social sciences research, generating abundant research results. While meta-analysis, systematic literature review (SLR) and bibliometrics are widely used in hotspot identification and knowledge synthesizing, deeper knowledge extraction, integration and utilization, a broader range of topics, a higher degree of automation and labor demands are expected. To maximize the utility of empirical findings and meet the above expectations, a Large Language Model (LLM)-assisted protocol is proposed in this paper. This protocol utilizes LLM to screen literature records, discriminate econometric empirical studies, and extract structured information from abstracts. Neo4j is used for storage, visualization, and subsequent utilization and mining of the extracted structured information. An empirical case of relationships between digitalization and greening is used to validate the feasibility of the protocol. The findings indicate the protocol accomplishes the verification of the mediating paths in existing research, the exploration of potential mediating paths, and the identification of collider factors, which offer valuable insights for future empirical studies related to digitalization-greening relationships. Future research directions of LLM-driven econometric modeling and knowledge hypernetworks construction via SLR methodologies are finally proposed based on this protocol.</div></div>","PeriodicalId":48454,"journal":{"name":"Technological Forecasting and Social Change","volume":"222 ","pages":"Article 124370"},"PeriodicalIF":13.3000,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Technological Forecasting and Social Change","FirstCategoryId":"91","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0040162525004019","RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BUSINESS","Score":null,"Total":0}

引用次数: 0

Abstract

Econometrics is widely used in economics and social sciences research, generating abundant research results. While meta-analysis, systematic literature review (SLR) and bibliometrics are widely used in hotspot identification and knowledge synthesizing, deeper knowledge extraction, integration and utilization, a broader range of topics, a higher degree of automation and labor demands are expected. To maximize the utility of empirical findings and meet the above expectations, a Large Language Model (LLM)-assisted protocol is proposed in this paper. This protocol utilizes LLM to screen literature records, discriminate econometric empirical studies, and extract structured information from abstracts. Neo4j is used for storage, visualization, and subsequent utilization and mining of the extracted structured information. An empirical case of relationships between digitalization and greening is used to validate the feasibility of the protocol. The findings indicate the protocol accomplishes the verification of the mediating paths in existing research, the exploration of potential mediating paths, and the identification of collider factors, which offer valuable insights for future empirical studies related to digitalization-greening relationships. Future research directions of LLM-driven econometric modeling and knowledge hypernetworks construction via SLR methodologies are finally proposed based on this protocol.

查看原文本刊更多论文

基于大语言模型的计量经济学实证研究结果自动综合：数字化与绿化关系的案例研究

计量经济学广泛应用于经济社会科学研究，产生了丰富的研究成果。而元分析、系统文献综述（SLR）和文献计量学在热点识别和知识综合方面的应用越来越广泛，知识的提取、整合和利用越来越深入，主题范围越来越广，自动化程度越来越高，对劳动力的需求也越来越大。为了最大限度地利用实证结果并满足上述期望，本文提出了一种大型语言模型（Large Language Model， LLM）辅助协议。该协议利用LLM筛选文献记录，区分计量经济学实证研究，并从摘要中提取结构化信息。Neo4j用于存储、可视化以及随后对提取的结构化信息的利用和挖掘。数字化与绿化关系的实证案例验证了协议的可行性。研究结果表明，该协议完成了现有研究中中介路径的验证、潜在中介路径的探索和碰撞因子的识别，为未来数字化与绿化关系的实证研究提供了有价值的见解。最后提出了基于该协议的法学硕士驱动计量经济建模和基于SLR方法构建知识超网络的未来研究方向。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Technological Forecasting and Social Change Multiple-

CiteScore

21.30

自引率

10.80%

发文量

813

期刊介绍： Technological Forecasting and Social Change is a prominent platform for individuals engaged in the methodology and application of technological forecasting and future studies as planning tools, exploring the interconnectedness of social, environmental, and technological factors. In addition to serving as a key forum for these discussions, we offer numerous benefits for authors, including complimentary PDFs, a generous copyright policy, exclusive discounts on Elsevier publications, and more.