Jiexun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiexun Li has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Jiyao Chen
Oregon State University
2 shared publications - Bin Su
Energy Studies Institute, National University of Singapore, Singapore, Singapore
1 shared publication - Dong Wang
College of Computer Science and Technology, Ocean University of China, Qingdao, China
1 shared publication - Guoxing Zhang
School of Management, Lanzhou University, Lanzhou, 730000, China
1 shared publication - Jin Xu
School of Economics and Management, Southwest Jiaotong University, Chengdu, China
1 shared publication - Jinfeng Bu
School of Economics and Management, Southwest Jiaotong University, Chengdu, China
1 shared publication
Latest Publications
- 10 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 71 (00189391) , 11361-11374
A Knowledge Transfer Framework Based on Deep-Reinforcement Learning for Multistage Construction Projects
Construction projects can produce excessive construction data using intelligent equipment. Deep learning algorithms can harness these data, discovering knowledge that can effectively enhance project execution and performance. However, these algorithms' efficacy hinges on the availability of data, often presenting a challenge at project initiation when data are scarce or absent. Although this issue can be alleviated through knowledge transfer algorithms, there is still a lack of a method for selecting knowledge source domains that can adapt to data distributions. Further, the long durations and dynamic environments of construction projects require timely updates to a project's knowledge base, which is often ignored by current knowledge-management practices. This study introduces a multi-stage, online knowledge transfer framework tailored to three distinct stages of construction projects: the initiation, data-emergence, and data-rich stages. Firstly, the framework transforms sourcQe-project data into target-project data, alleviating the initial data deficit. Subsequently, it utilizes a combination of multiple similarity metrics and a deep-reinforcement learning model to adaptively select source domains with minimal distribution disparities, improving the effect of knowledge transfer. Finally, it integrates concept-drift algorithms and constructs knowledge-source discrimination rule to automate the selection of knowledge sources and schedule updates, enabling dynamic knowledge transfer in construction projects.
- 10 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 71 (00189391) , 11361-11374
A Knowledge Transfer Framework Based on Deep-Reinforcement Learning for Multistage Construction Projects
Construction projects can produce excessive construction data using intelligent equipment. Deep learning algorithms can harness these data, discovering knowledge that can effectively enhance project execution and performance. However, these algorithms' efficacy hinges on the availability of data, often presenting a challenge at project initiation when data are scarce or absent. Although this issue can be alleviated through knowledge transfer algorithms, there is still a lack of a method for selecting knowledge source domains that can adapt to data distributions. Further, the long durations and dynamic environments of construction projects require timely updates to a project's knowledge base, which is often ignored by current knowledge-management practices. This study introduces a multi-stage, online knowledge transfer framework tailored to three distinct stages of construction projects: the initiation, data-emergence, and data-rich stages. Firstly, the framework transforms sourcQe-project data into target-project data, alleviating the initial data deficit. Subsequently, it utilizes a combination of multiple similarity metrics and a deep-reinforcement learning model to adaptively select source domains with minimal distribution disparities, improving the effect of knowledge transfer. Finally, it integrates concept-drift algorithms and constructs knowledge-source discrimination rule to automate the selection of knowledge sources and schedule updates, enabling dynamic knowledge transfer in construction projects.
- Open Access
- 30 April 2024
- Published by Oxford University Press (OUP) in PNAS Nexus
- Vol. 3 (5) , pgae199
Quantifying US air pollution policy: How political and regional factors influence pollutant mitigation
Air pollution control in the United States has evolved into a comprehensive policy system spanning from the federal to the state level over time. A unified quantitative analysis of policy intensity can shed light on the policy evolution across different levels, the influence of partisan and regional factors on policy, and the relationships with emissions of major pollutants. By harnessing the policy text of the Clean Air Act (CAA) at the federal level and State Implementation Plans (SIPs) at the state governments (1955–2020), we deployed a Natural Language Processing approach to define a policy intensity index to systematically quantify the US air policy landscape. Our findings highlight that the 1970 CAA amendment carries the most vigorous intensity as it established a holistic control system for the first time. Subsequent years witnessed a general trend of partisan polarization, eventually leading to a graduate convergence between red and blue states. Blue states demonstrated a closer alignment with federal directives and a superior efficacy in pollutant reduction. Regionally, the Northeast displays the highest overall policy intensity, and the West exhibits the highest coordination with the federal benchmarks, making these regions outperform others in air pollution control. Our study not only discusses policy implications for air pollutant reductions considering partisan and regional differences but also provides a novel measurement tool to quantify policies for assessing disparities and synergies.
- 30 April 2024
- Published by Oxford University Press (OUP) in PNAS Nexus
- Vol. 3 (5) , pgae199
Open AccessQuantifying US air pollution policy: How political and regional factors influence pollutant mitigation
Air pollution control in the United States has evolved into a comprehensive policy system spanning from the federal to the state level over time. A unified quantitative analysis of policy intensity can shed light on the policy evolution across different levels, the influence of partisan and regional factors on policy, and the relationships with emissions of major pollutants. By harnessing the policy text of the Clean Air Act (CAA) at the federal level and State Implementation Plans (SIPs) at the state governments (1955–2020), we deployed a Natural Language Processing approach to define a policy intensity index to systematically quantify the US air policy landscape. Our findings highlight that the 1970 CAA amendment carries the most vigorous intensity as it established a holistic control system for the first time. Subsequent years witnessed a general trend of partisan polarization, eventually leading to a graduate convergence between red and blue states. Blue states demonstrated a closer alignment with federal directives and a superior efficacy in pollutant reduction. Regionally, the Northeast displays the highest overall policy intensity, and the West exhibits the highest coordination with the federal benchmarks, making these regions outperform others in air pollution control. Our study not only discusses policy implications for air pollutant reductions considering partisan and regional differences but also provides a novel measurement tool to quantify policies for assessing disparities and synergies.
- 22 August 2022
- Published by Springer Nature in Scientometrics
- Vol. 127 (10) , 5819-5839
Measuring destabilization and consolidation in scientific knowledge evolution
- 22 August 2022
- Published by Springer Nature in Scientometrics
- Vol. 127 (10) , 5819-5839
Measuring destabilization and consolidation in scientific knowledge evolution
- 11 June 2022
- Published by Springer Nature in Information Systems Frontiers
- Vol. 25 (4) , 1479-1493
Combating Misinformation by Sharing the Truth: a Study on the Spread of Fact-Checks on Social Media
Misinformation on social media has become a horrendous problem in our society. Fact-checks on information often fall behind the diffusion of misinformation, which can lead to negative impacts on society. This research studies how different factors may affect the spread of fact-checks over the internet. We collected a dataset of fact-checks in a six-month period and analyzed how they spread on Twitter. The spread of fact-checks is measured by the total retweet count. The factors/variables include the truthfulness rating, topic of information, source credibility, etc. The research identifies truthfulness rating as a significant factor: conclusive fact-checks (either true or false) tend to be shared more than others. In addition, the source credibility, political leaning, and the sharing count also affect the spread of fact-checks. The findings of this research provide practical insights into accelerating the spread of the truth in the battle against misinformation online.
- 11 June 2022
- Published by Springer Nature in Information Systems Frontiers
- Vol. 25 (4) , 1479-1493
Combating Misinformation by Sharing the Truth: a Study on the Spread of Fact-Checks on Social Media
Misinformation on social media has become a horrendous problem in our society. Fact-checks on information often fall behind the diffusion of misinformation, which can lead to negative impacts on society. This research studies how different factors may affect the spread of fact-checks over the internet. We collected a dataset of fact-checks in a six-month period and analyzed how they spread on Twitter. The spread of fact-checks is measured by the total retweet count. The factors/variables include the truthfulness rating, topic of information, source credibility, etc. The research identifies truthfulness rating as a significant factor: conclusive fact-checks (either true or false) tend to be shared more than others. In addition, the source credibility, political leaning, and the sharing count also affect the spread of fact-checks. The findings of this research provide practical insights into accelerating the spread of the truth in the battle against misinformation online.
- 2 December 2019
- Published by Springer Nature
- p. 236-246
Detecting False Information in Medical and Healthcare Domains: A Text Mining Approach
- 2 December 2019
- Published by Springer Nature
- p. 236-246
Detecting False Information in Medical and Healthcare Domains: A Text Mining Approach
- 28 October 2017
- Published by Springer Nature
- p. 116-122
Analyzing mHeath Usage Using the mPower Data
- Open Access
- 1 January 2017
- Published by HICSS Conference Office
A Dynamic Network Measure of Knowledge Evolution: A Case Study of MIS Quarterly
Citation measures are the central metrics to assessing the impact of an article, the viability of research streams, the career success of scholars, as well as the quality and status of journals and academic units. While measuring the magnitude of the future usage, they cannot capture the substantial effects that an article may have on the subsequent use of its predecessors-whether it amplifies or disrupts the existing literature. We embrace that it is imperative to not only assess its impact but also assess how an article reinforces the existing research streams or breaks into a new stream to understand its true effect. Accordingly, we introduce a new, dynamic measure, and conduct a case study using all articles published between 1979-2016 at MIS Quarterly to illustrate the validity of the new measure, and conclude with some future research topics and implications.
- 1 January 2017
- Published by HICSS Conference Office
Open AccessA Dynamic Network Measure of Knowledge Evolution: A Case Study of MIS Quarterly
Citation measures are the central metrics to assessing the impact of an article, the viability of research streams, the career success of scholars, as well as the quality and status of journals and academic units. While measuring the magnitude of the future usage, they cannot capture the substantial effects that an article may have on the subsequent use of its predecessors-whether it amplifies or disrupts the existing literature. We embrace that it is imperative to not only assess its impact but also assess how an article reinforces the existing research streams or breaks into a new stream to understand its true effect. Accordingly, we introduce a new, dynamic measure, and conduct a case study using all articles published between 1979-2016 at MIS Quarterly to illustrate the validity of the new measure, and conclude with some future research topics and implications.
- 25 July 2016
- Published by Springer Nature in Electronic Commerce Research
- Vol. 17 (1) , 103-132
Sentiment community detection: exploring sentiments and relationships in social networks
- 25 July 2016
- Published by Springer Nature in Electronic Commerce Research
- Vol. 17 (1) , 103-132
Sentiment community detection: exploring sentiments and relationships in social networks