Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India

Research Article

Overseas Construction Suppliers Assessment based on Clustering and Sentiment Analysis

Download51 downloads
  • @INPROCEEDINGS{10.4108/eai.23-11-2023.2343249,
        author={Qing Mei Shi and Siva Shankar Ramasamy and Praveenkumar  Somasundara},
        title={Overseas Construction Suppliers Assessment based on Clustering and Sentiment Analysis},
        proceedings={Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India},
        publisher={EAI},
        proceedings_a={IACIDS},
        year={2024},
        month={3},
        keywords={sentiment analysis overseas construction suppliers classification techniques supplier evaluation risk management},
        doi={10.4108/eai.23-11-2023.2343249}
    }
    
  • Qing Mei Shi
    Siva Shankar Ramasamy
    Praveenkumar Somasundara
    Year: 2024
    Overseas Construction Suppliers Assessment based on Clustering and Sentiment Analysis
    IACIDS
    EAI
    DOI: 10.4108/eai.23-11-2023.2343249
Qing Mei Shi1,*, Siva Shankar Ramasamy1, Praveenkumar Somasundara2
  • 1: International College of Digital Innovation, Chiangmai University, Chiang Mai, Thailand
  • 2: Qualcomm Technologies Inc., USA
*Contact email: linlin_xu@cmu.ac.th

Abstract

The Global construction projects requires a combination of contractors, suppliers, Engineers, Real estate people, Labors in foreign soil. It is better to know or assess the team before involving them with major projects or government-based projects. The article proposes an innovative approach to evaluate overseas construction suppliers using clustering and sentiment analysis techniques which analyze the textual data from various sources, such as customer reviews and supplier communications. The sentiment scores are utilized for supplier classification using machine learning algorithms. This work study and validates the effectiveness of our approach in assisting construction companies with supplier selection and risk management. Despite some limitations, our approach provides valuable insights into supplier performance and reputation. By leveraging sentiment analysis, construction companies can make informed decisions and enhance project outcomes through better supplier management. The method also involves K-Mean clustering to set up the construction unit to increase the score of the construction supply to the projects. This research contributes to advancing sentiment analysis applications in the construction industry on a global scale..