Georgia Institute of Technology
Exploratory Analysis of Construction Job Opening Advertisements for Investigating Actual Labor Needs Using Web scraping and Text Analytics
Abstract
dc:description.abstractA comprehensive analysis of construction job opening advertisements was conducted to extract detailed information on wages, locations, and job requirements. This study utilized web scraping and text mining techniques to collect a dataset comprising over 1.4 million job openings across the United States. The research employed a combination of natural language processing (NLP), machine learning (ML), statistical methods, application programming interfaces (APIs), and chatbots across three main chapters. Chapter 1 focused on identifying skill sets required for multiskilled laborers in the construction industry. Chapter 2 examined wage disparities to address issues of workforce equity. In Chapter 3, chatbots were employed to explore additional dynamics within the construction job market. This dissertation introduces an innovative approach to capturing and analyzing large-scale data from construction job advertisements using web scraping and text analytics. The findings aim to revolutionize the understanding and management of the construction job market, providing valuable insights for industry stakeholders. The anticipated long-term benefits include improved strategic decision-making, enhanced workforce management strategies, and greater adaptability to dynamic market changes.
Degree
thesis:*- Level thesis:degree_level
- Doctoral
- Department dc:contributor.department
- Building Construction
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Oh, Heung Jin
- Advisor dc:contributor.advisor
-
- Ashuri, Baabak
- Committee members dc:contributor.committeemember
-
- Yang, Eunhwa
- Wen, Jing
- Marks, Eric
- Shahandashti, Mohsen
Subjects
dc:subject × 8Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/75660