The travel and hospitality industry faces significant safety challenges, particularly with regard to women's experiences, which significantly impact their participation and viewpoints. This research investigates these concerns by looking at the experiences of women and risk management strategies used in the industry. We preprocess qualitative data using tokenisation in an orderly way, breaking down textual responses into manageable portions for research. Finding significant themes and patterns in women's safety worries can be accomplished through feature selection utilising Latent Semantic Analysis (LSA). Logistic regression is a classification approach used to predict risk levels and determine the primary reasons of harmful interactions. The findings demonstrate a substantial correlation between organisational, societal, and environmental factors and perceived safety hazards. This report gives industry stakeholders useful insights by highlighting the importance of targeted risk management strategies and legislative initiatives. By using machine learning techniques, the research advances knowledge and offers evidence-based solutions to increase safety and inclusivity for women in the travel and hospitality industries.
Read full abstract