Comparative Analysis of Energy Efficiency Action Plans of Malaysia and Ireland Using Text Mining


  • Kimberly Chan Fuze Ecoteer Outdoor Adventures Sdn Bhd (Perhentian Turtle Project)
  • Khuneswari Gopal Pillay Universiti Tun Hussein onn Malaysia


Text Mining, Energy Efficiency Action Plan, Non-Negative Matrix Factorization, Word Cloud


The growing population and energy demand across the globe has become a significant concern to the environment as it continues to strain non-renewable resources. Malaysia was leading as the highest energy consumer in Asia and Ireland responsible for 30 per cent of greenhouse gas emissions in the European Union (EU). The National Energy Efficiency Action Plan (NEEAP) aims to achieve energy efficiency targets across EU has recently been adopted by Malaysia in 2015. The objectives of this research are to determine measures and initiatives of the action plans using Non-Negative Matrix Factorization, to generate a word cloud of the common terms in the action plan and to identify the key differences of the focus between the action plans. The text from the action plan is pre-processed and text mining is carried out with Python programming language using the natural language toolkit, SpaCy and scikit.learn libraries. Both Malaysia and Ireland showed the energy and efficiency as the most frequent in the word cloud, followed by electricity and industrial, and transport, building, and public respectively. This showed a link between the topics and the frequent words appearing in the action plan. The objectives of this research were achieved, and text mining was able to find differences between the two action plans. Potential measures for future NEEAPs for Malaysia with a topic prediction model using NMF can be learned from the action plans of other developed and developing countries and N-grams can be usedto extract collocation of words to create a sophisticated word cloud.




How to Cite

Chan, K., & Gopal Pillay, K. (2023). Comparative Analysis of Energy Efficiency Action Plans of Malaysia and Ireland Using Text Mining . Enhanced Knowledge in Sciences and Technology, 3(1), 207–215. Retrieved from