@article{scholars12764,
           title = {Sentiment analysis techniques to analyze hse situational awareness at oil and gas platforms using machine learning},
             doi = {10.21817/indjcse/2020/v11i5/201105244},
            note = {cited By 3},
          volume = {11},
          number = {5},
           pages = {640--645},
       publisher = {Engg Journals Publications},
         journal = {Indian Journal of Computer Science and Engineering},
            year = {2020},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85094810514&doi=10.21817\%2findjcse\%2f2020\%2fv11i5\%2f201105244&partnerID=40&md5=dbe17cbecf5075c11527d6f8838e0344},
        abstract = {Health Safety \& Environment (HSE) situational awareness is a very important aspect of any risky workplace. Negligence in complying with HSE policies and practices might lead to unwanted incidents, critical injuries, death, spread of diseases and environmental pollution. In most corporations, information on HSE related incidents is disseminated through formal channels such as reports. Employees on the other hand frequently use social media to share, complain and discuss HSE-related issues. The issues are discussed through an informal platform, it is difficult to analyze opinions for further action. Therefore, this study will investigate existing sentiment analysis models and formulate a suitable sentiment analysis model using machine learning technique. Through literature review, Na{\~A}?ve Bayes model was found to be the most efficient text classification in sentiment analysis. This technique still needs further enhancement as the accuracy is not within requirement. Upon enhancing the Na{\~A}?ve Bayes model, a better outcome can be attained. {\^A}{\copyright} 2020, Engg Journals Publications. All rights reserved.},
          author = {Dafaallah, D. E. and Hashim, A. S.},
            issn = {09765166}
}