Social media is widely used as a means of interactions among virtual communities as more and more people openly create, share, and/or exchange information and ideas in Facebook, Twitter, Instagram, LinkedIn, YouTube and online forums. With the increasing amount of data available on social media channels, valuable insights into how people feel about products, person, issues, initiatives or services can be obtained if the social media is monitored for mentions of brand, competitor brands, initiatives, issues, persons and related keywords to help organizations make smarter, data-driven decisions. However, many of the currently available social media listening tools cannot be effectively used for monitoring the Malaysian social media. Malaysian use a lot of mixed languages such as Manglish. We also have our own Malay short forms, neologism, sarcasm and idioms. There are also issues of other noises and spams in the Malaysian social media before it can be mined accurately. Many of the current rule-based approaches, machine learning-based approaches and their hybrids fails to accurately mine the Malaysian social media because of these issues. In this talk, we will discuss the approaches that can be used to handle the issues, such as using our own valence shifter, Malaysian lexicons, and sarcasm handler. Finally, we will d iscuss how deep learning, data fusion and Generative Pre-trained Transformer tools can be used to mine the Malaysian social media.
Dr Naomie is a professor at the Faculty of Computing UTM. She obtained her PhD (Computational Informatics) from University of Sheffield. She is currently the Director of UTM Big Data Centre. She works on design of new algorithms to improve the effectiveness of searching and mining of new knowledge from various types of data. She has been involved in 57 research projects with a total amount of nearly RM5 million. She has published more than 400 papers. She has been awarded as 2020 Malaysia Top Research Scientist by Akademi Sains Malaysia. Some of her other awards are PECIPTA 2011 Gold Medal award for her cross-language semantic plagiarism detection system, the I-inova 2010 Gold Medal award for her Islamic Ontology-based Quran search engine, BioInnovation 2011 Bronze Award for UTMChem Workbench Molecular Database System, iPhex Gold Medal Award for innovation in teaching and learning, UTM 2011 Best Research Award and UTM 2014 Best Research Award. Her innovation in big data, data warehousing and mobile applications has benefited industry such as MAMPU, Johor Corporations, Malaysia Marine and Heavy Engineering Ptd. Ltd., Malaysia Higher Education Ministry and Companies Commission of Malaysia (SSM). 48 PhD students have graduated under her supervision. She was a fellow of the Japan Society for Promotion of Science and is the Head of the Malaysian Big Data Research Consortium.