Asia pacific journal of information systems

  • 제34권2호
  • /
  • Pages.400-420
  • /
  • 2024
  • /
  • 2288-5404(pISSN)
  • /
  • 2288-6818(eISSN)
한국경영정보학회 (The Korea Society of Management Information Systems)
권호 표지
DOI QR코드

DOI QR Code

Sentimental Analysis of Twitter Data Using Machine Learning and Deep Learning: Nickel Ore Export Restrictions to Europe Under Jokowi's Administration 2022

  • Sophiana Widiastutie (Department of International Relations, Universitas Pembangunan Nasional Veteran Jakarta) ;
  • Dairatul Maarif (Department of International Relations, Universitas Pembangunan Nasional Veteran Jakarta) ;
  • Adinda Aulia Hafizha (Department of International Relations, Universitas Pembangunan Nasional Veteran Jakarta)
  • 투고 : 2023.08.24
  • 심사 : 2024.01.22
  • 발행 : 2024.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Nowadays, social media has evolved into a powerful networked ecosystem in which governments and citizens publicly debate economic and political issues. This holds true for the pros and cons of Indonesia's ore nickel export restriction to Europe, which we aim to investigate further in this paper. Using Twitter as a dependable channel for conducting sentiment analysis, we have gathered 7070 tweets data for further processing using two sentiment analysis approaches, namely Support Vector Machine (SVM) and Long Short Term Memory (LSTM). Model construction stage has shown that Bidirectional LSTM performed better than LSTM and SVM kernels, with accuracy of 91%. The LSTM comes second and The SVM Radial Basis Function comes third in terms of best model, with 88% and 83% accuracies, respectively. In terms of sentiments, most Indonesians believe that the nickel ore provision will have a positive impact on the mining industry in Indonesia. However, a small number of Indonesian citizens contradict this policy due to fears of a trade dispute that could potentially harm Indonesia's bilateral relations with the EU. Hence, this study contributes to the advancement of measuring public opinions through big data tools by identifying Bidirectional LSTM as the optimal model for the dataset.

키워드

참고문헌

  1. Ahmad, M., Aftab, S., Bashir, M. S., and Hameed, N. (2018). Sentiment analysis using SVM: A systematic literature review. International Journal of Advanced Computer Science and Applications, 9(2), 182-188. https://doi.org/10.14569/IJACSA.2018.090226 
  2. Ahuja, R., Chug, A., Kohli, S., Gupta, S., and Ahuja, P. (2019). The impact of features extraction on the sentiment analysis. Procedia Computer Science, 152, 341-348. https://doi.org/10.1016/j.procs.2019.05.008 
  3. Aladwani, A. M., and Dwivedi, Y. K. (2018). Towards a theory of SocioCitizenry: Quality anticipation, trust configuration, and approved adaptation of governmental social media. International Journal of Information Management, 43(March), 261-272. https://doi.org/10.1016/j.ijinfomgt.2018.08.009 
  4. Aljedaani, W., Rustam, F., Mkaouer, M. W., Ghallab, A., Rupapara, V., Washington, P. B., Lee, E., and Ashraf, I. (2022). Sentiment analysis on Twitter data integrating TextBlob and deep learning models: The case of US airline industry. Knowledge-Based Systems, 255, 109780. https://doi.org/10.1016/j.knosys.2022.109780 
  5. Altig, D., Baker, S., Barrero, J. M., Bloom, N., Bunn, P., Chen, S., Davis, S. J., Leather, J., Meyer, B., Mihaylov, E., Mizen, P., Parker, N., Renault, T., Smietanka, P., and Thwaites, G. (2020). Economic uncertainty before and during the COVID-19 pandemic. Journal of Public Economics, 191, 104274. https://doi.org/10.1016/j.jpubeco.2020.104274 
  6. Ardianti, R., and Lestari, W. D. (2023). Government policy regarding coal and nickel export ban the impact on the indonesian mining industry. International Journal of Accounting, Management and Economic Research (IJAMER), 1(1), 23-33.  https://doi.org/10.56696/ijamer.v1i1.5
  7. Blazquez, D., and Domenech, J. (2018). Big Data sources and methods for social and economic analyses. Technological Forecasting and Social Change, 130, 99-113. https://doi.org/10.1016/j.techfore.2017.07.027 
  8. Boon-Itt, S., and Skunkan, Y. (2020). Public perception of the COVID-19 pandemic on Twitter: Sentiment analysis and topic modeling study. JMIR Public Health Surveill, 6(4), e21978. https://doi.org/10.2196/21978 
  9. Cahyani, D. E., and Patasik, I. (2021). Performance comparison of tf-idf and word2vec models for emotion text classification. Bulletin of Electrical Engineering and Informatics, 10(5), 2780-2788. https://doi.org/10.11591/eei.v10i5.3157 
  10. Carracedo, P., Puertas, R., and Marti, L. (2021). Research lines on the impact of the COVID-19 pandemic on business. A text mining analysis. Journal of Business Research, 132, 586-593. https://doi.org/10.1016/j.jbusres.2020.11.043 
  11. Chen, L. C., Lee, C. M., and Chen, M. Y. (2020). Exploration of social media for sentiment analysis using deep learning. Soft Computing, 24(11), 8187-8197. https://doi.org/10.1007/s00500-019-04402-8 
  12. Chory, R. N., Nasrun, M., and Setianingsih, C. (2019). Sentiment analysis on user satisfaction level of mobile data services using Support Vector Machine (SVM) algorithm. In Proceedings - 2018 IEEE International Conference on Internet of Things and Intelligence System, IOTAIS 2018 (pp. 194-200). https://doi.org/10.1109/IOTAIS.2018.8600884 
  13. Day, M. Y., and Lin, Y. Da. (2017). Deep learning for sentiment analysis on google play consumer review. In Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017, 2017-Janua (pp. 382-388). https://doi.org/10.1109/IRI.2017.79 
  14. Day, M. Y., and Teng, H. C. (2017). A study of deep learning to sentiment analysis on word of mouth of smart bracelet. In Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017 (pp. 763-770). https://doi.org/10.1145/3110025.3110129 
  15. Devika, M. D., Sunitha, C., and Ganesh, A. (2016). Sentiment analysis: A comparative study on different approaches. Procedia Computer Science, 87, 44-49. https://doi.org/10.1016/j.procs.2016.05.124 
  16. Duncombe, C. (2017). Twitter and transformative diplomacy: Social media and Iran-US relations. International Affairs, 93(3), 545-562. https://doi.org/10.1093/ia/iix048 
  17. Duncombe, C. (2019). The politics of Twitter: Emotions and the power of social media. International Political Sociology, 13(4), 409-429. https://doi.org/10.1093/ips/olz013 
  18. Elgendy, N., and Elragal, A. (2016). Big data analytics in support of the decision making process. In Procedia Computer Science, 100, 1071-1084. https://doi.org/10.1016/j.procs.2016.09.251 
  19. Georgiadou, E., Angelopoulos, S., and Drake, H. (2020). Big data analytics and international negotiations: Sentiment analysis of Brexit negotiating outcomes. International Journal of Information Management, 51(November 2019). https://doi.org/10.1016/j.ijinfomgt.2019.102048 
  20. Graham, T., Jackson, D., and Broersma, M. (2014). New platform, old habits? Candidates' use of Twitter during the 2010 British and Dutch general election campaigns. New Media and Society, 18(5). https://doi.org/10.1177/1461444814546728 
  21. Grcar, M., Cherepnalkoski, D., Mozetic, I., and Kralj Novak, P. (2017). Stance and influence of Twitter users regarding the Brexit referendum. Computational Social Networks, 4(1). https://doi.org/10.1186/s40649-017-0042-6 
  22. Grover, P., Kar, A. K., Dwivedi, Y. K., and Janssen, M. (2019). Polarization and acculturation in US Election 2016 outcomes - Can twitter analytics predict changes in voting preferences. Technological Forecasting and Social Change, 145, 438-460. https://doi.org/10.1016/j.techfore.2018.09.009 
  23. Grubmuller, V., Gotsch, K., and Krieger, B. (2013). Social media analytics for future oriented policy making. European Journal of Futures Research, 1(20), 1-9. https://doi.org/10.1007/s40309-013-0020-7 
  24. Guerrero-Sole, F. (2018). Interactive behavior in political discussions on Twitter: Politicians, media, and citizens' patterns of interaction in the 2015 and 2016 electoral campaigns in Spain. Social Media and Society, 4(4). https://doi.org/10.1177/2056305118808776 
  25. Hall, W., Tinati, R., and Jennings, W. (2018). From brexit to trump: Social media's role in democracy. Computer, 51(1), 18-27. https://doi.org/10.1109/MC.2018.1151005 
  26. Han, K. X., Chien, W., Chiu, C. C., and Cheng, Y. T. (2020). Application of support vector machine (SVM) in the sentiment analysis of twitter dataset. Applied Sciences (Switzerland), 10(3). https://doi.org/10.3390/app10031125 
  27. Hurlimann, M., Davis, B., Cortis, K., Freitas, A., and Fernandez, S. (2016). A Twitter Sentiment Gold Standard for the Brexit Referendum. In SEMANTiCS 2016: Proceedings of the 12th International Conference on Semantic Systems. https://doi.org/10.1145/2993318.2993350 
  28. Imran, A. S., Daudpota, S. M., Kastrati, Z., and Batra, R. (2020). Cross-cultural polarity and emotion detection using sentiment analysis and deep learning on covid-19 related tweets. IEEE Access, 8, 181074-181090. https://doi.org/10.1109/ACCESS.2020.3027350 
  29. International Labour Organization. (2022). A Just Energy Transition in Southeast Asia: The Impacts of Coal Phase-Out on Jobs. International Labour Organization. 
  30. International Nickel Study Group. (2021). The World Nickel Factbook 2021. Retrieved from https://insg.org/wp-content/uploads/2022/02/publist_The-World-Nickel-Factbook-2021.pdf 
  31. Kadhim, A. I. (2019). Term weighting for feature extraction on Twitter: A comparison between BM25 and TF-IDF. In 2019 International Conference on Advanced Science and Engineering, ICOASE 2019 (pp. 124-128). https://doi.org/10.1109/ICOASE.2019.8723825 
  32. Krustiyati, A., and Christine, N. (2022). Analyzing the lawsuit of the European Union over nickel ore export regulation in Indonesia. Croatian International Relations Review, XXVIII(89), 121-135. https://doi.org/10.2478/CIRR-2022-0007 
  33. Kurniawan, A. R., Murayama, T., and Nishikizawa, S. (2021). Appraising affected community perceptions of implementing programs listed in the environmental impact statement: A case study of Nickel smelter in Indonesia. The Extractive Industries and Society, 8(1), 363-373. https://doi.org/10.1016/j.exis.2020.11.015 
  34. Leelawat, N., Jariyapongpaiboon, S., Promjun, A., and Boonyarak, S. (2022). Twitter data sentiment analysis of tourism in Thailand during the COVID-19 pandemic using machine learning. Heliyon, 8(June). https://doi.org/10.1016/j.heliyon.2022.e10894 
  35. Lim, B., Kim, H. S., and Park, J. (2021). Implicit interpretation of Indonesian export bans on LME nickel prices: Evidence from the announcement effect. Risks, 9(93). https://doi.org/10.3390/risks9050093 
  36. Liu, B. (2012). Sentiment Analysis and Opinion Mining. Morgan and Claypool Publishers. 
  37. Lyu, Z., and Takikawa, H. (2022). Media framing and expression of anti-China sentiment in COVID-19-related news discourse: An analysis using deep learning methods. Heliyon, 8(8), e10419. https://doi.org/10.1016/j.heliyon.2022.e10419 
  38. Ma, Y., Wang, M., and Li, X. (2022). Analysis of the characteristics and stability of the global complex nickel ore trade network. Resources Policy, 79, 103089. https://doi.org/10.1016/j.resourpol.2022.103089 
  39. Medhat, W., Hassan, A., and Korashy, H. (2014). Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal, 5(4), 1093-1113. https://doi.org/10.1016/j.asej.2014.04.011 
  40. Mohammed, S. H., and Al-Augby, S. (2020). LSA and LDA topic modeling classification: Comparison study on E-books. Indonesian Journal of Electrical Engineering and Computer Science, 19(1), 353-362. https://doi.org/10.11591/ijeecs.v19.i1.pp353-362 
  41. Mourya, A. K., ShafqatUlAhsaan, and Kaur, H. (2020). Performance and evaluation of different kernels in support vector machine for text mining. In M. N. Mohanty and S. Das (Eds.), Advances in Intelligent Computing and Communication (pp. 264-271). Springer Singapore. 
  42. Naing, H. W., Thwe, P., Mon, A. C., and Naw, N. (2019). Analyzing sentiment level of social media data based on SVM and Naive Bayes algorithms. Advances in Intelligent Systems and Computing, 744, 68-76. https://doi.org/10.1007/978-981-13-0869-7_8 
  43. Naseem, U., Razzak, I., Khushi, M., Eklund, P. W., and Kim, J. (2021). COVIDSenti: A large-scale benchmark Twitter data set for COVID-19 sentiment analysis. IEEE Transactions on Computational Social Systems, 8(4), 1003-1015. https://doi.org/10.1109/TCSS.2021.3051189 
  44. Naw, N., and Mon, A. C. (2018). Social media data analysis in sentiment level by using support vector machine. Journal of Pharmacognosy and Phytochemistry, 7(1S), 609-613. 
  45. Nemes, L., and Kiss, A. (2021). Social media sentiment analysis based on COVID-19. Journal of Information and Telecommunication, 5(1), 1-15. https://doi.org/10.1080/24751839.2020.1790793 
  46. Neogi, A. S., Garg, K. A., Mishra, R. K., and Dwivedi, Y. K. (2021). Sentiment analysis and classification of Indian farmers' protest using twitter data. International Journal of Information Management Data Insights, 1(2). https://doi.org/10.1016/j.jjimei.2021.100019 
  47. Nguyen, N. H., Nguyen, D. T. A., Ma, B., and Hu, J. (2022). The application of machine learning and deep learning in sport: predicting NBA players' performance and popularity. Journal of Information and Telecommunication, 6(2), 217-235. https://doi.org/10.1080/24751839.2021.1977066 
  48. Pandyaswargo, A. H., Wibowo, A. D., Maghfiroh, M. F. N., Rezqita, A., and Onoda, H. (2021). The emerging electric vehicle and battery industry in Indonesia: Actions around the nickel ore export ban and a SWOT analysis. Batteries, 7(80). https://doi.org/10.3390/batteries7040080 
  49. Pasupa, K., and Seneewong Na Ayutthaya, T. (2019). Thai sentiment analysis with deep learning techniques: A comparative study based on word embedding, POS-tag, and sentic features. Sustainable Cities and Society, 50(December 2018), 101615. https://doi.org/10.1016/j.scs.2019.101615 
  50. Prastyo, P. H., Sumi, A. S., Dian, A. W., and Permanasari, A. E. (2020). Tweets responding to the indonesian government's handling of COVID-19: Sentiment analysis using SVM with normalized poly kernel. Journal of Information Systems Engineering and Business Intelligence, 6(2), 112. https://doi.org/10.20473/jisebi.6.2.112-122 
  51. Pratama, B., Saputra, D. D., Novianti, D., and Purnamasari, E. P. (2019). Sentiment analysis of the Indonesian police mobile brigade corps based on Twitter posts using the SVM and NB methods. Journal of Physics: Conference Series, 1201. https://doi.org/10.1088/1742-6596/1201/1/012038 
  52. Prentice, C., Chen, J., and Stantic, B. (2020). Timed intervention in COVID-19 and panic buying. Journal of Retailing and Consumer Services, 57, 102203. https://doi.org/10.1016/j.jretconser.2020.102203 
  53. Rahardi, M., Aminuddin, A., Abdulloh, F. F., and Nugroho, R. A. (2022). Sentiment analysis of Covid-19 vaccination using support vector machine in Indonesia. International Journal of Advanced Computer Science and Applications, 13(6), 534-539. https://doi.org/10.14569/IJACSA.2022.0130665 
  54. Rahat, A. M., Kahir, A., and Masum, A. K. M. (2019). Comparison of Naive Bayes and SVM Algorithm based on Sentiment Analysis Using Review Dataset. In Proceedings of the 2019 8th International Conference on System Modeling and Advancement in Research Trends, SMART 2019 (pp. 266-270). https://doi.org/10.1109/SMART46866.2019.9117512 
  55. Razali, N. A. M., Malizan, N. A., Hasbullah, N. A., Wook, M., Zainuddin, N. M., Ishak, K. K., Ramli, S., and Sukardi, S. (2021). Opinion mining for national security: Techniques, domain applications, challenges and research opportunities. Journal of Big Data, 8(1). https://doi.org/10.1186/s40537-021-00536-5 
  56. Soelistijo, U. W. (2013). Prospect of potential nickel added value development in Indonesia. Earth Science, 2(6), 129-138. https://doi.org/10.11648/j.earth.20130206.13 
  57. Sontayasara, T., Jariyapongpaiboon, S., Promjun, A., Seelpipat, N., Saengtabtim, K., Tang, J., and Leelawat, N. (2021). Twitter sentiment analysis of bangkok tourism during covid-19 pandemic using support vector machine algorithm. Journal of Disaster Research, 16(1), 24-30. https://doi.org/10.20965/jdr.2021.p0024 
  58. Tai, K. S., Socher, R., and Manning, C. D. (2015). Improved semantic representations from tree-structured long short-Term memory networks. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference, 1, 1556-1566. https://doi.org/10.3115/v1/p15-1150 
  59. U.S. Geological Survey. (2022). Mineral Commodity Summaries 2022. U.S. Geological Survey, Retrieved from https://doi.org/10.3133/mcs2022 
  60. Vijay, and Verma, P. (2022). Extremism detection on social media using SVM text classifier. Journal of Pharmaceutical Negative Results, 13(7), 3748-3753. https://doi.org/10.47750/pnr.2022.13.S07.477 
  61. Wankhade, M., Rao, A. C. S., and Kulkarni, C. (2022). A survey on sentiment analysis methods, applications, and challenges. Artificial Intelligence Review, 55(7). Springer Netherlands. https://doi.org/10.1007/s10462-022-10144-1 
  62. Widiatedja, I. G. N. P. (2021). Indonesia's export ban on nickel ore: Does it violate the World Trade Organization (WTO) rules? Journal of World Trade, 667-696. http://www.kluwerlawonline.com/api/Product/CitationPDFURL?file=Journals%5CTRAD%5CTRAD2021028.pdf  1028.pdf