Exploring Implied Performance Metrics In Customer Trustworthiness Toward The Acquisition Of Halal Food's Status
DOI:
https://doi.org/10.53840/myjict7-2-160Keywords:
Sentiment Analysis, Halal Food, Natural Language Processing, Performance Metrics, Machine Learning ModelAbstract
Social media is used extensively in various fields, including Natural Language Processing research. The exponential growth of user-generated social media content raises the potential for opinion mining to analyze consumer behavior. Sentiment Analysis concerns the computer treatment of people's views, ideas, and subjective experiences to recognize and extract sentiment from a text. The influence of religious conviction, halal awareness, halal certification, and food ingredients are all-inclusive in Muslim consumers' considerations while acquiring halal food. Those aspects assist in uncovering sentimental analysis on customer dependability toward halal certification during expressing issues related to halal food acquisition on social media. We aim to determine a correlation between the halal certification scheme and reliability prediction classification relating to customers' intention to acquire halal products. Identifying corresponding sentiment polarities in sentences is generated by utilizing the Malaya NLTK library to label them as positive, negative, or neutral. A sample of 895 tweets with the hashtag #sijilhalal was gauged and trained for an accurate prediction Machine Learning model using Random Forest, Logistic Regression, K-Nearest Neighbor, Decision Tree, and Naive Bayes. The Correlation Matrix for each model shows how features are related. As in its Confusion Matrix, we can observe an outcome overview of the model's accuracy, precision, recall, and F1-score. It successfully demonstrates the performance evaluation metric on model efficiency and applicability in choosing the best higher-accuracy model for predicting customer tendency toward halal food acquisition. In general, the Logistic Regression model performs the best in this study of predicting the occurrence of customer trustworthiness toward the acquisition of halal food. The findings show that consumers' belief in a food source and halal certification leads them to entirely acquire the food (tagged as loyal) or disregard the food (tagged as churn).
Downloads
References
Alshamsi, A., Bayari, R., & Salloum, S. (2020). Sentiment analysis in English Texts. Advances in Science, Technology and Engineering Systems, 5(6), 1638–1689. https://doi.org/10.25046/AJ0506200
Amiri, H., & Chua, T. S. (2012). Mining slang and urban opinion words and phrases from cQA services: An optimization approach. WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining, 193–202. https://doi.org/10.1145/2124295.2124319
Ariffin, S. N. A. N., & Tiun, S. (2020). Rule-based text normalization for malay social media texts. International Journal of Advanced Computer Science and Applications, 11(10), 156–162. https://doi.org/10.14569/IJACSA.2020.0111021
Azam, M. S. E., & Abdullah, M. A. (2020). Global Halal Industry: Realities and Opportunities. International Journal of Islamic Business Ethics, 5(1), 47. https://doi.org/10.30659/ijibe.5.1.47-59
Chekima, K., & Alfred, R. (2016). An automatic construction of Malay stop words based on aggregation method. Communications in Computer and Information Science, 652(September), 180–189. https://doi.org/10.1007/978-981-10-2777-2_16
Demirel, Y., & Yaşarsoy, E. (2017). Exploring Consumer Attitudes Towards Halal. Journal of Tourismology, 3(1), 34–43. https://doi.org/10.26650/jot.2017.3.1.0003
Feizollah, A., Mostafa, M. M., Sulaiman, A., Zakaria, Z., & Firdaus, A. (2021). Exploring halal tourism tweets on social media. Journal of Big Data, 8(1). https://doi.org/10.1186/s40537-021-00463-5
Gamal, D., Alfonse, M., M.El-Horbaty, E.-S., & M.Salem, A.-B. (2019). Twitter Benchmark Dataset for Arabic Sentiment Analysis. International Journal of Modern Education and Computer Science, 11(1), 33–38. https://doi.org/10.5815/ijmecs.2019.01.04
Gonçalves, P., Araújo, M., Benevenuto, F., & Cha, M. (2014). Comparing and Combining Sentiment Analysis Methods. https://doi.org/10.1145/2512938.2512951
Gregory, H., Li, S., Mohammadi, P., Tarn, N., Draelos, R., & Rudin, C. (2020). A Transformer Approach to Contextual Sarcasm Detection in Twitter. 270–275. https://doi.org/10.18653/v1/2020.figlang-1.37
Hasbullah, S. S., Maynard, D., Wan Chik, R. Z., Mohd, F., & Noor, M. (2016). Automated content analysis: A sentiment analysis on Malaysian government social media. ACM IMCOM 2016: Proceedings of the 10th International Conference on Ubiquitous Information Management and Communication. https://doi.org/10.1145/2857546.2857577
Husein, Z. (2018). Malaya, Natural-Language-Toolkit library for bahasa Malaysia, powered by Deep Learning Tensorflow. In GitHub repository.
Kassim, M. N., Maarof, M. A., Zainal, A., & Wahab, A. A. (2016). Word stemming challenges in Malay texts: A literature review. 2016 4th International Conference on Information and Communication Technology, ICoICT 2016, 4(c). https://doi.org/10.1109/ICoICT.2016.7571887
Khan, G., & Khan, F. (2020). “Is this restaurant halal?” Surrogate indicators and Muslim behaviour. Journal of Islamic Marketing, 11(5), 1105–1123. https://doi.org/10.1108/JIMA-01-2019-0008
Khirulnizam Abd Rahman. (2014). List of Malay stop words. http://blog.kerul.net/2014/01/list-of-malay-stop-words.html
Lan, T. S., & Logeswaran, R. (2020). Challenges and development in Malay natural language processing. Journal of Critical Reviews, 7(3), 61–65. https://doi.org/10.31838/jcr.07.03.10
Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis Lectures on Human Language Technologies, 5(1), 1–184. https://doi.org/10.2200/S00416ED1V01Y201204HLT016
Mohd Farid Hadi Sharif, D. M. Z. A. G. (2019). Halal Viral Issues in Malaysia. Halal Journal, 3, 61–71.
Pal, A. R., & Saha, D. (2013). Detection of Jargon Words in a Text Using Semi-Supervised Learning. July 2013, 95–107. https://doi.org/10.5121/csit.2013.3411
Setik, R., Ahmad, R. M. T. R. L., & Marjudi, S. (2021). Exploring Classification For Sentiment Analysis From Halal Based Tweets. 2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS), 1–6. https://doi.org/10.1109/aidas53897.2021.9574255
Shahrinaz, I., Kasuma, J., Sarpinah, B., & Naimullah, S. (2015). Purchase Manufactured Halal Food Products among Muslim students Do Attitude , Trust and Knowledge have relationship towards Purchase intention of Manufactured Halal Food Product ? 737(November).
Sharma, P., & Sharma, A. K. (2020). Experimental investigation of automated system for twitter sentiment analysis to predict the public emotions using machine learning algorithms. Materials Today: Proceedings, xxxx. https://doi.org/10.1016/j.matpr.2020.09.351
Stopwords, I. (n.d.). Indonesian ( Malay ) Stopwords.
Wiebe, J., & Riloff, E. (2005). Creating subjective and objective sentence classifiers from unannotated texts. Lecture Notes in Computer Science, 3406(October), 486–497. https://doi.org/10.1007/978-3-540-30586-6_53
Windasari, I. P., Uzzi, F. N., & Satoto, K. I. (2017). Sentiment analysis on Twitter posts: An analysis of positive or negative opinion on GoJek. Proceedings - 2017 4th International Conference on Information Technology, Computer, and Electrical Engineering, ICITACEE 2017, 2018-Janua, 266–269. https://doi.org/10.1109/ICITACEE.2017.8257715
Zhao, J., Liu, K., & Xu, L. (2016). Sentiment Analysis: Mining Opinions, Sentiments, and Emotions. Computational Linguistics, 42(3), 595–598. https://doi.org/10.1162/coli_r_00259
Zohreh Madhoushi, Z. M., Hamdan, A. R., & Zainudin, S. (2019). Aspect-Based Sentiment Analysis Methods in Recent Years. Asia-Pacific Journal of Information Technology & Multimedia, 08(01), 79–96.https://doi.org/10.17576/apjitm-2019-0801-07
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Malaysian Journal of Information and Communication Technology (MyJICT)
This work is licensed under a Creative Commons Attribution 4.0 International License.
