Uncovering negative sentiments: a study of indonesian twitter users' health opinions on coffee consumption

Laksono Budiarto; Nissa Mawada   Rokhman; Wako   Uriu

doi:10.31763/businta.v7i1.606

Authors

Laksono Budiarto Universitas Negeri Malang
Nissa Mawada Rokhman Universitas Negeri Malang
Wako Uriu Chikushi Jogakuen University

DOI:

https://doi.org/10.31763/businta.v7i1.606

Keywords:

sentiment analysis, twitter, coffee effect, negative opinion, RapidMiner

Abstract

The increase in coffee consumption among the public is due to several reasons, including health and lifestyle reasons. Awareness of the positive and negative effects of coffee consumption has also increased in society. This research is a sentiment analysis that aims to investigate Twitter users' opinions about the impact of coffee consumption on their health. The method used involves data collection using the RapidMiner application, utilizing the Twitter Application Programming Interface (API) function connected to a prepared Twitter account. The obtained data underwent data cleaning, saved as an Excel file type, training and testing, and model evaluation. Then, the data was classified into three categories: Negative Opinion, Neutral Opinion, and Positive Opinion. The results showed that less than 10% of opinions were positive, 19% were neutral, and 73% were negative. The opinions obtained are useful information for stakeholders in the coffee industry. They can also be used to determine better steps in educating the public about coffee.

References

R. Poole, O. J. Kennedy, P. Roderick, J. A. Fallowfield, P. C. Hayes, and J. Parkes, “Coffee consumption and health: umbrella review of meta-analyses of multiple health outcomes,” BMJ, vol. 359, p. j5024, Nov. 2017, doi: 10.1136/bmj.j5024.

J. V. Higdon and B. Frei, “Coffee and Health: A Review of Recent Human Research,” Crit. Rev. Food Sci. Nutr., vol. 46, no. 2, pp. 101–123, Mar. 2006, doi: 10.1080/10408390500400009.

F. Bastian et al., “From Plantation to Cup: Changes in Bioactive Compounds during Coffee Processing,” Foods, vol. 10, no. 11, p. 2827, Nov. 2021, doi: 10.3390/foods10112827.

A. Samoggia and B. Riedel, “Consumers’ Perceptions of Coffee Health Benefits and Motives for Coffee Consumption and Purchasing,” Nutrients, vol. 11, no. 3, p. 653, Mar. 2019, doi: 10.3390/nu11030653.

WHO, “Global action plan for the prevention and control of noncommunicable diseases 2013-2020.,” World Heal. Organ., p. 102, 2013, [Online]. Available at: https://www.who.int/publications/i/item/9789241506236.

M. Hu and B. Liu, “Mining and summarizing customer reviews,” in Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, Aug. 2004, pp. 168–177, doi: 10.1145/1014052.1014073.

G. Uddin and F. Khomh, “Automatic Mining of Opinions Expressed About APIs in Stack Overflow,” IEEE Trans. Softw. Eng., vol. 47, no. 3, pp. 522–559, Mar. 2021, doi: 10.1109/TSE.2019.2900245.

M. Imran, P. Mitra, and C. Castillo, “Twitter as a Lifeline: Human-annotated Twitter Corpora for NLP of Crisis-related Messages,” Proc. 10th Int. Conf. Lang. Resour. Eval. Lr. 2016, pp. 1638–1643, May 2016, Accessed: Jun. 22, 2023. [Online]. Available: https://arxiv.org/abs/1605.05894v2.

A. O. P. Dewi, A. Isnaini, and M. F. Lestari, “An Analysis of the post-COVID-19 Information Distribution on Social Media,” E3S Web Conf., vol. 359, p. 02037, Oct. 2022, doi: 10.1051/e3sconf/202235902037.

N. Öztürk and S. Ayvaz, “Sentiment analysis on Twitter: A text mining approach to the Syrian refugee crisis,” Telemat. Informatics, vol. 35, no. 1, pp. 136–147, Apr. 2018, doi: 10.1016/j.tele.2017.10.006.

C. J. Rameshbhai and J. Paulose, “Opinion mining on newspaper headlines using SVM and NLP,” Int. J. Electr. Comput. Eng., vol. 9, no. 3, p. 2152, Jun. 2019, doi: 10.11591/ijece.v9i3.pp2152-2163.

S. Sendari, I. A. E. Zaeni, D. C. Lestari, and H. P. Hariyadi, “Opinion Analysis for Emotional Classification on Emoji Tweets using the Naïve Bayes Algorithm,” Knowl. Eng. Data Sci., vol. 3, no. 1, pp. 50–59, Aug. 2020, doi: 10.17977/um018v3i12020p50-59.

Z. Ding, Z. Li, and C. Fan, “Building energy savings: Analysis of research trends based on text mining,” Autom. Constr., vol. 96, pp. 398–410, Dec. 2018, doi: 10.1016/j.autcon.2018.10.008.

M. Bjaoui, H. Sakly, M. Said, N. Kraiem, and M. S. Bouhlel, “Depth insight for data scientist with RapidMiner « an innovative tool for AI and big data towards medical applications»,” in Proceedings of the 2nd International Conference on Digital Tools & Uses Congress, Oct. 2020, pp. 1–6, doi: 10.1145/3423603.3424059.

P. Ristoski, C. Bizer, and H. Paulheim, “Mining the Web of Linked Data with RapidMiner,” J. Web Semant., vol. 35, pp. 142–151, Dec. 2015, doi: 10.1016/j.websem.2015.06.004.

Z. E. Rasjid and R. Setiawan, “Performance Comparison and Optimization of Text Document Classification using k-NN and Naïve Bayes Classification Techniques,” Procedia Comput. Sci., vol. 116, pp. 107–112, Jan. 2017, doi: 10.1016/j.procs.2017.10.017.

K. Yadav and R. Thareja, “Comparing the Performance of Naive Bayes And Decision Tree Classification Using R,” Int. J. Intell. Syst. Appl., vol. 11, no. 12, pp. 11–19, Dec. 2019, doi: 10.5815/ijisa.2019.12.02.

M. Singh, M. Wasim Bhatt, H. S. Bedi, and U. Mishra, “WITHDRAWN: Performance of bernoulli’s naive bayes classifier in the detection of fake news,” in Materials Today: Proceedings, Dec. 2020, p. 1, doi: 10.1016/j.matpr.2020.10.896.

RapidMiner, RapidMiner Studi o Manual, p.116, 2012. [Online]. Available at: https://docs.rapidminer.com/downloads/RapidMiner-v6-user-manual.pdf.

Twitter, “Twitter Polls – how to create and how to vote.”. [Online]. Available at: https://help.twitter.com/en/using-twitter/twitter-polls.