DOI : https://doi.org/10.62527/ijasce.6.2.211

Predicting Customer Sentiment in Social Media Interactions: Analyzing Amazon Help Twitter Conversations Using Machine Learning

Md Arif (1), Mehedi Hasan (2), Sarder Abdulla Al Shiam (3), Md Parvez Ahmed (4), Mazharul Islam Tusher (5), Md Zikar Hossan (6), Aftab Uddin (7), Suniti Devi (8), Md Habibur Rahman (9), Md Zinnat Ali Biswas (10), Touhid Imam (11)
(1) Department of Management Science and Quantitative Methods, Gannon University, United States
(2) Department of Management -Business Analytics, St Francis College, United States
(3) Department of Management -Business Analytics, St Francis College, United States
(4) Master of Science in Information Technology, Washington University of Science and Technology, United States
(5) Department Of Computer Science, Monroe College, New Rochelle, New York, United States
(6) Department of Business Administration, International American University, Los Angeles, California, United States
(7) Fox School of Business & Management, Temple University, United States
(8) Department of Management Science and Quantitative Methods, Gannon University, United States
(9) Department of Business Administration, International American University, Los Angeles, California, United States
(10) MA in Education, University of South Wales, Wales, United Kingdom
(11) Department of Computer Science, University of South Dakota, Vermillion, South Dakota, United States
Fulltext View | Download
How to cite (IJASEIT) :
Arif, M., Hasan, M., Al Shiam, S. A., Ahmed, M. P., Tusher, M. I., Hossan, M. Z., … Imam, T. (2024). Predicting Customer Sentiment in Social Media Interactions: Analyzing Amazon Help Twitter Conversations Using Machine Learning. International Journal of Advanced Science Computing and Engineering, 6(2), 52–56. https://doi.org/10.62527/ijasce.6.2.211
Citation Format :

Social media platforms, particularly Twitter, have become essential sources of data for various applications, including marketing and customer service. This study focuses on analyzing customer interactions with Amazon's official support account, "@AmazonHelp," to understand and predict changes in customer sentiment during these interactions. Using the Twitter API, we extracted English-language tweets mentioning "@AmazonHelp," pre-processed the data, and categorized conversations to facilitate analysis. The primary objectives were to classify changes in customer sentiment and predict the overall sentiment change based on initial sentiment. We conducted experiments using multiple machines learning algorithms, including K-nearest neighbor, Naive Bayes, Artificial Neural Network, Bayes Net, Support Vector Machine, Logistic Regression, and Bagging with RepTree. Our dataset comprised over 6,500 conversations, filtered to include those with four or more tweets. Results indicated that K-nearest neighbor and Support Vector Machine offered the best balance between accuracy and F-measure, while Bagging with RepTree achieved the highest accuracy but had a lower F-measure. This study demonstrates the potential of integrating sentiment analysis and machine learning to effectively predict customer sentiment in social networks, providing valuable insights for improving customer engagement strategies.

A. K. Dwivedi, “Performance evaluation of different machine learning techniques for prediction of heart disease,” Neural Comput. Appl., vol. 29, no. 10, pp. 685–693, Sep. 2016, doi: 10.1007/s00521-016-2604-1.

R. Aswani, A. K. Kar, P. V. Ilavarasan, and Y. K. Dwivedi, “Search engine marketing is not all gold: Insights from Twitter and Seoclerks,” Int. J. Inf. Manage., vol. 81, pp. 107–116, 2018, doi:10.1016/j.ijinfomgt.2017.07.005.

S. Park, J. Cho, K. Park, and H. Shin, “Customer sentiment analysis with more sensibility,” Eng. Appl. Artif. Intell., vol. 104, p. 104356, 2021, doi: 10.1016/j.engappai.2021.104356.

D. Gräbner, M. Zanker, G. Fliedl, and M. Fuchs, “Classification of customer reviews based on sentiment analysis,” in Inf. Commun. Technol. Tour. 2012, Vienna, Austria: Springer, 2012, pp. 460–470, doi: 10.1007/978-3-7091-1142-0_40.

S. Yi and X. Liu, “Machine learning based customer sentiment analysis for recommending shoppers, shops based on customers’ review,” Complex Intell. Syst., vol. 6, no. 3, pp. 621–634, 2020, doi:10.1007/s40747-020-00155-2.

O. Grljević and Z. Bošnjak, “Sentiment analysis of customer data,” Strategic Manage. – Int. J. Strategic Manage. Decision Support Syst. Strategic Manage., vol. 23, no. 3, 2018, doi:10.5937/StraMan1803038G.

F. Sudirjo, K. Diantoro, J. A. Al-Gasawneh, H. K. Azzaakiyyah, and A. M. A. Ausat, “Application of ChatGPT in improving customer sentiment analysis for businesses,” J. Teknol. Syst. Inf. Bisnis, vol. 5, no. 3, pp. 283–288, 2023, doi: 10.47233/jteksis.v5i3.871.

V. Sharma and T. Manocha, “Comparative analysis of online fashion retailers using customer sentiment analysis on Twitter,” in Proc. Int. Conf. Innov. Comput. Commun. (ICICC), Feb. 2022, doi:10.2139/ssrn.4361107.

S. Jumabek, K. Tuwelbay, A. Allabay, and B. Geldibayev, “Current trends in the formation of mathematical terminology on an online platform,” Int. J. Adv. Sci. Comput. Eng., vol. 6, no. 1, pp. 7–12, 2024, doi: 10.62527/ijasce.6.1.188.

Z. Singla, S. Randhawa, and S. Jain, “Sentiment analysis of customer product reviews using machine learning,” in Proc. Int. Conf. Intell. Comput. Control (I2C2), Jun. 2017, pp. 1–5, doi:10.1109/I2C2.2017.8321910.

M. S. Hossain and M. F. Rahman, “Customer sentiment analysis and prediction of insurance products’ reviews using machine learning approaches,” FIIB Bus. Rev., vol. 12, no. 4, pp. 386–402, 2023, doi:10.1177/23197145221115793.

Z. A. Dieksona et al., “Sentiment analysis for customer review: Case study of Traveloka,” Procedia Comput. Sci., vol. 216, pp. 682–690, 2023, doi: 10.1016/j.procs.2022.12.184.

A. R. Prananda and I. Thalib, “Sentiment analysis for customer review: Case study of GO-JEK expansion,” J. Inf. Syst. Eng. Bus. Intell., vol. 6, no. 1, p. 1, 2020, doi: 10.20473/jisebi.6.1.1-8.

A. Adak, B. Pradhan, and N. Shukla, “Sentiment analysis of customer reviews of food delivery services using deep learning and explainable artificial intelligence: Systematic review,” Foods, vol. 11, no. 10, p. 1500, 2022, doi: 10.3390/foods11101500.

S. Moghaddam, “Beyond sentiment analysis: Mining defects and improvements from customer feedback,” in Adv. Inf. Retr., 37th Eur. Conf. IR Res. (ECIR), Vienna, Austria, Mar.–Apr. 2015, pp. 400–410, doi: 10.1007/978-3-319-16354-3_44.

A. Mardiah, D. Defni, A. H. Lestari, J. Junaldi, and T. Ritmi, “Classification of population data of Nagari based on economic level using the K-nearest neighbor method,” Int. J. Adv. Sci. Comput. Eng., vol. 6, no. 1, pp. 33–37, 2024, doi: 10.62527/ijasce.6.1.191.

M. A. Rahman et al., “Advancements in retail price optimization: Leveraging machine learning models for profitability and competitiveness,” J. Bus. Manage. Stud., vol. 6, no. 3, pp. 103–110, 2024, doi: 10.32996/jbms.2024.6.3.11.

L. Fitri, D. Lestari, and F. Nurul, “Measuring public satisfaction with data services using sentiment analysis on Twitter,” in Proc. Int. Conf. Data Softw. Eng. (ICoDSE), 2018.

N. F. Ibrahim, X. Wang, and H. Bourne, “Exploring the effect of user engagement in online brand communities: Evidence from Twitter,” Comput. Human Behav., vol. 72, pp. 321–338, 2017, doi:10.1016/j.chb.2017.03.005.

H. S. Saragih and A. S. Girsang, “Customer engagement analysis on social media using sentiment mining: A case study on online transportation companies in Indonesia,” J. Theor. Appl. Inf. Technol., vol. 95, no. 7, 2017.

S. Al-Otaibi, M. Ykhlef, and N. Aljohani, “A tweet advisor system for measuring customer satisfaction using sentiment analysis,” J. King Saud Univ. – Comput. Inf. Sci., 2018.

H. Shirdastian, M. Laroche, and M.-O. Richard, “Using big data analytics to study brand authenticity sentiments: The case of Starbucks on Twitter,” Int. J. Inf. Manage., vol. 48, pp. 291–307, Oct. 2019, doi:10.1016/j.ijinfomgt.2017.09.007.

M. S. Rana, M. M. Hossain, R. M. Jewel, and M. R. Islam, “Evaluating customers satisfaction of electronic banking: An empirical study in Bangladesh,” SIJ Trans. Ind. Financial Bus. Manage., vol. 5, no. 3, pp. 7–12, 2017, doi: 10.9756/SIJIFBM/V5I3/05040160101.

B. P. Ghosh et al., “Deep learning in stock market forecasting: Comparative analysis of neural network architectures across NSE and NYSE,” J. Comput. Sci. Technol. Stud., vol. 6, no. 1, pp. 68–75, 2024, doi: 10.32996/jcsts.2024.6.1.8.

M. S. Chowdhury et al., “Deep learning models for stock market forecasting: A comprehensive comparative analysis,” J. Bus. Manage. Stud., vol. 6, no. 2, pp. 95–99, 2024, doi: 10.32996/jbms.2024.6.2.9.

M. Bhuiyan, “Carbon footprint measurement and mitigation using AI,” SSRN Electron. J., 2024, doi: 10.2139/ssrn.4746446.

M. A. S. Mozumder et al., “Revolutionizing organizational decision-making for banking sector: A machine learning approach with CNNs in business intelligence and management,” J. Bus. Manage. Stud., vol. 6, no. 3, pp. 111–118, 2024, doi: 10.32996/jbms.2024.6.3.12.

O. Hammad, M. R. Rahman, N. Clements, S. Mishra, S. Miller, and E. Sullivan, “PureNav: A personalized navigation service for environmental justice communities impacted by planned disruptions,” in Proc. Int. Conf. Adv. Social Netw. Anal. Mining (ASONAM), Nov. 2023, pp. 56–63, doi: 10.1145/3625007.3627512.