Journal of Intelligent Marketing Management

Journal of Intelligent Marketing Management

The Role of Team Identification and Sentiment Analysis of Iranian Football Clubs’ Fans in Twitter Social Media with Natural Language Processing

Document Type : Excerpt from doctoral thesis

Authors
Leila Heidari 1
Najaf Aghaei 2
Hossein Akbari Yazdi 2
1 Faculty of Physical Education and Sports Sciences, Kharazmi University, Tehran, Iran
2 Department of Sport Management, Faculty of Physical Education and Sports Sciences, Kharazmi University, Tehran, Iran
JABM.3.2.15564.35887879085849695
Abstract
Introduction: Natural Language Processing (NLP) is a vital subfield of artificial intelligence that helps computers understand and interpret human language. The purpose of this research was to identify and understand the sentiments expressed by football fans on Twitter, especially after special events such as the Premier League, and to present a model based on their team identification level.

Methods: The current research is applied research in terms of its purpose and descriptive-analytical research in terms of its nature. The statistical population included all the tweets generated on Twitter by the fans of the clubs present in the 2021/22 Iranian Premier Football League. Therefore, 5560 tweets were collected after 120 games of the second-half season of the Premier Football League. Special Lexicon and sentiment classifiers based on artificial intelligence (VADER dictionary) were used in a Python environment as a sentiment analysis tool. A Regression model was used to predict fans'' sentiments.

Results: The results of natural language processing showed that positive sentiments were the most expressed emotions by fans. The regression model predicted fans'' sentiments based on factors such as the level of team identification and the result of winning and losing the game, and the conceptual model of the research was confirmed.

Conclusion: This study can be used by media and marketing managers of teams who seek a deeper understanding of the emotional dynamics of football fans.
Keywords
artificial intelligence
data mining
premier league
user-generated content

Subjects

Akhavan, N. (2013). Electronic Iran-The Cultural Politics of an Online Evolution (p. 168). Rutgers University Press.
Aloufi, S., Alzamzami, F., Hoda, M., & El Saddik, A. (2018, April). Soccer fans sentiment through the eye of big data: The UEFA champions league as a case study. In 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) (pp. 244-250). IEEE.
Atghia, N., & Nazarian, A. (2023). Economic sustainability: a solution to the financial problems of football clubs. Sport, Business and Management: An International Journal, 14(1), 56-79.
Babac, M. B., & Podobnik, V. (2016). A sentiment analysis of who participates, how and why, at social media sport websites: how differently men and women write about football. Online Information Review.
Burton, N. (2019). Exploring user sentiment towards sponsorship and ambush marketing. International Journal of Sports Marketing and Sponsorship, 20(4), 583-602.
Byrne, E., & Corney, D. (2014). Sweet FA: Sentiment, Swearing and Soccer. In SoMuS@ ICMR.
Chang, Y. (2019). Spectators’ emotional responses in tweets during the Super Bowl 50 game. Sport Management Review, 22(3), 348-362.
Chin, C. Y., & Huang, W. Y. (2023). Discovering fans and anti-fans among social media users based on their emotional reactions and comments. Journal of Information Science.
Chmait, N., & Westerbeek, H. (2021). Artificial Intelligence and Machine Learning in Sport Research: An Introduction for Non-data Scientists. Frontiers in Sports and Active Living, 3.
Eskandari, Z. T. (2022). ‘We support football in our heart’: female football fandom in Iran. Soccer & Society, 23(3), 258-270.
Fan, M., Billings, A., Zhu, X., & Yu, P. (2020). Twitter-based BIRGing: Big Data analysis of English national team fans during the 2018 FIFA World Cup. Communication & Sport, 8(3), 317-345.
Golchin, SH. (2020). Predicting the results of soccer games using machine learning methods. (Master's thesis, Tarbiat Modares University). [In Persian].
Hegde, S. U., Zaiba, A. S., & Nagaraju, Y. (2021). Hybrid cnn-lstm model with glove word vector for sentiment analysis on football specific tweets. In 2021 international conference on advances in electrical, computing, communication and sustainable technologies (ICAECT) 1-8. IEEE.
Jackson, J. R. (2019). Toxic Culture: An Emotion and Sentiment Analysis of College Football Fans in Relation to Controversy and Win-Loss Records. (Master's thesis, Louisiana State University and Agricultural & Mechanical College).
Jahanfar, H. (2021). Artificial Intelligence in Marketing: A Systematic Review and Future Research Path. New Business Attitudes, 2(4), 1-14. [In Persian].
Javani, V., Ehsani, M., Amiry, M., & Kozechiyan, H. (2013). The study of fans’ brand loyalty in Iranian professional football league. International Journal of Research in Business and Social Science (2147-4478), 2(2), 38-46.
Jensen, J. A., Turner, B. A., James, J., McEvoy, C., Seifried, C., Delia, E., Greenwell, T.C., Ross, S. & Walsh, P. (2016). Forty years of BIRGing: New perspectives on Cialdini’s seminal studies. Journal of Sport Management, 30(2), 149-161.
Khademian Hashemi, N. (2019). Improving the management of sports teams using machine learning. (Master's thesis in computer, Khatam University). [In Persian].
Kolbinger, O., Knopp, M. (2020). Video kills the sentiment—exploring fans’ reception of the video    assistant referee in the English premier league using Twitter data. PloS one, 15(12), e0242728.
Li, Y., & Xie, Y. (2020). Is a picture worth a thousand words? An empirical study of image content and social media engagement. Journal of Marketing Research, 57(1), 1-19.
Lu, C. J., Lee, T. S., Wang, C. C., & Chen, W. J. (2021). Improving Sports Outcome Prediction Process Using Integrating Adaptive Weighted Features and Machine Learning Techniques. Processes, 9(9), 1563.
Mahboob, K., Ali, F., & Nizami, H. (2019). Sentiment analysis of RSS feeds on sports news–a case study. International Journal of Information Technology and Computer Science, 11(12), 19-29.
Mansouri, H., Rezaei, Z., Rozfarakh, A., & Abdollahi, H. M. (2022). The relationship between team social responsibility and patronage intentions football premier league fans: The moderator role of team identity. Sport Psychology Studies, 10(38), 187-206.
Mamo, Y., Su, Y., & Andrew, D. P. (2021). The transformative impact of big data applications in sport marketing: current and future directions. International Journal of Sports Marketing and Sponsorship.
Miklosik, A., Kuchta, M., Evans, N., & Zak, S. (2019). Towards the adoption of machine learning-based analytical tools in digital marketing. Ieee Access, 7, 85705-85718.  
Mileski, M., Campos, D. P., Carvalho, L. F., & Mantovani, R. G. (2024). Sentiment Analysis in Social Networks during the 2021 and 2022 Formula 1 Seasons: A Study Using Natural Language Processing on Twitter. Anais do Computer on the Beach, 15, 236-243
Mińska-Struzik, E., Jankowska, B., & Ekonomiczny, U. (Eds.). (2021). toward the" new Normal" After Covid-19: A Post-transition Economy Perspective. PUEB Press. Poznań University of Economics and Business.
Mohammadi, S. (2020). State control and the online contestation of Iranian female spectators and activists. Communication & Sport, 8(4-5), 651-667.
Mohammadkazemi, R., Kardar, S., & Pouriz, M. (2020). The Effect of Use of Text Messaging on Soccer Fans’ Behavior (The Case of Iranian Professional League-Persian Gulf League). Association of Marketing Theory and Practice Proceedings.
Mousavi, S. M., Amiri Aghdaie, S. F. (2020). Marketing Research in the Fourth Industrial Revolution, Using ‘Big Data’ Analytics and ‘Machine Learning’ to Provide Value to the Customer. New Markeing Research, 10(4), 37-54. [In Persian].
Murray, J. (2019). Fan Identification in Professional Sport. St. John Fisher College.
Netzer, O., Feldman, R., Goldenberg, J., & Fresko, M. (2012). Mine your own business: Market-structure surveillance through text mining. Marketing Science, 31(3), 521-543.
Nurcahyawati, V., & Mustaffa, Z. (2023). Vader Lexicon and Support Vector Machine Algorithm to Detect Customer Sentiment Orientation. Journal of Information Systems Engineering & Business Intelligence, 9(1).
Panchal, D., Mehta, M., Mishra, A., Ghole, S., & Dandge, S. (2022). Sentiment Analysis Using Natural Language Processing. International Journal for Research in Applied Science and Engineering Technology, 10(5), 2262-2266.
Pegoraro, A. (2014). Twitter as disruptive innovation in sport communication. Communication & Sport, 2(2), 132-137.
Pottala, M. (2018). Artificial Intelligence: Artificial Intelligence in Sports. (Master's thesis, Centria University of applied science).
Price, J., Farrington, N., & Hall, L. (2013). Changing the game? The impact of Twitter on relationships between football clubs, supporters and the sports media. Soccer & Society, 14(4), 446-461.
Rahimizadeh, M., Sajadi, S. N., Goodarzi, M., & Ghamati, H. (2012). A comparison of online marketing and interaction with fans through official website of football clubs in Iran, Asia and Europe. International Research Journal of Applied and Basic Sciences, 3(5), 1065-1071.
Rahman, M. M., Rosenberger III, P. J., Yun, J. H., de Oliveira, M. J., & Köcher, S. (2024). Keeping the ball rolling: using the SOR framework to investigate the determinants of football fan loyalty. Asia Pacific Journal of Marketing and Logistics, 36(1), 122-147.
Roma, P., & Aloini, D. (2019). How does brand-related user-generated content differ across social media? Evidence reloaded. Journal of Business Research, 96, 322-339.
Saha, S., Showrov, M. I. H., Rahman, M. M., & Majumder, M. Z. H. (2022). Vader vs. Bert: A comparative performance analysis for sentiment on coronavirus outbreak. In International Conference on Machine Intelligence and Emerging Technologies (371-385). Cham: Springer Nature Switzerland.
Seilsepour, A., Ravanmehr, R., & Sima, H. R. (2019). 2016 Olympic Games on Twitter: Sentiment Analysis of Sports Fans Tweets using Big Data Framework. Journal of Advances in Computer Engineering and Technology, 5(3), 143-160.
Semati, M. (Ed.). (2007). Media, culture and society in Iran: living with globalization and the Islamic state (Vol. 5). Routledge.
Tunca, S., Sezen, B., & Balcioglu, Y. S. (2023). Content and sentiment analysis of the New York Times   Coronavirus (2019-nCOV) articles with natural language processing (NLP) and Leximancer. Electronics, 12(9).
Venkatesh, K. C., Nagaraj, Y., & Swetha, S. (2021). Comprehensive Analysis of Classifier to Identify Sentiment in Football Specific Tweets. In ICASISET 2020: Proceedings of the First International Conference on Advanced Scientific Innovation in Science, Engineering and Technology, ICASISET 2020, 16-17 May 2020, Chennai, India (283). European Alliance for Innovation.
Wunderlich, F., & Memmert, D. (2020). Innovative approaches in sports science—lexicon-based sentiment analysis as a tool to analyze sports-related Twitter communication. Applied sciences, 10(2), 431.
Yan, G., Steller, D., Watanabe, N. M., & Popp, N. (2018). What determines user-generated content creation of college football? A big-data analysis of structural influences. International Journal of Sport Communication, 11(2), 219-240.
Yan, S. A., & Mawhorter, P. (2023). Twitter sentiment analysis: fan engagement in esports matches. In Proc. 13th IADIS Int. Conf. ICT, Soc. Hum. Beings 2020, ICT 2020 (257-261).

  • Receive Date 15 September 2024
  • Revise Date 05 October 2024
  • Accept Date 06 October 2024