Decoding the impact of emotions: machine learning insights on user interests in social networks

Henda Ouertani

Abstract


This study investigates the correlation that exists between users' emotional states and their expressed interests in the context of social network. By utilizing cutting-edge machine learning methods, we set out to reveal the connections that underpin user behavior.  Saudi Arabia is among the nations with the highest usage of X (previously Twitter). Several studies used the analysis of English tweets to determine the topic of interest and whether the user is passive or active. Studies that examined user interaction to ascertain interest have been conducted with reference to Arabic tweets. There are, however, few studies that track how an external factor, like emotions, affects interest over time. To investigate the relationship between interest and emotion, we used two models of supervised algorithms:  Support Vector Machines (SVM) and Naïve Bayes. Once the topic of interests and emotions were classified, we discovered that the topic of interest had a higher accuracy than the emotion classifier because it had been applied to a sample of dataset. Furthermore, the SVM outperformed Naïve Bayes in terms of accuracy for classifying both topics of interest and emotions. Finally, the result indicates that the interests for specific user change over time according to the emotions

Full Text:

PDF

References


A. Abdel-Hafez, Y. Xu, A Survey of User Modelling in Social Media Websites, Computer and Information Science 30 (2022), no. 3, 5-20.

N. Reimann, Twitter Hemorrhaging Its Most Active Users, Report Says, https://www.forbes.com/sites/nicholasreimann/2022/10/25/twitter-hemorrhaging-its-mostactive-users-report-says/?sh=e34ed5e6e5e1

Statista Search Department, Countries with the most X/Twitter users 2023. Statista, https://www.statista.com/statistics/242606/number-of-active-twitter-users-in-selectedcountries

(Accessed September 13th, 2023.)

T.S. Sai Kumar, K. Arunaggiri Pandian, S. Thabasum Aara, K. Nagendra Pandian, A Reliable Technique for Sentiment Analysis on Tweets via Machine Learning and BERT, Asian Conference on Innovation in Technology (ASIANCON) 27 August (2021).

R. Abbasi, G. Rehman, J. Lee, F. M. Riaz, B. Luo, Discovering temporal user interest on twitter by using semantic based dynamic interest finding model (TUT), 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chengdu, China, 2017, 743-747. DOI:10.1109/ITNEC.2017.8284832

N. Nimita Mangal, S. Sartaj Kanwar, R. Rajdeep Niyogi, Prediction of Twitter Users' Interest Based on Tweets, In: (J. Mandal, S. Satapathy, M. Sanyal, V. Bhateja (Eds.)) Proceedings of the First International Conference on Intelligent Computing and Communication. Advances in Intelligent Systems and Computing, 458 (2016), pp. 167-175, Springer, Singapore. DOI:10.1007/978-981-10-2035-3_18

Ma. Cebral-Loureda, A. Hernandez-Baqueiro, E. Tamés-Munoz, A text mining analysis of human flourishing on Twitter, Scientific reports 13 (2023), Article number 3403.

A.P. Logan, P.M. LaCasse, B. Lunday, Social network analysis of Twitter interactions: a directed multilayer network approach, Soc. Netw. Anal. Min. 13 (2023), Article number 65.

M.A. Al-Hagery, M.A.Alassaf, F.M. Al-kharboush, Exploration of the best performance method of emotions classification for arabic tweets, Indonesian Journal of Electrical Engineering and Computer Science 19 (2020), no. 2, Article number 1010.

M. Abdullah, M. AlMasawa, I. Makki, M. Alsolmi, S. Mahrous, Emotions extraction from Arabic tweets, International Journal of Computers and Applications 42 (2020), no. 7, 661-675.

M.N.M. Shelke, Approaches of Emotion Detection from Text, International Journal of Computer Science and Information Technology 2 (2014), 123-128.

S.B. Kotsiantis, Supervised Machine Learning: A Review of Classification, Informatica (Slovenia) 31 (2007), 249-268.

I.D. Wood, S. Ruder, Emoji as Emotion Tags for Tweets, Proceedings of LREC, Workshop, Emotion and Sentiment Analysis (2016), 76-79.

P. Ekman, An argument for basic emotions, Cognition and Emotion 6 (1992), no. 3-4, 169-200.

M. Ikonomakis, S. Kotsiantis, V. Tampakas, Text Classification Using Machine Learning Techniques, WSEAS TRANSACTIONS on COMPUTERS 4 (2005), 966-074.

sklearn.svm.LinearSVC - scikit-learn 0.20.3 documentation. https://scikitlearn.org/stable/modules/generated/sklearn.svm.LinearSVC.html

sklearn.naive-bayes.MultinomialNB - scikit-learn 0.20.3 documentation. https://scikitlearn.org/stable/modules/generated/sklearn.naive-bayes.MultinomialNB.html

D. Kim, D. Seo, S. Cho, P. Kang, Multi-co-training for document classification using various document representations: TF-IDF, LDA, and Doc2Vec, Information Sciences 477 (2019), 15-29.




DOI: https://doi.org/10.52846/ami.v50i2.1874