Abstract Instagram is one of the most popular social networks for marketing. Predicting the popularity of a post on Instagram is important to determine the influence of a user for marketing purposes. There were studies on popularity prediction on Instagram using various features and datasets. However, they haven't fully addressed the challenge of data variability of the global dataset, where they either used local datasets or discretized output. This research compared several regression techniques to predict the Engagement Rate (ER) of posts using a global dataset. The prediction model, coupled with the results of the popularity trend analysis, will have more utility for a larger audience compared to existing studies. The features were extracted from hashtags, image analysis, and user history. It was found that image quality, posting time, and type of image highly impact ER. The prediction accuracy reached up to 73.1% using the Support Vector Regression (SVR), which is higher than previous studies on a global dataset. User history features were useful in the prediction since the data showed a high variability of ER if compared to a local dataset. The added manual image assessment values were also among the top predictors.

References

[1] Almgren K., Lee J., and Kim M., “Predicting the Future Popularity of Images on Social Networks,” in Proceedings of The 3rd Multidisciplinary International Social Networks Conference, Union, pp. 1-6, 2016.

[2] Bae Y. and Lee H., “Sentiment Analysis of Twitter Audiences: Measuring the Positive or Negative Influence of Popular Twitterers,” Journal of the American Society for Information Science and Technology, vol. 63, no. 12, pp. 2521-2535, 2012.

[3] Berger J. and Milkman K., “What Makes Online Content Viral,” Journal of Marketing Research, vol. 49, no. 2, pp. 192-205, 2012.

[4] Cakmak K., Cikrikcioglu I., and Demiralp O., “The Causal Determinants of Popularity in Instagram,” Technical Report, 2017.

[5] Code M., Instagram, Social Media, and The “Like”: Exploring Virtual Identity’s Role in 21st Century Students’ New Socialization Experience, M.S Theses, Brock University, 2015.

[6] De S., Maity A., Shitole S., Goel V., and Bhattacharya A., “Predicting the Popularity of Instagram Posts for a Lifestyle Magazine Using Deep Learning,” in Proceedings of 2nd IEEE International Conference on Communication Systems, Computing and Information Technology Applications, Mumbai, pp. 174-177, 2017.

[7] Ding K., Ma K., and Wang S., “Intrinsic Image Popularity Assessment,” in Proceedings of the 27th ACM International Conference on Multimedia, Nice, pp. 1979-1987, 2019.

[8] Feehan B., “Social Media Industry Benchmark Report.” https://www.rivaliq.com/blog/2019- social-media-benchmark-report/, Last Visited, 2020.

[9] Gelli F., Uricchio T., Bertini M., Del Bimbo A., and Fu Chang S., “Image Popularity Prediction in Social Media Using Sentiment and Context Features,” in Proceedings of the 23rd ACM International Conference on Multimedia, New York, pp. 907-910, 2015.

[10] Iqbal M., “Instagram Revenue and Usage Statistics.” https://www.businessofapps.com/data/instagram- statistics/, Last Visited, 2020.

[11] Joshi D., Datta D., Fedorovskaya E., Lu X., Luong Q., Wang J., Li J., and Luo J., On Aesthetics and Emotions in Scene Images: A Computational Perspective, MIT Press Scholarship Online, 2014.

[12] Khalid N., Jayasainan S., and Hassim N., “Social Media Influencers-Shaping Consumption Culture Among Malaysian Youth,” International Conference on Humanities and Social Sciences, Kuala Lumpur, pp. 1-12, 2018.

[13] Lennan C., Nguyen H., and Tran D., Image Quality Assessment, https://github.com/idealo/image-quality Assessment, Last Visited, 2019.

[14] Mazloom M., Rietveld R., Rudinac S., Worring M., and Dolen W., “Multimodal Popularity Prediction of Brand-Related Social Media Posts,” in Proceedings of the 24th ACM international Conference on Multimedia, Amsterdam, pp. 197- 201, 2016.

[15] Nandagiri V. and Philip L., “Impact of Influencers from Instagram and Youtube on Their Followers,” International Journal of Multidisciplinary Research and Modern Education, vol. 4, no. 1, pp. 2454-6119, 2018.

[16] Paul K., “Instagram tests hiding how many people like a post. That has influencers worried.” https://www.theguardian.com/technology/2019/n ov/15/instagram-likes-influencers-social-media, Last Visited, 2019.

[17] Qian C., Tang, J., Penza M., and Ferri C., “Instagram Popularity Prediction via Neural Networks and Regression Analysis,” pp. 2561- 2570, 2017.

[18] Saxton G. and Waters R., “What do Stakeholders Like on Facebook? Examining Public Reactions to Nonprofit Organizations’ Informational, Promotional, and Community-Building Messages,” Journal of Public Relations Research, vol. 26, no. 3, pp. 280-299, 2014.

[19] Southern M., “Instagram Has 1 Billion Monthly Users, Now the Fastest Growing Social Network.” https://www.searchenginejournal.com/instagram- 1-billion-monthly-users-now-fastest-growing- social-network/258127/, Last Visited, 2019.

[20] Statista., “Most Famous Social Network Sites Worldwide as of, Ranked By Number Of Active Users (in millions),” https://www.statista.com/statistics/272014/global -social-networks-ranked-by-number-of-users/, Last Visited, 2018.

[21] Talebi H. and Milanfar P., “Nima: Neural Image Assessment,” IEEE Transactions on Image Processing, vol. 27, no. 8, pp. 3998-4011, 2018.

[22] Top-Hashtags, Top 100 HashTags on Instagram. https://top-hashtags.com/instagram/, Last Visited, 2020.

[23] Trzcinski T. and Rokita P., “Predicting popularity of Online Videos Using Support Vector Regression,” IEEE Transactions on Multimedia, vol. 19, no. 11, pp. 2561-2570, 2017.

[24] Vorhaus J., “Instagram Influencer Rates,” http://blog.influence.co/instagram-influencer- rates/, Last Visited, 2019.

[25] Windt G., Artistic Creativity: Transforming Sorrow Into Beauty, Truth and Art, M.S Theses, 94 The International Arab Journal of Information Technology, Vol. 18, No. 1, January 2021 Simon Fraser University, 2004.

[26] Zhang X., Sun S., and Zhang K., “A New Hybrid Improved Method for Measuring Concept Semantic Similarity in WordNet,” The International Arab Journal of Information Technology, vol. 17, no. 4, pp. 433-439, 2020.

[27] Zhang Z., Zhou Z., Li J., Chen T., and Luo J., “How to Become Instagram Famous: Post Popularity Prediction with Dual-Attention,” in Proceedings of IEEE International Conference on Big Data , Seattle, pp. 2383-2392, 2018.

[28] Zohourian A., Sajedi H., and Yavary A., “Popularity Prediction of Images and Videos on Instagram,” in Proceedings of 4th International Conference on Web Research, Tehran, pp. 111- 117, 2018. Kristo Radion Purba is currently a computer science PhD student at Taylor’s University Malaysia, starting from 2018. His research interests are in artificial intelligence, machine learning, and social network influence maximization. Prior to joining Taylor’s, he was an informatics lecturer at Petra Christian University, Indonesia for 4 years (2014-2018), and also a contracted programmer at EHS (Environment, Health and Safety) department at PT. HM. Sampoerna, Tbk, Indonesia (2013-2017). He is also an active mobile apps, games, websites developer since 2008 until now. David Asirvatham Dr. David Asirvatham is currently the Head for the School of Computing and IT, Taylor’s University. Prior to this, he was the Director for the Centre of Information Technology at University of Malaya. He has held numerous posts such the Associate Dean for Faculty of Information Technology (Multimedia University), Project Manager for the Multimedia and IT Infrastructure Development for a university campus (US$14 million), Finance Committee for Multimedia University, SAP Advisory Council, Consultant for e- University Project and many more. Dr. David completed his Ph.D. from Multimedia University, M.Sc. (Digital System) from Brunel University (U.K.), and B.Sc. (Hons) Ed. and Post-Graduate Diploma in Computer Science from University of Malaya. He has been lecturing as well as managing ICT projects for the past 25 years. His area of expertise will include Neural Network, E-Learning, ICT Project Management, Multimedia Content Development and recently he has done some work on Big Data analytics. Raja Kumar Murugesan Dr Raja Kumar Murugesan is an Associate Professor of Computer Science, and Head of Research for the Faculty of Innovation and Technology at Taylor’s University, Malaysia. He has a PhD in Advanced Computer Networks from the Universiti Sains Malaysia, and has over 28 years’ experience as an educator. His research interests include IPv6, and Future Internet, Internet Governance, Computer Networks, Network Security, IoT, Blockchain, Machine Learning, and Affective Computing. He is a member of the IEEE and IEEE Communications Society, Internet Society (ISOC), and associated with the IPv6 Forum, Asia Pacific Advanced Network Group (APAN), Internet2, and Malaysia Network Operator Group (MyNOG) member’s community.