Matching Potential Customers and Influencers for Social Media Marketing

Öz

Social media platforms are so important for the advertising industry. Companies have a huge amount of budget for advertisement and try to select an influencer as the face of their brand for these advertisements. Each brand is related to a specific segment of customers. When the true influencer is followed by this segment, advertising companies contact him/her. The objective of this work is to facilitate the job of the advertising company by matching the brand and the influencer to use the budget of the advertising company appropriately. Accordingly, our work makes an analysis of real/fake account detection, gender, and age range prediction of the influencer’s followers. In this work, it is focused on the real accounts by eliminating the fake ones and the gender, age- range prediction of these real accounts is considered. The detection of fake accounts is transformed into a binary classification problem by observing the features of real and fake accounts. Another binary classification solution is presented for gender detection by checking the pictures of the account owners and their names together. A pre-trained deep learning model for follower age range prediction is provided based on the pictures of these followers. The accuracy of the predictions is evaluated for each of the three situations and the success of our approach is observed for influencer/follower matching.

Anahtar Kelimeler

• Deep learning
• fake account detection
• image processing
• machine learning
• social media analysis

Kaynakça

1. M. Pütter, “The impact of social media on consumer buying intention”, Journal of International Business Research and Marketing, 2017, 3(1), pp. 7-13.
2. C. Schwemmer and S. Ziewiecki, “Social media sellout: The increasing role of product promotion on YouTube”, Social Media + Society, 2018, 4(3), pp. 1-20.
3. M. Delbaere, B. Michael and B. J. Phillips, “Social media influencers: A route to brand engagement for their followers”, Psychology and Marketing, 2021, 38(3), pp. 101-112.
4. M. Bruhn, V. Schoenmueller and D. B. Schäfer, “Are social media replacing traditional media in terms of brand equity creation?”, 2012, Management Research Review, 35(9), pp. 770-790.
5. E. Constantinides, “Foundations of social media marketing”, Procedia-Social and Behavioral Sciences, 2014, 148, pp. 40-57.
6. X. J. Lim, A. M. Radzol, J. Cheah and M. W. Wong, “The impact of social media influencers on purchase intention and the mediation effect of customer attitude”, Asian Journal of Business Research, 2017, 7(2), pp. 19-36.
7. S. Woods, “#Sponsored: The emergence of influencer marketing”, 2016, https://trace.tennessee.edu/utk_chanhonoproj/1976.
8. T.Gan,S.Wang,M.Liu,X.Song,Y.Yao,andLiqiangNie,“SeekingMicro-influencersforBrandPromotion”,2019,InProceedings of the 27th ACM International Conference on Multimedia (MM '19). Association for Computing Machinery, New York, NY, USA, 1933–1941. DOI:https://doi.org/10.1145/3343031.3351080

9. S. Wang, T. Gan, Y. Liu, L. Zhang, J. Wu and L. Nie, "Discover Micro-influencers for Brands via Better Understanding," in IEEE Transactions on Multimedia, 2021, doi: 10.1109/TMM.2021.3087038.
10. F. C. Akyon and E. Kalfaoglu, “Instagram fake and automated account detection” In Proc. IEEE Innovations in Intelligent Systems and Applications Conference, 2019, pp. 1-7.
11. Y. Jeon, S.G. Jean and K. Han, “Better targeting of consumers: Modeling multifactorial gender and biological sex from Instagram posts”, Journal of User Modeling and User-Adapted Interaction, 2020, vol. 30, pp. 833-866.
12. K. Han, S. Lee, J. Y. Jang, Y. Jung, and D. Lee, “Teens are from mars, adults are from venus: analyzing and predicting age groups with behavioral characteristics in instagram.”, In Proceedings of the 8th ACM Conference on Web Science (WebSci '16), Association for Computing Machinery, 2016, pp. 35-44.
13. A. Farseev, K. Lepikhin, H. Schwartz and E. K. Ang., “SoMin.ai: social multimedia influencer discovery marketplace” In Proc. of the 26th ACM International Conference on Multimedia, pp. 1234-1236, 2018.
14. T. Niciporuc, "Comparative analysis of the engagement rate on Facebook and Google Plus social networks," Proceedings of International Academic Conferences 0902287, International Institute of Social and Economic Sciences, 2014.
15. E. Naumanen and M. Pelkonen, “Celebrities of Instagram - What Type of Content Influences Followers’ Purchase Intentions and Engagement Rate?”, Master’s Thesis, Aalto University. School of Business, 2017.
16. R. L. H. Yew, S. B. Suhaidi, P. Seewoochurn and V. K. Sevamalai, "Social Network Influencers’ Engagement Rate Algorithm Using Instagram Data," 2018 Fourth International Conference on Advances in Computing, Communication & Automation (ICACCA), pp. 1-8, doi: 10.1109/ICACCAF.2018.8776755, 2018.
17. O. M. Parkhi, A. Vedaldi, and A. Zisserman, "Deep face recognition", BMVC 2015, 2015, pp. 41.1–41.12, 2015.
18. S. I. Serengil and A. Ozpinar, “LightFace: A Hybrid Deep Face Recognition Framework, ” 2020 Innovations in Intelligent Systems and Applications Conference (ASYU), pp. 1-5, doi: 10.1109/ASYU50717.2020.9259802, 2020.