ABSTRACT
In the social media domain user-to-user recommendation is an important factor to suggest new content and to strengthen the user social circle. In this paper we investigate how to improve user-to-user recommendation exploiting a user similarity metric computed analysing the photos shared by users on their Instagram profile. We consider in particular users with an established credibility and audience, the so called "influencers". The main idea is that if two influencers publish photos containing similar content it is more likely that they share the same interests and are similar. Moreover, users that follow other users sharing related content are also more similar. Similarity between influencers' photo collections is estimated through neural network embeddings, using a network trained to classify photo collections in categories of interest. An hybrid recommendation approach, which combines collaborative filtering and results from this compact representation of visual content of photo collections, is proposed. Experiments on a large dataset of ~4.8M Instagram users show how our visual approach enhances the performance of a user-to-user recommender with respect to a baseline recommendation algorithm based on collaborative filtering.
Supplemental Material
Available for Download
- Saeideh Bakhshi, David A. Shamma, and Eric Gilbert. 2014. Faces Engage Us: Photos with Faces Attract More Likes and Comments on Instagram. In Proc. of SIGCHI Conference on Human Factors in Computing Systems (CHI). 965--974.Google ScholarDigital Library
- M. Cheung, J. She, and Z. Jie. 2015. Connection Discovery Using Big Data of User-Shared Images in Social Media. IEEE Transactions on Multimedia, Vol. 17, 9 (Sep. 2015), 1417--1428.Google ScholarDigital Library
- Ryadh Dahimene, Camelia Constantin, and Cédric du Mouza. 2014. RecLand: A Recommender System for Social Networks. In Proc. of CIKM.Google ScholarDigital Library
- Marijke De Veirman, Veroline Cauberghe, and Liselot Hudders. 2017. Marketing through Instagram influencers: the impact of number of followers and product divergence on brand attitude. International Journal of Advertising, Vol. 36, 5 (2017), 798--828.Google ScholarCross Ref
- Xuetao Ding, Xiaoming Jin, Yujia Li, and Lianghao Li. 2013. Celebrity recommendation with collaborative social topic regression. In Proc. of IJCAI.Google Scholar
- C. Fan, H. Hao, C. K. Leung, L. Y. Sun, and J. Tran. 2018. Social Network Mining for Recommendation of Friends Based on Music Interests. In Proc. of ASONAM.Google Scholar
- Bruce Ferwerda and Marko Tkalcic. 2018. Predicting Users' Personality from Instagram Pictures: Using Visual and/or Content Features?. In Proc. of UMAP. 5.Google ScholarDigital Library
- Francesco Gelli, Xiangnan He, Tao Chen, and Tat-Seng Chua. 2017. How personality affects our likes: Towards a better understanding of actionable images. In Proc. of ACM Multimedia (MM).Google ScholarDigital Library
- Dongyan Guo, Jingsong Xu, Jian Zhang, Min Xu, Ying Cui, and Xiangjian He. 2017. User relationship strength modeling for friend recommendation on Instagram. Neurocomputing, Vol. 239 (2017), 9 -- 18.Google ScholarDigital Library
- Ido Guy. 2018. People Recommendation on Social Media .Springer International Publishing, Cham, 570--623.Google Scholar
- Alexander Hermans, Lucas Beyer, and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017).Google Scholar
- Susie Khamis, Lawrence Ang, and Raymond Welling. 2017. Self-branding, 'micro-celebrity' and the rise of Social Media Influencers. Celebrity Studies, Vol. 8, 2 (2017), 191--208.Google ScholarCross Ref
- Joseph A Konstan, Bradley N Miller, David Maltz, Jonathan L Herlocker, Lee R Gordon, and John Riedl. 1997. GroupLens: applying collaborative filtering to Usenet news. Commun. ACM, Vol. 40, 3 (1997), 77--87.Google ScholarDigital Library
- Maciej Kula. 2015. Metadata embeddings for user and item cold-start recommendations. In Proc. of CBRecSys.Google Scholar
- Bamshad Mobasher. 2007. Data mining for web personalization. The adaptive web (2007).Google ScholarDigital Library
- S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proc. of UAI.Google Scholar
- D. Semedo, J. Magalh aes, and F. Martins. 2018. Inferring User Gender from User Generated Visual Content on a Deep Semantic Space. In Proc. of EUSIPCO.Google Scholar
- Junho Song, Kyungsik Han, Dongwon Lee, and Sang-Wook Kim. 2018. “Is a picture really worth a thousand words?”: A case study on classifying user attributes on Instagram. PLOS ONE, Vol. 13, 10 (10 2018), 1--22.Google ScholarCross Ref
- Z. Wang, J. Liao, Q. Cao, H. Qi, and Z. Wang. 2015. Friendbook: A Semantic-Based Friend Recommendation System for Social Networks. IEEE Transactions on Mobile Computing, Vol. 14, 3 (March 2015), 538--551.Google ScholarDigital Library
- Jian Wei, Jianhua He, Kai Chen, Yi Zhou, and Zuoyin Tang. 2017. Collaborative filtering and deep learning based recommendation system for cold start items. Expert Systems with Applications, Vol. 69 (2017), 29 -- 39.Google ScholarCross Ref
- Jason Weston, Samy Bengio, and Nicolas Usunier. 2011. Wsabie: Scaling up to large vocabulary image annotation. In Proc. of IJCAI.Google Scholar
Index Terms
Keeping up with the Influencers: Improving User Recommendation in Instagram using Visual Content
Recommendations
Discovery of Topical Authorities in Instagram
WWW '16: Proceedings of the 25th International Conference on World Wide WebInstagram has more than 400 million monthly active accounts who share more than 80 million pictures and videos daily. This large volume of user-generated content is the application's notable strength, but also makes the problem of finding the ...
Improving user recommendation by extracting social topics and interest topics of users in uni-directional social networks
With the rapid growth of population on social networks, people are confronted with information overload problem. This clearly makes filtering the targeted users a demanding and key research task. Uni-directional social networks are the scenarios where ...
Recommendation in reciprocal and bipartite social networks: a case study of online dating
SBP'13: Proceedings of the 6th international conference on Social Computing, Behavioral-Cultural Modeling and PredictionMany social networks in our daily life are bipartite networks that are built on reciprocity. How can we recommend users/friends to a user, so that the user is interested in and attractive to recommended users? In this research, we propose a new ...
Comments