Xin-Jing Wang
Mo Yu
Lei Zhang
Wei-Ying Ma
ABSTRACT
In this paper, we introduce a system named Argo which provides intelligent advertising made possible from users' photo collections. Based on the intuition that user-generated photos imply user interests which are the key for profitable targeted ads, the Argo system attempts to learn a user's profile from his shared photos and suggests relevant ads accordingly. To learn a user interest, in an offline step, a hierarchical and efficient topic space is constructed based on the ODP ontology, which is used later on for bridging the vocabulary gap between ads and photos as well as reducing the effect of noisy photo tags. In the online stage, the process of Argo contains three steps: 1) understanding the content and semantics of a user's photos and auto-tagging each photo to supplement user-submitted tags (such tags may not be available); 2) learning the user interest given a set of photos based on the learnt hierarchical topic space; and 3) representing ads in the topic space and matching their topic distributions with the target user interest; the top ranked ads are output as the suggested ads. Two key challenges are tackled during the process: 1) the semantic gap between the low-level image visual features and the high-level user semantics; and 2) the vocabulary impedance between photos and ads. We conducted a series of experiments based on real Flickr users and Amazon.com products (as candidate ads), which show the effectiveness of the proposed approach.
- Badi, R. Recognition and Representation of User Interest. Master Thesis, Texas A&M University, 2005.Google Scholar
- Broder, A., Fontoura, M., et al. A Semantic Approach to Contextual Advertising. SIGIR, pp. 559--566, 2007. Google ScholarDigital Library
- Chen C., Chen M., and Sun Y. PVA: A Self-Adaptive Personal View Agent. Journal of Intelligent Information Systems, p. 173--194, 2002. Google ScholarDigital Library
- Chen, Y., Xue, G.-R., and Yu, Y. Advertising Keyword Suggestion Based On Concept Hierarchy, In Proc. of ACM WSDM, 2008. Google ScholarDigital Library
- Crandall, D., Backstrom, L., et al. Mapping the World's Photos. WWW, 2009. Google ScholarDigital Library
- Evans, A., Fernandez, M., et al. Adaptive Multimedia Access: From User Needs Semantic Personalization. In Proc. Of IEEE Int. Symposium on Circuits and Systems, 2006.Google ScholarCross Ref
- Google AdWords Keyword Tool. https://adwords.google.com/select/KeywordToolExternal.Google Scholar
- Grcar, M., Mladenic, D., and Grobelnik, M. User Profiling for Interest-focused Browsing History. UserSWeb, 2005.Google Scholar
- Gunduz, S., and Ozsu, M. A User Interest Model for Web Page Navigation. In Proc. of Int. Workshop on Data Mining for Actionable Knowledge (DMAK), Seoul, Korea, April, pages 46--57, 2003.Google Scholar
- Hua, X.-S., Mei, T., and Li, S. P. When Multimedia Advertising Meets the New Internet Era. Intl Workshop on Multimedia Signal Processing, pp. 1--5, 2008.Google Scholar
- Jing, F., Li, M. et al. Learning Region Weighting from Relevance Feedback in Image Retrieval. In Proc. of IEEE Int. Conf. on Acoustics Speech and Signal, 2002.Google Scholar
- Joshi, A., and Motwani, R. Keyword Generation for Search Engine Advertising. In Proc. of the 6th IEEE Int. Conf. on Data Mining --- Workshops. 2006. Google ScholarDigital Library
- Kim, H. R., and Chan, P. K. Learning Implicit User Interest Hierarchy for Context in Personalization. In Proc. of International Conference on Intelligent User Interface, 2003. Google ScholarDigital Library
- Lacerda, A., Cristo, M., et al. Learning to Advertise. SIGIR, pp. 549--556, 2006. Google ScholarDigital Library
- Letizia, L. H. An Agent That Assists Web Browsing. In Proc. of the International Joint Conference on Artificial Intelligence, Montreal, CA, 1995.Google Scholar
- Li, X., Guo, L., and Zhao, Y. Tag-based Social Interest Discovery. WWW, pp. 675--684. 2008. Google ScholarDigital Library
- Li Z., Zhang L., Ma W.-Y. Delivering Online Advertisements Inside Images, In Proc. of ACM Multimedia, Vancouver, Canada, October 2008. Google ScholarDigital Library
- Ma, Z., Pant, G., and Sheng, O. Interest-Based Personalized Search. ACM Trans. on Information Systems, vol. 25(1), 2007. Google ScholarDigital Library
- Middleton S., De Roure D., and Shadbolt N. Capturing Knowledge of User Preferences: Ontologies in Recommender Systems. In Proc. of the 1st International Conference on Knowledge Capture (K-Cap2001), Victoria, BC Canada, 2001. Google ScholarDigital Library
- Murdock, V., Ciaramita, M., and Plachouras, V. A Noisy-Channel Approach to Contextual Advertising. ADKDD, pp. 21--28, 2007. Google ScholarDigital Library
- Plangprasopchok, A., and Lerman, K. Constructing Folksonomies from User-Specificed Relations on Flickr. WWW, 2009. Google ScholarDigital Library
- Ribeiro-Neto, B., Cristo, M., et al. Impedance Coupling in Con-tent-targeted Advertising. SIGIR, pp. 496--503, 2005. Google ScholarDigital Library
- Trajkova, J., and Gauch, S. Improving Ontology-Based User Profiles. In Proc. of RIAO, pp. 380--389, 2004.Google Scholar
- Wang, X.-J., Zhang, L., et al. Annotating Images by Mining Image Search Results. T-PAMI, vol. 30(11), pp. 1919--1932, 2008. Google ScholarDigital Library
- WordTracker. http://www.wordtracker.com.Google Scholar
- Zhou, X., Wu, S.-T., et al. Utilizing Search Intent in Topic Ontology-based User Profile for Web Mining. In Proc. Of IEEE Int. Conf. on Web Intelligence, 2006. Google ScholarDigital Library
Index Terms
- Argo: intelligent advertising by mining a user's interest from his photo collections
Recommendations
Argo: intelligent advertising made possible from users' photos
MM '09: Proceedings of the 17th ACM international conference on MultimediaThough monetizing user-generated photos has a great potential in image business, this topic is seldom touched due to the difficulties of both image understanding and ads-to-images vocabulary matching. In this technical demonstration, we show case the ...
Advertising based on users' photos
ICME'09: Proceedings of the 2009 IEEE international conference on Multimedia and ExpoIn this paper, we tackle the problem of learning a user's interest from his photo collections and suggesting relevant ads. We address two key challenges in this work: 1) understanding a user's photos to detect his interest, and 2) bridging the lexical ...
Social User Interest Mining: Methods and Applications
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mininghe abundance of user generated content on social networks pro-vides the opportunity to build models that are able to accurately and effectively extract, mine and predict users' interests with the hopes of enabling more effective user engagement, better ...
Comments