TY - GEN
T1 - Non-user Generated Annotation on User Shared Images for Connection Discovery
AU - Cheung, Ming
AU - She, James
AU - Li, Xiaopeng
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015
Y1 - 2015
N2 - Social graphs, representing the online friendships among users, are one of the most fundamental types of data for many social media applications, such as recommendation, virality prediction and marketing. However, this data may be unavailable due to the privacy concerns of users, or kept privately by social network operators, which makes such applications difficult. One of the possible solutions to discover user connections is to use shared content, especially images on online social networks, such as Flickr and Instagram. This paper investigates how non-user generated labels annotated on shared images can be used for connection discovery with different color-based and feature-based methods. The label distribution is computed to represent users, and followee/follower relationships are recommended based on the distribution similarity. These methods are evaluated with over 200k images from Flickr and it is proven that with non-user generated labels, user connections can be discovered, regardless of the method used. Feature-based methods are also proven to be 95% better than color-based methods, and 65% better than tag-based methods.
AB - Social graphs, representing the online friendships among users, are one of the most fundamental types of data for many social media applications, such as recommendation, virality prediction and marketing. However, this data may be unavailable due to the privacy concerns of users, or kept privately by social network operators, which makes such applications difficult. One of the possible solutions to discover user connections is to use shared content, especially images on online social networks, such as Flickr and Instagram. This paper investigates how non-user generated labels annotated on shared images can be used for connection discovery with different color-based and feature-based methods. The label distribution is computed to represent users, and followee/follower relationships are recommended based on the distribution similarity. These methods are evaluated with over 200k images from Flickr and it is proven that with non-user generated labels, user connections can be discovered, regardless of the method used. Feature-based methods are also proven to be 95% better than color-based methods, and 65% better than tag-based methods.
KW - annotation
KW - big data
KW - connection discovery
KW - online social network
KW - recommendation
UR - http://www.scopus.com/inward/record.url?scp=84964502515&partnerID=8YFLogxK
U2 - 10.1109/DSDIS.2015.113
DO - 10.1109/DSDIS.2015.113
M3 - Conference contribution
AN - SCOPUS:84964502515
T3 - Proceedings - 2015 IEEE International Conference on Data Science and Data Intensive Systems; 8th IEEE International Conference Cyber, Physical and Social Computing; 11th IEEE International Conference on Green Computing and Communications and 8th IEEE International Conference on Internet of Things, DSDIS/CPSCom/GreenCom/iThings 2015
SP - 204
EP - 209
BT - Proceedings - 2015 IEEE International Conference on Data Science and Data Intensive Systems; 8th IEEE International Conference Cyber, Physical and Social Computing; 11th IEEE International Conference on Green Computing and Communications and 8th IEEE International Conference on Internet of Things, DSDIS/CPSCom/GreenCom/iThings 2015
A2 - Yang, Laurence T.
A2 - Chen, Jinjun
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2015 IEEE International Conference on Data Science and Data Intensive Systems; 8th IEEE International Conference Cyber, Physical and Social Computing; 11th IEEE International Conference on Green Computing and Communications and 8th IEEE International Conference on Internet of Things, DSDIS/CPSCom/GreenCom/iThings 2015
Y2 - 11 December 2015 through 13 December 2015
ER -