A Tale of Three Social Networks: User Activity Comparisons across Facebook, Twitter, and Foursquare

Wang, Pinghui; He, Wenbo; Zhao, Junzhou

doi:10.1109/mic.2013.128

Cited by 27 publications

(22 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The emergence of new cross-linking functionality in modern social Web platforms is related to our work. For instance, the work conducted by Wang et al [25] performed high level comparison between Facebook, Twitter and Foursquare profiles for randomly sampled Foursquare users; they performed both content level and network level analysis. From the network point of view, it was noted that "67 percent of friend pairs on Foursquare are also friends on Facebook, and 43 percent of friend pairs on Foursquare follow each other on Twitter" [25].…”

Section: Related Workmentioning

confidence: 99%

“…For instance, the work conducted by Wang et al [25] performed high level comparison between Facebook, Twitter and Foursquare profiles for randomly sampled Foursquare users; they performed both content level and network level analysis. From the network point of view, it was noted that "67 percent of friend pairs on Foursquare are also friends on Facebook, and 43 percent of friend pairs on Foursquare follow each other on Twitter" [25]. The authors observed that active Foursquare users are usually active in Twitter as well, which is consistent with the observations derived from our dataset.…”

Section: Related Workmentioning

confidence: 99%

“…These social services are often connected to each other by deploying the so-called cross-linking functionality [4]. With multi-source and mobility-related data, understanding user behaviours via user profile learning is promising and possible [13] [15][17] [25] [26].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Harvesting Multiple Sources for User Profile Learning

Farseev

Nie

Akbari

et al. 2015

Proceedings of the 5th ACM on International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

User profile learning, such as mobility and demographic profile learning, is of great importance to various applications. Meanwhile, the rapid growth of multiple social platforms makes it possible to perform a comprehensive user profile learning from different views. However, the research efforts on user profile learning from multiple data sources are still relatively sparse, and there is no large-scale dataset released towards user profile learning. In our study, we contribute such benchmark and perform an initial study on user mobility and demographic profile learning. First, we constructed and released a large-scale multi-source multimodal dataset from three geographical areas. We then applied our proposed ensemble model on this dataset to learn user profile. Based on our experimental results, we observed that multiple data sources mutually complement each other and their appropriate fusion boosts the user profiling performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Harvesting Multiple Sources for User Profile Learning

Farseev

Nie

Akbari

et al. 2015

Proceedings of the 5th ACM on International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

show abstract

“…The sampling methods they used are biased. Differently, we present a holistic study of the Wang et al [18] compared a series of user activity across Foursquare, Facebook, and Twitter using 200K randomly sampled users. In our work, we have explored more on the cross-site linking function, and addressed a number of unexplored viable issues, such as the distribution of different linking options, behavioral difference among users with different linking options, and user privacy.…”

Section: Related Workmentioning

confidence: 99%

Understanding Cross-site Linking in Online Social Networks

Yang

Zhuang

Cao

et al. 2014

Proceedings of the 8th Workshop on Social Network Mining and Analysis

View full text Add to dashboard Cite

Online social networks (OSNs) have attracted billions of users, and play an important role in people's daily life. A user often has accounts on multiple OSN sites. In this paper, we study the emerging "cross-site linking" function, which is supported by many OSNs. Our study is based on Foursquare, a representative location-based social networking (LBSN) service. We conduct a data-driven analysis by using crawled public profiles of almost all (if not all) Foursquare users. Our analysis has shown that the crosssite linking function is widely adopted by Foursquare users, and the users who have enabled this function are more active than other users. We have also found that users who are more concerned with online privacy have a lower probability to enable the cross-site linking function. Besides analyzing crawled Foursquare user profiles, we further explore cross-site linking between Foursquare and other OSN sites, i.e., Facebook and Twitter. The study on "FoursquareFacebook" linking indicates that users have a high probability to provide consistent information to different OSNs. Meanwhile, "Foursquare-Twitter" linking is used to demonstrate the usefulness of aggregating user-generated content across multiple OSN sites. We present a gender-based analysis of Twitter, which is made accurate by leveraging crosssite links between Foursquare and Twitter.

show abstract

“…Finding those structures can be beneficial in many fields, such as finding protein complexes in biological networks and topical, disciplinary groups in collaborative networks, etc [1,2,3,4,5,6,7].…”

Section: Introductionmentioning

confidence: 99%