Studying User Footprints in Different Online Social Networks
The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
With the growing popularity and usage of online social media services, people now have accounts (some times several) on multiple and diverse services like Facebook, Linked In, Twitter and You Tube. Publicly available information can be used to create a digital footprint of any user using these social media services. Generating such digital footprints can be very useful for personalization, profile management, detecting malicious behavior of users. A very important application of analyzing users' online digital footprints is to protect users from potential privacy and security risks arising from the huge publicly available user information. We extracted information about user identities on different social networks through Social Graph API, Friend Feed, and Profilactic, we collated our own dataset to create the digital footprints of the users. We used username, display name, description, location, profile image, and number of connections to generate the digital footprints of the user. We applied context specific techniques (e.g. Jaro Winkler similarity, Word net based ontologies) to measure the similarity of the user profiles on different social networks. We specifically focused on Twitter and Linked In. In this paper, we present the analysis and results from applying automated classifiers for disambiguating profiles belonging to the same user from different social networks. User ID and Name were found to be the most discriminative features for disambiguating user profiles. Using the most promising set of features and similarity metrics, we achieved accuracy, precision and recall of 98%, 99%, and 96%, respectively.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning
Fayyad, U. M., & Irani, K. B. (1993) · International Joint Conference on Artificial Intelligence · Cited by 3,534
The feature selection problem: traditional methods and a new algorithm
Kira, K., & Rendell, L. A. (1992) · National Conference on Artificial Intelligence · Cited by 1,897
The minimum description length principle in coding and modeling
Barron, A., Rissanen, J., & Yu, B. (1998) · IEEE Transactions on Information Theory · doi:10.1109/18.720554 · Cited by 1,019 · cited 1×
“Table I shows the features’ discriminative capacity according to four different scores: Information Gain (IG), Relief [21], Minimum Description Length (MDL) [22] and Gini coefficient [23].”
BackgroundAll your contacts are belong to us: automated identity theft attacks on social networks
Bilge, L., Strufe, T., Balzarotti, D., & Kirda, E. (2009) · Proceedings of the 18th international conference on World wide web · doi:10.1145/1526709.1526784 · Cited by 545
Connecting Corresponding Identities across Communities
Zafarani, R., & Liu, H. (2009) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v3i1.13993 · Cited by 224 · cited 4×
“Due to strong relationship between users’ offline and online identity [2], [3], users’ online digital footprints can help in uniquely identifying them.”
BackgroundMethodInfluentialUser identification across multiple social networks
Vosecky, J., Hong, D., & Shen, V. Y. (2009) · 2009 First International Conference on Networked Digital Technologies · doi:10.1109/ndt.2009.5272173 · Cited by 217 · cited 2×
“A user profile on any social networking website can be seen as an N dimensional vector, where each dimension is a profile field, e.g., username, first name, last name, location, description / about me, relationship and others [17].”
BackgroundIdentifying Users Across Social Tagging Systems
Iofciu, T., Fankhauser, P., Abel, F., & Bischoff, K. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v5i1.14153 · Cited by 201 · cited 3×
“Researchers have also used tags created by users (on different social networking sites such as Flickr, Delicious, StumbleUpon) to connect accounts using semantic analysis of the tags [5], [8], [12].”
BackgroundMethodHow Unique and Traceable Are Usernames?
Perito, D., Castelluccia, C., Kaafar, M. A., & Manils, P. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-22263-4_1 · Cited by 194
Abusing Social Networks for Automated User Profiling
Balduzzi, M. `., Platzer, C., Holz, T., Kirda, E., Balzarotti, D., & Kruegel, C. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15512-3_22 · Cited by 178 · cited 1×
“Unification of users’ multiple online identities can lead to various privacy and security threats like: identity thefts and profile cloning [3], [9] which can lead to compromised accounts [1]; directed spam and phishing [10]; online profiling by advertisers and attackers [11]; online stalking [1].”
BackgroundLinking social networks on the web with FOAF: a semantic web case study
Golbeck, J., & Rothstein, M. (2008) · National Conference on Artificial Intelligence · Cited by 174
Domain-independent data cleaning via analysis of entity-relationship graph
Kalashnikov, D. V., & Mehrotra, S. (2006) · ACM Transactions on Database Systems · doi:10.1145/1138394.1138401 · Cited by 165 · cited 1×
“All these factors make user profile linking across social networks a challenging task in comparison to Named Entity Recognition [13].”
BackgroundUser identification for cross-system personalisation
Carmagnola, F., & Cena, F. (2008) · Information Sciences · doi:10.1016/j.ins.2008.08.022 · Cited by 117 · cited 2×
“belonging to the same user [1], [2], [4], [15]–[18].”
BackgroundSemantic Modelling of User Interests Based on Cross-Folksonomy Analysis
Szomszor, M., Alani, H., Cantador, I., O’Hara, K., & Shadbolt, N. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88564-1_40 · Cited by 113
Detecting social network profile cloning
Kontaxis, G., Polakis, I., Ioannidis, S., & Markatos, E. P. (2011) · 2011 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops) · doi:10.1109/percomw.2011.5766886 · Cited by 108 · cited 2×
“User profile attributes were used to identify accounts belonging to the same user [1], [2], [4], [15]–[18].”
MethodLarge Online Social Footprints--An Emerging Threat
Irani, D., Webb, S., Li, K., & Pu, C. (2009) · 2009 International Conference on Computational Science and Engineering · doi:10.1109/cse.2009.459 · Cited by 102
Correlating user profiles from multiple folksonomies
Szomszor, M., Cantador, I., & Alani, H. (2008) · ACM Conference on Hypertext and Social Media (HT) · doi:10.1145/1379092.1379103 · Cited by 84 · cited 2×
“Researchers have also used tags created by users (on different social networking sites such as Flickr, Delicious, StumbleUpon) to connect accounts using semantic analysis of the tags [5], [8], [12].”
BackgroundMethodFeature Selection for Text Classification Based on Gini Coefficient of Inequality
Singh, S. R., Murthy, H. A., & Gonsalves, T. A. (2010) · Cited by 74
Harnessing the Social Web: The Science of Identity Disambiguation
Rowe, M., & Ciravegna, F. (2010) · Open Research Online (The Open University) · Cited by 10
Cited by
Inferring anchor links across multiple heterogeneous social networks
Kong, X., Zhang, J., & Yu, P. S. (2013) · Proceedings of the 22nd ACM international conference on Information & Knowledge Management · doi:10.1145/2505515.2505531 · Cited by 356
User Identity Linkage across Online Social Networks: A Review
Shu, K., Wang, S., Tang, J., Zafarani, R., & Liu, H. (2017) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3068777.3068781 · Cited by 267
An efficient reconciliation algorithm for social networks
Korula, N., & Lattanzi, S. (2014) · Proceedings of the VLDB Endowment · doi:10.14778/2732269.2732274 · Cited by 238
“To improve on these first naive approaches, several machine learning models were developed [3, 17, 20, 25, 28], all of which collect several features of the users (name, location, image, connections topology), based on which they try to identify users across networks.”
MethodWhat's in a name?: an unsupervised approach to link users across communities
Liu, J., Zhang, F., Song, X., Song, Y.-I., Lin, C.-Y., & Hon, H.-W. (2013) · Proceedings of the sixth ACM international conference on Web search and data mining · doi:10.1145/2433396.2433457 · Cited by 226
“General Terms Algorithms, Experimentation Keywords Social network, User linking, Pairwise classification”
BackgroundDetecting Clusters of Fake Accounts in Online Social Networks
Xiao, C., Freeman, D. M., & Hwa, T. (2015) · Proceedings of the 8th ACM Workshop on Artificial Intelligence and Security · doi:10.1145/2808769.2808779 · Cited by 184
“[23] develop features to detect malicious users who create fake accounts across different social networks.”
Background
Metadata
- Authors
- Malhotra, A., Totti, L., Meira, W., Kumaraguru, P., & Almeida, V.
- Venue
- 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining
- Publisher
- IEEE
- Published
- 2012-08
- Pages
- 1065-1070
- OpenAlex
- W2077738931
- Cited by
- 221
- References
- 18
- FWCI
- 26.19
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.