The DOI matches its Crossref record; 195 of the 207 references it cites were found in a registry or an index.
Authorship Attribution for Social Media Forensics
Abstract
The veil of anonymity provided by smartphones with pre-paid SIM cards, public Wi-Fi hotspots, and distributed networks like Tor has drastically complicated the task of identifying users of social media during forensic investigations. In some cases, the text of a single posted message will be the only clue to an author's identity. How can we accurately predict who that author might be when the message may never exceed 140 characters on a service like Twitter? For the past 50 years, linguists, computer scientists, and scholars of the humanities have been jointly developing automated methods to identify authors based on the style of their writing. All authors possess peculiarities of habit that influence the form and content of their written works. These characteristics can often be quantified and measured using machine learning algorithms. In this paper, we provide a comprehensive review of the methods of authorship attribution that can be applied to the problem of social media forensics. Furthermore, we examine emerging supervised learning-based methods that are effective for small sample sizes, and provide step-by-step explanations for several scalable approaches as instructional case studies for newcomers to the field. We argue that there is a significant need in forensics for new authorship attribution algorithms that can exploit context, can process multi-modal data, and are tolerant to incomplete knowledge of the space of all possible authors at training time.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
Lu, Z. Q. J. (2010) · Journal of the Royal Statistical Society Series A (Statistics in Society) · doi:10.1111/j.1467-985x.2010.00646_6.x · Cited by 12,916
Foundations of statistical natural language processing
Manning, C. D., & Schütze, H. (1999) · Cited by 9,816
Introduction to Modern Information Retrieval
Salton, G., & McGill, M. J. (1983) · Virtual Defense Library (Ministerio de Defensa) · Cited by 9,743
An Introduction to Statistical Modeling of Extreme Values
Coles, S. (2001) · Springer Series in Statistics · doi:10.1007/978-1-4471-3675-0 · Cited by 7,352
From the New York Times Magazine
Minsky, & Hyman, P. (1979) · Cited by 6,899
Research works printed but not linked: 14
- 2014, Guess Language Guess the Natural Language of a Text
- stamatatos, 2014, Overview of the author identification task at PAN 2014, Proc Conf CLEF, 877
- burrows, 1992, Computers and the study of literature, Computers and Written Texts, 1, 167
- stolerman, 2014, Classify, but verify: Breaking the closed-world assumption in stylometric authorship attribution, Proc Annu IFIP WG Int Conf Digit Forensics, 1
- eder, 2015, Stylo Functions for a Variety of Stylometric Analyses
- rashid, 2013, Simple Ways to Make Anonymous Phone Calls Secure Your Data
- ellegård, 1964, A Statistical method for determining authorship, Junius Lett, 40, 85
- 2013, In Search of OPSEC Magic Sauce Hacker OPSEC Blog
- kelly, 2014, Pyenchant A spellchecking Library for Python
- mascol, 1888, Curves of Pauline and pseudo-Pauline style I, Unitarian Review, 30, 453
- mccallum, 2002, Mallet A machine learning for language toolkit
- merriam, 1979, What Shakespeare wrote in Henry VIII (part I), Bard, 2, 81
- merriam, 1982, The authorship of Sir Thomas More, ALLC Bull Assoc Library Linguistic Comput, 10, 1
- merriam, 1980, What Shakespeare wrote in Henry VIII (part II), Bard, 2, 11
Cited by
Sorted by citations
Learning and the Unknown: Surveying Steps toward Open World Recognition
Boult, T. E., Cruz, S. S., Dhamija, A. R., Günther, M., Henrydoss, J., & Scheirer, W. J. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33019801 · Cited by 134
Self-citationDu, X., Hargreaves, C. J., Sheppard, J., Anda, F., Sayakkara, A., Le‐Khac, N., & Scanlon, M. (2020) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3407023.3407068 · Cited by 130
Multi-Dimensional Gender Bias Classification
Dinan, E., Fan, A., Wu, L., Weston, J., Kiela, D., & Williams, A. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.23 · Cited by 117
Digital Forensics in Cyber Security—Recent Trends, Threats, and Opportunities
Alghamdi, M. (2021) · IntechOpen eBooks · doi:10.5772/intechopen.94452 · Cited by 68
Explainable Authorship Verification in Social Media via Attention-based Similarity Learning
Boenninghoff, B., Hessler, S., Kolossa, D., & Nickel, R. M. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9005650 · Cited by 66
Metadata
- Authors
- Rocha, A., Scheirer, W. J., Forstall, C. W., Cavalcante, T., Theophilo, A., Shen, B., Carvalho, A. R. B., & Stamatatos, E.
- Affiliations
- Universidade Estadual de Campinas (UNICAMP) (BR)
- University of Notre Dame (US)
- University of the Aegean (GR)
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2017-01
- Volume
- 12
- Issue
- 1
- Pages
- 5-33
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W2508310662
- Cited by
- 222
- References
- 207
- Citations by year
- 2026: 6 · 2025: 5 · 2024: 13 · 2023: 25 · 2022: 22 · 2021: 39 · 2020: 43 · 2019: 28 · 2018: 27 · 2017: 14
- FWCI
- 18.95
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Information Forensics and Security (publishedVersion)
- Funders
- Brazilian Coordination for the Improvement of Higher Education and Personnel — CAPES (DeepEyes project)
- São Paulo Research Foundation – FAPESP (through the DéjàVu Project) (15/19222-9)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Physical Sciences › Computer Science › Information Systems › User Authentication and Security Systems
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Keywords
- authorship attribution, social media forensics, stylistic analysis, user identification, anonymity, multimodal data, forensic text analysis
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
