Predicting Insider Threat Risks through Linguistic Analysis of Electronic Communication
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
Organizations face growing risks from malicious or careless insiders. An insider threat may take many forms, including disgruntled workers, individuals under financial stress or intentional acts of espionage. Waiting for threats to manifest may leave an organization open to liability, hurt morale and in extreme cases lead to physical harm of others. However, predicting who may pose the greatest risk is challenging. Legal and economic concerns make direct psychological examinations challenging, while reliance upon supervisor or co-worker assessments may lead to unfounded accusations. This research investigates the potential for active monitoring of electronic communications as a method that may identify problems early, allowing for proactive mitigation through coaching, assistance programs and where warranted, termination. Research has found correlations between word use and behavior. This research demonstrates that subtle but measurable differences in the frequency of common words found in electronic communication may provide clues about potential insider threat risks.
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
Personality in 100,000 Words: A large-scale analysis of personality and word use among bloggers
Yarkoni, T. (2010) · Journal of Research in Personality · doi:10.1016/j.jrp.2010.04.001 · Cited by 637 · cited 3×
“A large study of text produced by “bloggers” found a close correlation between the results of word use analysis and subsequent personality questionnaires [11].”
BackgroundMethodResultEbstrup, J. F., Eplov, L. F., Pisinger, C., & Jørgensen, T. (2011) · Anxiety, Stress & Coping · doi:10.1080/10615806.2010.540012 · Cited by 359
Text messaging, personality, and the social context
Holtgraves, T. (2011) · Journal of Research in Personality · doi:10.1016/j.jrp.2010.11.015 · Cited by 166
Psychosocial Modeling of Insider Threat Risk Based on Behavioral and Word Use Analysis
Greitzer, Kangas, Noonan, Brown, & Ferryman (2013) · e-Service Journal · doi:10.2979/eservicej.9.1.106 · Cited by 47
Cited by
Homoliak, I., Toffalini, F., Guarnizo, J., Elovici, Y., & Ochoa, M. (2020) · ACM Computing Surveys · doi:10.1145/3303771 · Cited by 255
“For example, [Brown et al. 2013; Greitzer et al. 2013] use emails as a data source, however their approach works only with the text information of those emails and considers motive-based feature domains (i.e., personality factors, current emotional states); this is in contrast with [Legg et al.…”
MethodResultElectronic government: Towards e-democracy or democracy at risk?
Sundberg, L. (2019) · Safety Science · doi:10.1016/j.ssci.2019.04.030 · Cited by 77
Classification of Insider Threat Detection Techniques
Sanzgiri, A., & Dasgupta, D. (2016) · Proceedings of the 11th Annual Cyber and Information Security Research Conference · doi:10.1145/2897795.2897799 · Cited by 68
“…[18-21] Use of case studies and real-world insider attacker symptoms [22] Personality indicators & language usage in text &official documentation [23-24] Processes and artifacts used & accessed: Analyzed insider threats by using Fault Tolerance Analysis [25] Modeling adversarial behavior &…”
BackgroundMethodEmployee profiling via aspect-based sentiment and network for insider threats detection
Soh, C., Yu, S., Narayanan, A., Duraisamy, S., & Chen, L. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.05.043 · Cited by 61
Integrating Cyber Deception Into Attribute-Based Access Control (ABAC) for Insider Threat Detection
Alohaly, M., Balogun, O., & Takabi, D. (2022) · IEEE Access · doi:10.1109/access.2022.3213645 · Cited by 28
“During the same period of time, Brown et al. [2] exploited the co-relation between the words use and a set of psychological and behavioral risk factors to develop a proactive insider threat detection framework.”
BackgroundMethodMethods and Metrics for Evaluating Analytic Insider Threat Tools
Greitzer, F. L., & Ferryman, T. A. (2013) · 2013 IEEE Security and Privacy Workshops · doi:10.1109/spw.2013.34 · Cited by 22
Self-citationPaxton-Fear, K., Hodges, D., & Buckley, O. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-50309-3_42 · Cited by 9
“The current state of the art approaches to understand, and ultimately prevent insider threat, usually consider either technical [11,1,8], psychological or sociological [17,12,4] approaches with a small number of models which encapsulating a number of these factors (e.”
Background
Metadata
- Authors
- Brown, C. R., Watkins, A., & Greitzer, F. L.
- Venue
- 2013 46th Hawaii International Conference on System Sciences
- Publisher
- IEEE
- Published
- 2013-01
- Pages
- 1849-1858
- ISSN
- 1530-1605 (ISSN-L)
- OpenAlex
- W2126189917
- Cited by
- 38
- References
- 4
- FWCI
- 3.23
- 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.