Exploiting Linguistic Style as a Cognitive Biometric for Continuous Verification

Neal, Tempestt; Sundararajan, Kalaivani

doi:10.1109/icb2018.2018.00048

Cited by 12 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pokhriyal et al designed a biometric system to distinguish between genuine user and imposter by extracting stylistic features, semantic features, and syntactic features from the written contents of blogs on the internet [20]. Neal et al developed a continuous verification system using the character and lexical-level features extracted from the blogs written by the individuals and used these linguistic features as cognitive biometric trait [4]. Authors of [20] and [4] did not, however, consider the user's vocabulary set as linguistic features and did not experiment with their systems on any social networking data.…”

Section: Related Workmentioning

confidence: 99%

“…Neal et al developed a continuous verification system using the character and lexical-level features extracted from the blogs written by the individuals and used these linguistic features as cognitive biometric trait [4]. Authors of [20] and [4] did not, however, consider the user's vocabulary set as linguistic features and did not experiment with their systems on any social networking data. Most recently, Alonso-Fernandez et al proposed a system for social media forensics using the frequency of lexical, structural and syntactic properties obtained from tweets [21].…”

Section: Related Workmentioning

confidence: 99%

“…In addition to traditional forms of biometrics such as face, gait and iris, emerging research has focused on technologies that measure signals generated directly or indirectly by human thought processes. Examples of those biometrics include Electroencephalography (EEG) brain signal [3], linguistic style [4], keystroke dynamics [5], mouse movement [6], eye tracking [7], etc. The next-generation behavioral biometrics has broadened its scope from real-world activities to virtual user recognition in the cyberworld.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Template Aging in Multi-Modal Social Behavioral Biometrics

Tumpa

Gavrilova

2022

IEEE Access

View full text Add to dashboard Cite

The uniqueness of social interactions on online social networks draws attention to cybersecurity research. Social Behavioral Biometric (SBB) systems extract unique patterns from online communication traits trails and generate digital fingerprints for user identification. However, with time those behavioral patterns change. These affect the authentication ability of a SBB system. In this paper, we have combined for the first time textual, contextual and interpersonal communicative information of users in online social networks to develop a biometric system. The SBB traits are combined using the weighted sum rule score level fusion algorithm with the genetic algorithm employed to choose the feature weights. The effects of template aging on the individual SBB traits and overall system have been analyzed for the first time. The proposed system achieves the recognition accuracy of 99.25% and outperforms all prior research on SBB. The experimental results on permanence evaluation demonstrate that the developed system can perform remarkably well despite the template aging effect.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Template Aging in Multi-Modal Social Behavioral Biometrics

Tumpa

Gavrilova

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Dealing with implicitly collected data requires caution as they can reveal the user's identity from biometric information [101].…”

Section: Privacymentioning

confidence: 99%

Intelligent Interactive Technologies for Mental Health and Well-Being

Jovanovic

Jevremović

Pejović-Milovančević

2021

Artificial Intelligence: Theory and Applications

View full text Add to dashboard Cite

Mental healthcare has seen numerous benefits from interactive technologies and artificial intelligence. Various interventions have successfully used intelligent technologies to automate the assessment and evaluation of psychological treatments and mental well-being and functioning. These technologies include different types of robots, video games, and conversational agents. The paper critically analyzes existing solutions with the outlooks for their future. In particular, we: i) give an overview of the technology for mental health, ii) critically analyze the technology against the proposed criteria, and iii) provide the design outlooks for these technologies.

show abstract

“…Instance-based approaches are usually implemented using clustering algorithms or machine learning classifiers such as Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), or Decision Trees (DTs). Some studies have been conducted specifically using short digital texts such as Tweets [6], [16], [17], [18], [19], [30], [33], SMS [4], [5], or small pieces of texts from blog posts [35]. They are indicated in bold in Table 1.…”

Section: Literature Reviewmentioning

confidence: 99%

Writer Identification Using Microblogging Texts for Social Media Forensics

Alonso-Fernandez,

Belvisi,

Hernandez-Diaz

et al. 2020

Preprint

View full text Add to dashboard Cite

Establishing the authorship of online texts is a fundamental issue to combat several cybercrimes. Unfortunately, some platforms limit the length of the text, making the challenge harder. Here, we aim at identifying the author of Twitter messages limited to 140 characters. We evaluate popular stylometric features, widely used in traditional literary analysis, which capture the writing style at different levels (character, word, and sentence). We use a public database of 93 users, containing 1142 to 3209 Tweets per user. We also evaluate the influence of the number of Tweets per user for enrolment and testing. If the amount is sufficient (>500), a Rank 1 of 97-99% is achieved. If data is scarce (e.g. 20 Tweets for testing), the Rank 1 with the best individual feature method ranges from 54.9% (100 Tweets for enrolment) to 70.6% (1000 Tweets). By combining the available features, a substantial improvement is observed, reaching a Rank 1 of 70% when using 100 Tweets for enrolment and only 20 for testing. With a bigger hit list size, accuracy of the latter case increases to 86.4% (Rank 5) or 95% (Rank 20). This demonstrates the feasibility of identifying writers of digital texts, even with few data available.

show abstract

Exploiting Linguistic Style as a Cognitive Biometric for Continuous Verification

Cited by 12 publications

References 17 publications

Template Aging in Multi-Modal Social Behavioral Biometrics

Template Aging in Multi-Modal Social Behavioral Biometrics

Intelligent Interactive Technologies for Mental Health and Well-Being

Writer Identification Using Microblogging Texts for Social Media Forensics

Contact Info

Product

Resources

About