Stress level detection via OSN usage pattern and chronicity analysis: An OSINT threat intelligence module

Abstract Online Social Networks (OSN) are not only a popular communication and entertainment platform but also a means of self-representation. In this paper, we adopt an interdisciplinary approach combining Open Source Intelligence (OSINT) and user-generated content classification techniques with a user-driven stress test as applied to a Greek community of OSN users. The main goal of the paper is to study the chronicity of the stress level users experience, as depicted by OSN user generated content. In order to achieve that, we investigate whether collected data are able to facilitate the process of stress level detection. To this end, we perform unsupervised flat data classification of the user-generated content and formulate two working clusters which classify usage patterns that depict medium-to-low and medium-to-high stress levels respectively. To address the main goal of the paper, we divide user-generated content into chronologically defined sub-periods in order to study potential usage fluctuations over time. To this extent, we follow a process that includes (a) content classification into predefined categories of interest, (b) usage pattern metrics extraction and (c) metrics and clusters utilisation towards usage pattern fluctuation detection both through the prism of users' usual usage pattern and its correlation to the depicted stress level. Such an approach enables detection of time periods when usage pattern deviates from the usual and correlates such deviations to user experienced stress level. Finally, we highlight and comment on the emerging ethical issues regarding the classification of OSN user-generated content.

[1]  Irwin King,et al.  A brief survey of computational approaches in Social Computing , 2009, 2009 International Joint Conference on Neural Networks.

[2]  Shawn M. Bergman,et al.  Millennials, narcissism, and social networking: What narcissists do on social networking sites and why , 2011 .

[3]  Deborah A. Frincke,et al.  Social/Ethical Issues in Predictive Insider Threat Monitoring , 2011 .

[4]  Donald B. Rubin,et al.  Max-imum Likelihood from Incomplete Data , 1972 .

[5]  Munmun De Choudhury,et al.  The Nature of Emotional Expression in Social Media : Measurement , Inference and Utility , 2012 .

[6]  M. Maruish,et al.  The Use of Psychological Testing for Treatment Planning and Outcomes Assessment : Volume 1: General Considerations , 2004 .

[7]  Jenny Rosenberg,et al.  Online Impression Management: Personality Traits and Concerns for Secondary Goals as Predictors of Self-Presentation Tactics on Facebook , 2011, J. Comput. Mediat. Commun..

[8]  S. Joseph,et al.  Big 5 correlates of three measures of subjective well-being , 2003 .

[9]  Larry D. Rosen,et al.  Is Facebook creating "iDisorders"? The link between clinical symptoms of psychiatric disorders and technology use, attitudes and anxiety , 2013, Comput. Hum. Behav..

[10]  Dimitris Gritzalis,et al.  Proactive insider threat detection through social media: the YouTube case , 2013, WPES.

[11]  Teresa Correa,et al.  Who interacts on the Web?: The intersection of users' personality and social media use , 2010, Comput. Hum. Behav..

[12]  Lilian Mitrou,et al.  Which side are you on? A new Panopticon vs. privacy , 2013, 2013 International Conference on Security and Cryptography (SECRYPT).

[13]  Lisa Wise,et al.  Facebook and Diagnosis of Depression: A Mixed Methods Study , 2014 .

[14]  Tracii Ryan,et al.  Who uses Facebook? An investigation into the relationship between the Big Five, shyness, narcissism, loneliness, and Facebook usage , 2011, Comput. Hum. Behav..

[15]  Dimitris Gritzalis,et al.  An Insider Threat Prediction Model , 2010, TrustBus.

[16]  Fabrizio Sebastiani,et al.  Machine learning in automated text categorization , 2001, CSUR.

[17]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[18]  Cheri A. Levinson,et al.  Profiling Predicting Social Anxiety From Facebook Profiles , 2012 .

[19]  F. Kabre,et al.  The influence of facebook usage on the academic performance and the quality of life of college students , 2011 .

[20]  Cristina Alcaraz,et al.  Diagnosis mechanism for accurate monitoring in critical infrastructure protection , 2014, Comput. Stand. Interfaces.

[21]  Nir Friedman,et al.  Bayesian Network Classifiers , 1997, Machine Learning.

[22]  Helmut Krcmar,et al.  Big Data , 2014, Wirtschaftsinf..

[23]  J. Anderson,et al.  Penalized maximum likelihood estimation in logistic regression and discrimination , 1982 .

[24]  Ira S. Rubinstein,et al.  Big Data: The End of Privacy or a New Beginning? , 2013 .

[25]  Patricia S. Abril,et al.  Blurred Boundaries: Social Media Privacy and the Twenty‐First‐Century Employee , 2012 .

[26]  Clive Best,et al.  Open Source Intelligence , 2007, NATO ASI Mining Massive Data Sets for Security.

[27]  Kalyan Veeramachaneni,et al.  AI^2: Training a Big Data Machine to Defend , 2016, 2016 IEEE 2nd International Conference on Big Data Security on Cloud (BigDataSecurity), IEEE International Conference on High Performance and Smart Computing (HPSC), and IEEE International Conference on Intelligent Data and Security (IDS).

[28]  Lilian Mitrou,et al.  Can We Trust This User? Predicting Insider's Attitude via YouTube Usage Profiling , 2013, 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing.

[29]  Andrew McCallum,et al.  Efficient clustering of high-dimensional data sets with application to reference matching , 2000, KDD '00.

[30]  I. Pantic,et al.  Association between online social networking and depression in high school students: behavioral physiology viewpoint. , 2012, Psychiatria Danubina.

[31]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[32]  Richard Cumbley,et al.  Is "Big Data" creepy? , 2013, Comput. Law Secur. Rev..

[33]  Marc Rogers,et al.  Self-reported Deviant Computer Behavior: A Big-5, Moral Choice, and Manipulative Exploitive Behavior Analysis , 2006 .

[34]  Spiros Simitis.  Reconsidering the Premises of Labour Law: Prolegomena to an EU Regulation on the Protection of Employees' Personal Data , 1999 .

[35]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[36]  Bart W. Schermer,et al.  The limits of privacy in automated profiling and data mining , 2011, Comput. Law Secur. Rev..

[37]  A. Liu,et al.  A comparison of system call feature representations for insider threat detection , 2005, Proceedings from the Sixth Annual IEEE SMC Information Assurance Workshop.

[38]  D. Gritzalis,et al.  SOCIAL MEDIA PROFILING: A PANOPTICON OR OMNIOPTICON TOOL? , 2014 .

[39]  James E Boyd,et al.  Psychological test profiles of USAF pilots before training vs. type aircraft flown. , 2005, Aviation, space, and environmental medicine.

[40]  Tracy Packiam Alloway,et al.  Is Facebook Linked to Selfishness? Investigating the Relationships among Social Media Use, Empathy, and Narcissism , 2014 .

[41]  Lee A. Bygrave,et al.  A right to be forgotten? , 2014, Commun. ACM.

[42]  E. Eugene Schultz.  A framework for understanding and predicting insider attacks , 2002, Comput. Secur..

[43]  Yair Amichai-Hamburger,et al.  Social network use and personality , 2010, Comput. Hum. Behav..

[44]  Franck Dumortier.  Facebook and Risks of "De-contextualization" of Information , 2010, Data Protection in a Profiled World.

[45]  Craig Ross,et al.  Personality and motivations associated with Facebook use , 2009, Comput. Hum. Behav..

[46]  Christopher J. Carpenter,et al.  Narcissism on Facebook: Self-promotional and anti-social behavior , 2012 .

[47]  Rolph E. Anderson,et al.  Multivariate Data Analysis (7th ed. , 2009 .

[48]  M. Moreno,et al.  "Facebook depression?" social networking site use and depression in older adolescents. , 2012, The Journal of adolescent health : official publication of the Society for Adolescent Medicine.

[49]  Juliane M. Stopfer,et al.  Facebook Profiles Reflect Actual Personality, Not Self-Idealization , 2010, Psychological science.

[50]  Pushmeet Kohli,et al.  Personality and patterns of Facebook usage , 2012, WebSci '12.

[51]  Frank L. Greitzer,et al.  Identifying At-Risk Employees: Modeling Psychosocial Precursors of Potential Insider Threats , 2012, 2012 45th Hawaii International Conference on System Sciences.

[52]  Sotiris B. Kotsiantis,et al.  Supervised Machine Learning: A Review of Classification Techniques , 2007, Informatica.

[53]  Markus Jakobsson,et al.  Why and How to Perform Fraud Experiments , 2008, IEEE Security & Privacy.

[54]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[55]  Keven G. Ruby,et al.  The Insider Threat to Information Systems , 2022 .

[56]  Russell B. Clayton,et al.  Loneliness, anxiousness, and substance use as predictors of Facebook use , 2013, Comput. Hum. Behav..

[57]  John P A Ioannidis,et al.  Informed Consent, Big Data, and the Oxymoron of Research That Is Not Research , 2013, The American journal of bioethics : AJOB.

[58]  Abigail B Shoben,et al.  Does Consent Bias Research? , 2013, The American journal of bioethics : AJOB.

[59]  Jason Skues,et al.  Personality traits and Facebook use: The combined/interactive effect of Extraversion, Neuroticism and Conscientiousness , 2014 .

[60]  Daniele Quercia,et al.  The personality of popular facebook users , 2012, CSCW.

[61]  Oliver Brdiczka,et al.  Proactive Insider Threat Detection through Graph Learning and Psychological Context , 2012, 2012 IEEE Symposium on Security and Privacy Workshops.

[62]  Markus Jakobsson,et al.  Designing ethical phishing experiments: a study of (ROT13) rOnl query features , 2006, WWW '06.

[63]  Zeynep Tufekci,et al.  Big Data: Pitfalls, Methods and Concepts for an Emergent Field , 2013 .

[64]  Bing Liu,et al.  Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data , 2006, Data-Centric Systems and Applications.

[65]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[66]  Tim O'Reilly,et al.  What is Web 2.0: Design Patterns and Business Models for the Next Generation of Software , 2007 .

[67]  Lilian Mitrou,et al.  Insiders Trapped in the Mirror Reveal Themselves in Social Media , 2013, NSS.

[68]  Mark Batey,et al.  A tale of two sites: Twitter vs. Facebook and the personality predictors of social media usage , 2012, Comput. Hum. Behav..

[69]  A. Beck,et al.  An inventory for measuring clinical anxiety: psychometric properties. , 1988, Journal of consulting and clinical psychology.

[70]  Cristina Alcaraz,et al.  WASAM: A dynamic wide-area situational awareness model for critical domains in Smart Grids , 2014, Future Gener. Comput. Syst..

[71]  T. Graepel,et al.  Private traits and attributes are predictable from digital records of human behavior , 2013, Proceedings of the National Academy of Sciences.

[72]  Alex Pentland,et al.  Reality mining: sensing complex social systems , 2006, Personal and Ubiquitous Computing.