The insider on the outside: a novel system for the detection of information leakers in social networks

Abstract

Confidential information is all too easily leaked by naive users posting comments. In this paper we introduce DUIL, a system for Detecting Unintentional Information Leakers. The value of DUIL is in its ability to detect those responsible for information leakage that occurs through comments posted on news articles in a public environment, when those articles have withheld material nonpublic information. DUIL is comprised of several artifacts, each designed to analyse a different aspect of this challenge: the information, the user(s) who posted the information, and the user(s) who may be involved in the dissemination of information. We present a design science analysis of DUIL as an information system artifact comprised of social, information, and technology artifacts. We demonstrate the performance of DUIL on real data crawled from several Facebook news pages spanning two years of news articles.

The many faces of social media in business and economics research: Taking stock of the literature and looking into the future

“…Individual level . Studies investigating social media as a societal challenge at the individual level have concentrated on cyberbullying (Chan et al., 2019; Wong et al., 2021), well‐being (Allcott et al., 2020; Krasnova et al., 2015), addiction (Allcott et al., 2022; Bhargava & Velasquez, 2021; Osatuyi & Turel, 2020), and privacy issues (Acquisti et al., 2020; Cascavilla et al., 2018; Ong et al., 2022; Quach et al., 2022). Overall, research on cyberbullying has focused more on individual‐level psychological predictors (e.g., cognitive processes of bullies) and macro‐level predictors (e.g., environmental factors) than on IT artifacts; however, the latter have been the focus of more recent research (Lowry et al., 2016).…”

“…Finally, in the area of privacy research, the extant findings suggest that rather than being careless, most users are not aware of privacy issues (Ozdemir et al., 2017; Tow et al., 2010) and are not capable of attaining the desired levels of privacy (Acquisti et al., 2020). In this regard, research has developed systems to detect unintentional information leakage (e.g., in the context of Facebook comments; Cascavilla et al., 2018).…”

The Research Method we Need or Deserve? A Literature Review of the Design Science Research Landscape

“…However, examining these articles (c.f. Cascavilla et al, 2018;Pentland et al, 2017;Venkatesh, Aloysius, Hoehle, & Burton, 2017), it is possible to identify a contribution of significant results versus a contribution of significant theory, the latter being the barometer for assessing the level of knowledge contributions (Gregor & Hevner, 2013).…”

Developing data analytics capabilities: integrating the information systems success model and the resource-based view

“…Such systems' hardware is important to data collection and storage, ensuring an efficient data flow for business organizations. Data systems' software is also essential for business organizations to integrate different systems or technologies, create and run algorithms, visualize data, and scale their computing needs (Cascavilla et al, 2018). Additionally, distributed infrastructure is essential to setting up a data pipeline, supporting data analytics, and scaling data analytics' development.…”