A text summary-based method to detect new events from streams of online news articles

2022 | Information & Management | Citations: 0

Authors: Lee, Yen-Hsien; Wei, Chih-Ping; Hu, Paul Jen-Hwa; Wu, Pao-Feng; Jiang, How

Abstract: New event detection (NED), which is crucial to firms’ environmental surveillance ... Expand

Abstract: New event detection (NED), which is crucial to firms’ environmental surveillance, requires timely access to and effective analysis of live streams of news articles from various online sources. These news articles, available in unprecedent frequency and quantity, are difficult to sift through manually. Most of existing techniques for NED are full-text-based; typically, they perform full-text analysis to measure the similarity between a new article and previous articles. This full-text-based approach is potentially ineffective, because a news article often contains sentences that are less relevant to define the focal event being reported and the inclusion of these less relevant sentences into the similarity estimation can impair the effectiveness of NED. To address the limitation of the fulltext-based approach and support NED more effectively and efficiently, this study proposes and develops a summary-based event detection method that first selects relevant sentences of each article as a summary, then uses the resulting summaries to detect new events. We empirically evaluate our proposed method in comparison with some prevalent full-text-based techniques, including a vector space model and two deep-learning-based models. Our evaluation results confirm that the proposed method provides greater utilities for detecting new events from online news articles. This study demonstrates the value and feasibility of the text summarization approach for generating news article summaries for detecting new events from live streams of online news ar­ ticles, proposes a new method more effective and efficient than the benchmark techniques, and contributes to NED research in several important ways. Collapse

Topics: digital news domain-specific language website computer virus evaluation criteria

Methods: BERT deep learning cluster analysis decision tree classification supervised learning

Local learning from municipal ransomware attacks: A geographically weighted analysis

2021 | Information & Management | Citations: 0

Authors: Marett, Kent; Nabors, Misty

Abstract: The prevalence of security threats like ransomware continues to increase and vic ... Expand

Abstract: The prevalence of security threats like ransomware continues to increase and victimize a wide range of targets, which includes municipal information systems. These attacks are commonly reported in media outlets available in attacked communities. This study seeks to understand how effective news reporting can be toward influencing the behavior of people who live within the proximity of the attack. The results suggest a geographic influence on individual behaviors that could well extend beyond the context of information security into other areas of behavioral IS research. Collapse

Topics: ransomware data security IT security IT security threat website

Methods: autocorrelation analysis analysis of covariance longitudinal research regression analysis method cluster analysis

Local Learning from Municipal Ransomware Attacks

2020 | Americas Conference on Information Systems | Citations: 0

Authors: Marett, Kent; Nabors, Misty

Abstract: Ransomware is not only the bane of private businesses and publicly-traded compa ... Expand

Abstract: Ransomware is not only the bane of private businesses and publicly-traded companies, it has steadily targeted municipal governmental entities over the past couple of years. Such attacks can cripple a city's ability to provide services and support for its residents. Since these attacks are reported upon in the press, do an attacked community's citizens change their behavior in the wake of the attack?In this study, the security precautions being taken by residents within 20 miles of an attacked community were compared with Internet users living further away from the attacks. Using spatial analysis software like ArcGIS and GWR, we analyzed the data procured from an online survey of American Internet users and found that local learning complements users' prior victimization from cybercrime and their own selfinterest to influence their cautious behavior online. KeywordsRansomware, spatial analysis, precautionary behavior, local learning. Collapse

Topics: ransomware IT security threat IT security internet technology social media

Methods: analysis of covariance survey regression analysis method cross sectional survey digital trace data

Effects of sanctions, moral beliefs, and neutralization on information security policy violations across cultures

2020 | Information & Management | Citations: 12

Authors: Vance, Anthony; Siponen, Mikko T.; Straub, Detmar W.

Abstract: A principal concern of organizations is the failure of employees to comply with ... Expand

Abstract: A principal concern of organizations is the failure of employees to comply with information security policies (ISPs). Deterrence theory is one of the most frequently used theories for examining ISP violations, yet studies using this theory have produced mixed results. Past research has indicated that cultural differences may be one reason for these inconsistent findings and have hence called for cross-cultural research on deterrence in information security. To address this gap, we formulated a model including deterrence, moral beliefs, shame, and neutralization techniques and tested it with the employees from 48 countries working for a large multinational company. Collapse

Topics: national culture cross cultural research security policy computer virus laptop computer

Methods: theory development partial least squares regression structural equation modeling survey parametric test

Theories: deterrence theory cultural dimensions theory neutralization theory

See No Evil, Hear No Evil? Dissecting the Impact of Online Hacker Forums

2019 | Management Information Systems Quarterly | Citations: 26

Authors: Yue, Wei T.; Qiu-Hong Wang; Kai-Lung Hui

Abstract: Online hacker forums offer a prominent avenue for sharing hacking knowledge. Usi ... Expand

Abstract: Online hacker forums offer a prominent avenue for sharing hacking knowledge. Using a field dataset culled from multiple sources, we find that online discussion of distributed denial of service (DDOS) attacks in hackforums.net decreases the number of DDOS-attack victims. A 1% increase in discussion decreases DDOS attacks by 0.032% to 0.122%. This means that two DDOS-attack posts per day could reduce the number of victims by 700 to 2,600 per day. We find that discussion topics with similar keywords can variously increase or decrease DDOS attacks, meaning we cannot ascertain the impact of the discussion just by the post nature. Mentioning botnets, especially new botnets, increases the attacks, but the follow-up discussion decreases the attacks. Our results suggest that online-hacker-forum discussion may exhibit the dual-use characteristic. That is, it can be used for both good and bad purposes. We draw related managerial implications. Collapse

Topics: denial of service attack internet technology computer virus Python open source

Methods: term frequency–inverse document frequency latent dirichlet allocation forums posting qualitative content analysis topic model

Software Diversity for Improved Network Security: Optimal Distribution of Software-Based Shared Vulnerabilities

2017 | Information Systems Research | Citations: 0

Authors: Temizkan, Orcun; Park, Sungjune; Saydam, Cem

Abstract: Firms, and other agencies, tend to adopt widely used software to gain economic b ... Expand

Abstract: Firms, and other agencies, tend to adopt widely used software to gain economic benefits of scale, which can lead to a software monoculture. This can, in turn, involve the risk of correlated computer systems failure as all systems on the network are exposed to the same software-based vulnerabilities. Software diversity has been introduced as a strategy for disrupting such a monoculture and ultimately decreasing the risk of correlated failure. Nevertheless, common vulnerabilities can be shared by different software products. We thus expand software diversity research here and consider shared vulnerabilities between different software alternatives. We develop a combinatorial optimization model of software diversity on a network in an effort to identify the optimal software distribution that best improves network security. We also develop a simulation model of virus propagation based on the susceptible-infected-susceptible model. This model allows calculation of the epidemic threshold, a measure of network resilience to virus propagation. We then test the effectiveness of the proposed software diversity strategies against the spreading of viruses through a series of experiments. Collapse

Topics: pandemic corporate network security cloud computing IT security threat computer virus

Methods: computational algorithm simulation experiment optimization model linear optimization

Theories: information theory

‘Breaching’ Auditor Judgments of Information Security Effectiveness

2014 | International Conference on Information Systems | Citations: 0

Authors: Basoglu, K Asli; D’Arcy, John

Abstract: In this in-progress study we explore whether aspects of a prior data security br ... Expand

Abstract: In this in-progress study we explore whether aspects of a prior data security breach, along with prior audit performance, work to decrease auditor objectivity of information security (InfoSec) weaknesses in the subsequent audit period. We use SOX Section 404 as the contextual setting and our analysis is based on a unique dataset from publicly available sources. Preliminary results suggest that not only does former audit performance influence auditor judgments of InfoSec performance, but also the strength of this relationship changes based on public attention. We found no evidence for the influence of past breach severity on auditors’ judgments nor did we find that the influence of public attention is direct. Instead, it appears that auditors can be lured toward decreased objectivity in an indirect manner, based on the weight of public attention that increases their desire to validate past audit evaluations. Implications and plans for future research are discussed. Collapse

Topics: data breach Google+ Sarbanes–Oxley Act internet technology search engine

Methods: event study statistical hypothesis test descriptive statistic cross sectional survey

Capturing the essence of word-of-mouth for social commerce: Assessing the quality of online e-commerce reviews by a semi-supervised approach

2013 | Decision Support Systems | Citations: 0

Authors: Zheng, Xiaolin; Zhu, Shuai; Lin, Zhangxi

Abstract: In e-commerce, online product reviews significantly influence the purchase decis ... Expand

Abstract: In e-commerce, online product reviews significantly influence the purchase decisions of buyers and the marketing strategies employed by vendors. However, the abundance of reviews and their uneven quality make distinguishing between useful and useless reviews difficult for potential customers, thereby diminishing the benefits of online review systems. To address this problem, we develop a semi-supervised system called Online Review Quality Mining (ORQM). Embedded with independent component analysis and semi-supervised ensemble learning, ORQM exploits two opportunities: the improvement of classification performance through the use of a few labeled instances and numerous unlabeled instances, and the effectiveness of the social characteristics of e-commerce communities as identifiers of influential reviewers who write high-quality reviews. Three complementary experiments on datasets from Amazon.com show that ORQM exhibits remarkably higher performance in classifying reviews of different quality levels than do other well-accepted state-of-the-art text mining methods. The high performance of ORQM is also consistent and stable even under limited availability of labeled instances, thereby outperforming other baseline methods. The experiments also reveal that (1) the social features of reviewers are important in deriving better classification results; (2) classification results are affected by product type given the different purchase habits of consumers; and (3) reviews are contingent on the inherent nature of products, such as whether they are search goods or experience goods, and digital products or physical products, through which purchase decisions are influenced. Collapse

Topics: online review user-generated content social network spamming experience good

Methods: experiment support vector machine machine learning computational algorithm ensemble learning

Information Security Risk Management: In Which Security Solutions Is It Worth Investing?

2011 | Communications of the Association for Information Systems | Citations: 0

Authors: Fenz, Stefan; Ekelhart, Andreas; Neubauer, Thomas

Abstract: As companies are increasingly exposed to information security threats, decision ... Expand

Abstract: As companies are increasingly exposed to information security threats, decision makers are permanently forced to pay attention to security issues. Information security risk management provides an approach for measuring the security through risk assessment, risk mitigation, and risk evaluation. Although a variety of approaches have been proposed, decision makers lack well-founded techniques that (1) show them what they are getting for their investment, (2) show them if their investment is efficient, and (3) do not demand in-depth knowledge of the IT security domain. This article defines a methodology for management decision makers that effectively addresses these problems. This work involves the conception, design, and implementation of the methodology into a software solution. The results from two qualitative case studies show the advantages of this methodology in comparison to established methodologies. Collapse

Topics: knowledge representation business process management data security information security risk risk management

Methods: case study ontological modelling literature study Bayesian network business process modeling

The Economic Effect of Privacy Breach Announcements on Stocks: A Comprehensive Empirical Investigation

2011 | Americas Conference on Information Systems | Citations: 0

Authors: Nicholas-Donald, Aurelia; Matus, Jesus Francisco; Ryu, SeungEui; Mahmood, Adam M

Abstract: The 2009 CSI Computer Crime and Security Survey indicate that the financial frau ... Expand

Abstract: The 2009 CSI Computer Crime and Security Survey indicate that the financial fraud costs about $450,000 per victim organization. A comprehensive empirical investigation was conducted on the effect of publicly announced privacy breaches on the market value of breached companies. We use the abnormal returns, risk factors, and volumes to measure the market effect on the breached firms. Our results show that the cumulative abnormal return (CAR) due to a privacy breach is -1.5 percent at the .05 level. Our results also show that the mean risk factor for the breached firms increases by about 4 percent on the event day compare to the 250 pre-event days Finally, our results show that the volume of the event stocks are higher during the event days relative to the pre-event 60 days. None of the research studies in the information privacy breach area has investigated the abnormal risk and abnormal volume patterns around the privacy breach announcements. Collapse

Topics: privacy website computer virus denial of service attack IT security threat

Methods: event study longitudinal research LexisNexis