Towards a thematic dimensional framework of online fraud: An exploration of fraudulent email attack tactics and intentions

2023 | Decision Support Systems | Citations: 1

Authors: Bera, Debalina; Ogbanufe, Obi; Kim, Dan J.

Abstract: Despite anti-phishing filters, social engineering-based cyber-attacks still resu ... Expand

Abstract: Despite anti-phishing filters, social engineering-based cyber-attacks still result in billions of dollars lost annually, significant personal identity theft, loss of corporate secrets, and espionage. We review the phishing literature on psychological attacks and design tactics employed for deception by attackers. The result reveals the need to continuously identify tactics embedded in fraudulent email content to understand why users still fall prey to phishing attacks. Using the literature as a backdrop, we identify and conceptualize a thematic dimensional framework of fraudulent phishing attacks. This study uses benchmark datasets of fraudulent email to empirically validate the proposed dimensional framework. Specifically, a combination of machine learning-based content analysis and topic modeling found a majority of the discovered topics were labeled against the proposed di­ mensions. Statistical analysis was employed to provide empirical evidence of the thematic dimensions of fraudulent email attacks. This study thus, not only extends the cybersecurity literature by identifying and vali­ dating eight dimensions that enrich our understanding of phishing and attack identification but stimulates cu­ mulative research endeavors to develop yet more comprehensive dimensional frameworks of phishing email attacks. Collapse

Topics: phishing email phishing electronic mail email spam personalization

Methods: term frequency–inverse document frequency natural language processing topic model discriminant analysis literature study

How much is too much? The nonlinear link between emotional arousal and review helpfulness

2023 | Decision Support Systems | Citations: 0

Authors: Chou, Yen-Chun

Abstract: Online reviews affect consumer purchase decisions and become prevalent in differ ... Expand

Abstract: Online reviews affect consumer purchase decisions and become prevalent in different sectors. Platforms elicit useful reviews by allowing consumers to vote for helpfulness. The link between review features and review helpfulness hence has been a topic of broad interest in information systems (IS) and Internet commerce. Psy­ chological science studies show that expressed emotions in information – valence and arousal significantly in­ fluence receivers’ engagement and valuation. Unlike valence (negative or positive) that is widely-analyzed, emotional arousal is a less-studied attribute of online reviews. This study presents a careful account of the nonlinear link between emotional arousal and review helpfulness. Following a rigorous procedure of theorizing and testing nonlinear relationships (Haans et al. 2016), we articulate latent mechanisms leading to an inverted Ushaped association and how valence would moderate the nonlinear effect of review arousal. We analyze reviews on experience goods from Yelp.com and find firm support for our hypotheses. The findings are triangulated using reviews on search goods from Amazon.com. While the nonlinear effect of review arousal and interactions with review valence are robust to both types of goods, an alternative moderation path of review valence on the inverted U-shaped relationship is observed. Our empirical study contributes to the literature by shedding lights on the dynamics among arousal, valence, review helpfulness, and product types, which illustrates a prototypical example to IS/e-commerce scholars on rigorously conceptualizing and estimating U-shaped links as well as their moderations. Collapse

Topics: tablet experience good online review user-generated content electronic commerce

Methods: theory development product review triangulation sentiment analysis reference modelling

Coastal Resilience with Social Data Analytics: A Design Science Approach

2023 | International Conference on Information Systems | Citations: 0

Authors: Lee, Carol; Yoon, YoungHo; Bharati, Pratyush

Abstract: ... Expand

Abstract: Collapse

Topics: Twitter individual impact decision making privacy user interface

Methods: design science topic model design artifact design principle natural language processing

Elaboration likelihood model, endogenous quality indicators, and online review helpfulness

2022 | Decision Support Systems | Citations: 7

Authors: Chou, Yen-Chun; Chuang, Howard Hao-Chun; Liang, Ting-Peng

Abstract: Given strong influences of online customer reviews on consumer purchase decision ... Expand

Abstract: Given strong influences of online customer reviews on consumer purchase decisions, identifying helpful reviews has received broad attention from practitioners and researchers. The elaboration likelihood model (ELM) has been adopted to explain the review feature–helpfulness link. However, when analyzing reviews from websites, existing studies tend to ignore that quality indicators such as length and readability are merely cues and have not circumvented endogeneity induced by unseen argument quality. Hence, we propose an extended ELM applica­ tion to observational data on review helpfulness. We develop a research model that integrates relevant quality indicators and sentiment features based on a circumplex model of affect. To test our hypotheses, we use pub­ lically available review datasets from three platforms (Amazon.com, Drugs.com, and Yelp.com) and adopt an instrument-free method that allows for arbitrary correlations between unseen argument quality and multiple endogenous indicators. Our analysis shows that ignoring endogeneity would result in invalid effect size and hypothesis-testing. In addition to identifying effects of endogenous quality indicators on review helpfulness, we find asymmetric effects of positive and negative valence contingent on low or high arousal. By articulating conceptual pitfalls and illustrating empirical remedies, our study aims to be a prototypical example of performing ELM-grounded analyses of online customer reviews. Collapse

Topics: tablet online review user-generated content electronic commerce website

Methods: product review regression analysis method statistical hypothesis test topic model sentiment analysis

Theories: elaboration likelihood model

Coastal Resilience Decision Making with Machine Learning

2022 | Americas Conference on Information Systems | Citations: 2

Authors: Lee, Carol; Yoon, YoungHo; Bharati, Pratyush

Abstract: Our research aims to understand how social data can be integrated with climate ... Expand

Abstract: Our research aims to understand how social data can be integrated with climate data using machine learning for coastal resilience decisions. Although data analytics techniques have been adapted for decision models, incorporating unstructured data is a challenge. We adapt a design science research approach to develop a coastal resilience decision model that can accommodate various sets of climate criteria and social attributes to help us understand coastal risks in communities vulnerable to coastal hazards. We collected social data from environmental groups and individuals and conducted an exploratory social media data analysis on coastal resilience in the greater Boston, U.S., area. We employ non-negative matrix factorization (NMF), a topic modeling technique, to extract human-interpretable topics from a preliminary dataset of 131 documents from 50 different accounts. The outcomes of this research can help community members and policy makers understand and develop robust sustainability and climate focused decisions. Collapse

Topics: social media climate change decision making Twitter Facebook

Methods: non negative matrix factorization data transformation topic model design artifact design science

Use of Electronic Word of Mouth as Quality Metrics: A Comparison of Airline Reviews on Twitter and Skytrax

2022 | HICSS | Citations: 0

Authors: Lu, Lin; Mitra, Amit; Wang, Yen-Yao; Wang, Yu; Xu, Pei

Abstract: User-generated content (UGC) at online platforms serves as a critical data sourc ... Expand

Abstract: User-generated content (UGC) at online platforms serves as a critical data source in the service industry as it can be accessed in real-time and reflect customers’ changing focus on service aspects. Drawing upon the importance-performance analysis framework, we propose a methodology to derive service quality metrics by utilizing the heterogeneous sources of UGC with customized text mining techniques and examining the effectiveness of these quality metrics. UGC data related to major U.S. airlines were collected from non-social media (Skytrax) and social media platforms (Twitter) from 2014 to June 2019. The results suggest that the topic distributions and the UGC-derived weighted service quality (WSQ, which represents the weighted sentiment based on service aspects) significantly vary between the non-social media and social media platforms. In addition, the WSQ scores derived from two platforms are significant indicators of the objective service quality measurement (i.e., airline quality rating) with stronger predictive power from the social media derived WSQ score. Collapse

Topics: social media Twitter service quality online review user-generated content

Methods: topic model sentiment analysis chi squared test parametric test paired t-test

How Network Embeddedness Affects Real-Time Performance Feedback: An Empirical Investigation

2022 | Information Systems Research | Citations: 0

Authors: Petryk, Mariia; Rivera, Michael; Bhattacharya, Siddharth; Qiu, Liangfei; Kumar, Subodha

Abstract: Firms and organizations are increasingly using real-time performance feedback me ... Expand

Abstract: Firms and organizations are increasingly using real-time performance feedback mechanisms to evaluate employees, where any employee (rather than just the supervisor) can rate other employees. Hence, a need arises to better understand how network positions of employees in such a system impact their performance. Analyzing nearly 4,000 feedback instances from employees at five major organizations that use such a real-time performance feedback application called DevelapMe, we explore the effects of network embeddedness—or the nature of relationships among employees—on performance rating scores according to two dimensions of embeddedness: (i) positional, the position of an individual in the emerging network of performance ratings, and (ii) structural, the extent to which a person is entrenched in a network of relationships. We visualize rating networks within organizations: Employees are nodes, and connections between nodes exist if an evaluation between the pair occurs. We find that specific aspects of network embeddedness affect performance rating scores differently. In particular, a rater’s positional embeddedness (measured by eigenvector centrality) is positively associated with the rating score he or she gives others. However, a rater’s structural embeddedness (measured by outdegree centrality) is negatively associated with the rating score he or she gives. We also uncover the moderating effects of anonymity and hierarchy on the role of network embeddedness, as well as the sentiment of the textual comments provided with feedback. Our findings have important implications for the design of performance management systems using network analysis. History: Param Singh, Senior Editor; Zhengrui Jiang, Associate Editor. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2022.1110. Collapse

Topics: anonymity peer-to-peer model social network individual productivity social influence

Methods: experimental group propensity score method network analysis robustness check propensity score matching

Theories: social network theory

Uncovering Thematic Dimensions of Fraudulent Emails using Topic Modelling

2021 | Americas Conference on Information Systems | Citations: 0

Authors: Bera, Debalina; Kim, Dan

Abstract: Recently, research on fraudulent email detection has expanded from its purely t ... Expand

Abstract: Recently, research on fraudulent email detection has expanded from its purely technological orientation into understanding the role of human behavior in security breaches. However, an area that has been lacking is literature/theory-grounded content analysis in social engineering threat. While there exists an extensive body of anecdotal subjective literature, factors that account for phishing attack's incessant success remain largely speculative. To better understand this, we propose a dimensional framework to identify the thematic nature of phishing emails that would not only help to understand the underlining technical subterfuge but also enhance our knowledge to effectively sense contextual social engineering tricks and the nature of such attacks, from multiple angles. To validate the dimensional elements, we will employ topic modeling techniques to analyze the themes of fraudulent email attack utilizing four benchmark datasets. Based on the analysis, this study discusses theoretical contributions and practical recommendations along with further directions of the research. Collapse

Topics: email phishing phishing email spam electronic mail IT security

Methods: topic model term frequency–inverse document frequency logistic regression k-means clustering self organizing map

The Impact of Helping Others in Coopetitive Crowdsourcing Communities

2021 | Journal of the Association for Information Systems | Citations: 9

Authors: Dissanayake, Indika; Nerur, Sridhar; Wang, Jingguo; Yasar, Mahmut; Zhang, Jie

Abstract: Organizations are increasingly engaging the community through crowdsourcing plat ... Expand

Abstract: Organizations are increasingly engaging the community through crowdsourcing platforms to evolve innovative solutions to challenging business problems. Participants on such platforms often simultaneously cooperate and compete with one another to earn top honors. This paper addresses the imperative to understand the dynamics of knowledge sharing in such a coopetitive environment. Specifically, our study relies on the conceptual foundations of social exchange and social capital theories to investigate how help rendered (e.g., exchanging ideas or sharing knowledge) by participants in an online coopetitive crowdsourcing setting affects their performance. Furthermore, the study examines the moderating effects of the intensity of competition. Results of our econometrics analyses suggest that help given in a highly competitive contest, as opposed to a less competitive one, is more likely to be reciprocated, but less likely to improve the contributor’s contest performance. In addition, our study found that help received by participants positively impacts their contest performance, and partially mediates the relationship between help rendered and contest performance. This research also provides insight into what motivates participants to share knowledge under conditions of coopetition. The findings of our study have strong implications for both theory and practice. Collapse

Topics: crowdsourcing knowledge sharing social capital online community open source

Methods: instrumental variables estimation machine learning data transformation robustness check theoretical contribution

Theories: social exchange theory social capital theory

Measuring Sustainability through Textual Analysis

2021 | International Conference on Information Systems | Citations: 0

Authors: Maibaum, Frederik; Foege, Johann Nils

Abstract: The global climate crisis makes the transition towards a sustainable society th ... Expand

Abstract: The global climate crisis makes the transition towards a sustainable society the central challenge of our time. Such a transition is only possible if the global economy engages substantial efforts to reduce its ecological footprint. While IS scholars agree that it is important to identify organizational change activities that support such a sustainable development, it remains challenging to capture firms' sustainability in a quantitative, longitudinal way. In this paper, we describe the development of a text-based measure for firms' sustainability that enables us to assess how IS affect firms' sustainability in a longitudinal setting. Our approach uses machinelearning textual analysis to create a sustainability dictionary that we use to calculate a sustainability score based on 10-k filings and earnings calls for S&P 500 firms from 1994 to 2017. This score will allow us to better understand the sustainability implications of (green) IS. Collapse

Topics: database system green IS high-performance computing organization structure digital innovation

Methods: topic model longitudinal research qualitative content analysis survey computational algorithm