Explore the vast range of titles available.

The past few years have witnessed millions of credit/debit cards flowing through the underground economy and ultimately causing significant financial loss. Examining key underground economy sellers has both practical and academic significance for cybercrime forensics and criminology research. Drawing on social media analytics, we have developed the AZSecure text mining system for identifying and profiling key sellers. The system identifies sellers using sentiment analysis of customer reviews and profiles sellers using topic modeling of advertisements. We evaluated the AZSecure system on eight international underground economy forums. The system significantly outperformed all benchmark machine-learning methods on identifying advertisement threads, classifying customer review sentiments, and profiling seller characteristics, with an average F-measure of about 80 percent to 90 percent. In our case study, we identified the famous carder, Rescator, who was affiliated with the Target breach, and captured important seller characteristics in terms of product type, payment options, and contact channels. Our research leverages social media analytics to probe into the underground economy in order to help law enforcement target key sellers and prevent future fraud. It also contributes to our understanding of the use of information technology in detecting deception in online systems.

Trust is frequently investigated as an indicator of a mutual relationship. Trust is especially important for globally distributed collaboration in light of the lack of face-to-face interactions. As the perception of trust is a dynamic process, however, little research is conducted measuring trust development. Whether facilitation intervention is beneficial for trust development is also unknown. In order to fill the research gaps, we followed a design science approach and incorporated collaboration engineering into the design of the treatment. Data were collected in a series of experiments with Chinese and U.S. mixed teams, including a longitudinal survey, interviews, and documentation. Through the comparison of the treatment group with the control group, we found that trust was significantly improved in the treatment group. In addition, several trust antecedents were found to explain the development. The power of facilitated collaboration is also validated as helpful for trust development. This research makes several implications, such as proposing a series of trust antecedents, a treatment design of a collaboration engineering (CE) approach for trust improvement, and a new context application of CE. This research could also help the practitioners in globally distributed collaboration who want to improve trust over time.

Social media communications offer valuable feedback to firms about their brands. We present a targeted approach to Twitter sentiment analysis for brands using supervised feature engineering and the dynamic architecture for artificial neural networks. The proposed approach addresses challenges associated with the unique characteristics of the Twitter language and brand-related tweet sentiment class distribution. We demonstrate its effectiveness on Twitter data sets related to two distinctive brands. The supervised feature engineering for brands offers final tweet feature representations of only seven dimensions with greater feature density. Reducing the dimensionality of the representations reduces the complexity of the classification problem and feature sparsity. Two sets of experiments are conducted for each brand in three-class and five-class tweet sentiment classification. We examine five-class classification to target the mild sentiment expressions that are of particular interest to firms and brand management practitioners. We compare the proposed approach to the performances of two state-of-the-art Twitter sentiment analysis systems from the academic and commercial domains. The results indicate that it outperforms these state-of-the-art systems by wide margins, with classification F 1 -measures as high as 88 percent and excellent recall of tweets expressing mild sentiments. Furthermore, they demonstrate the tweet feature representations, though consisting of only seven dimensions, are highly effective in capturing indicators of Twitter sentiment expression. The proposed approach and vast majority of features identified through supervised feature engineering are applicable across brands, allowing researchers and brand management practitioners to quickly generate highly effective tweet feature representations for Twitter sentiment analysis on other brands.

Information systems (IS) integration is a critical challenge for value-creating mergers and acquisitions. Appropriate design and implementation of IS integration is typically a precondition for enabling a majority of the anticipated business benefits of a combined organization. Often, IS integration projects are subject to deficiencies (e.g., loss of the target firm's business capabilities with expedited integration) that limit value creation. Drawing on a configurational perspective, we reanalyze 37 published case studies of problematic IS integrations and identify the potential deficiencies and how they are produced. Our findings reveal nine causal configurations that together explain deficiency as a consequence of multiple paths of interconnected mechanisms and contextual conditions that drive their actualization. Finally, based on a post hoc analysis of 25 cases where no negative outcomes are reported, we discuss approaches for managing IS integration to avoid realizing the actualization of deficiencies.

This article studies the strategic network formation in a location-based social network. We build an empirical model of social link creation that incorporates individual characteristics and pairwise user similarities. Specifically, we define four user proximity measures from biography, geography, mobility, and short messages. To construct proximity from unstructured text information, we build topic models using Latent Dirichlet Allocation. Using Gowalla data with 385,306 users, 3 million locations, and 35 million check-in records, we empirically estimate the model to find evidence on the homophily effect on network formation. To cope with possible endogeneity issues, we use exogenous weather shocks as our instrumental variables and find the empirical results are robust: network formation decisions are significantly affected by our proximity measures.