Visualizing the Maturing Global API Ecosystem

2022 | HICSS | Citations: 1

Authors: Heshmatisafa, Saeid; Huhtamäki, Jukka; Seppänen, Marko

Abstract: Platform boundary resources are prominent digital strategy tools for companies t ... Expand

Abstract: Platform boundary resources are prominent digital strategy tools for companies to disclose business assets to partners and consumers. However, the platform boundary resources of API ecosystems are dependent on API usage and characteristics as well as the social environment around them. This study focuses on the global API ecosystem guided by two assumptions: 1) geographic proximity is distorted, and the global API ecosystem is decentralized in a digitally connected world, and 2) open co-innovation is somewhat prone to geographic nearness and centralized. A data-driven network analysis was utilized to depict the global and regional geolocation of more than 22,000 APIs and 6,000 mashups. First, the global locations of API providers were examined. Next, the connectivity of API mashups at global and regional levels was studied. The findings suggest that APIs are distributed globally, and the API ecosystem has moved from emerging to mature; however, the distribution is skewed towards entrepreneurial regions in North America. Finally, the theoretical and managerial implications are discussed. Collapse

Topics: application programming interface Python productivity missing data Tableau software

Methods: computational algorithm exploratory data analysis cluster analysis network analysis

Fraudulent review detection model focusing on emotional expressions and explicit aspects: investigating the potential of feature engineering

2022 | Decision Support Systems | Citations: 5

Authors: Kumar, Ajay; Gopal, Ram D.; Shankar, Ravi; Tan, Kim Hua

Abstract: Reading customer reviews before purchasing items online has become a common prac ... Expand

Abstract: Reading customer reviews before purchasing items online has become a common practice; however, some companies use machine learning (ML) algorithms to generate false reviews in order to create positive brand images of their own products and negative images of competitors' offerings. Existing techniques use review content to identify fraudulent reviewers; however, spammers become more intelligent, started to learn from their mistakes, and changed their tactics in order to avoid detection techniques. Thus, investigating fraudulent ac­ counts' behaviour of generating fake negative or positive reviews for competitors or themselves and the necessity of ML classifiers to identify fraudulent reviews, is more important than ever. In this research, we present a novel feature engineering approach in which we (1) extract several “review-centric” and “reviewer-centric” features from a dataset; (2) combine the cumulative effects of features distributions into a unified model that represents overall behavior of the fraudulent reviewers; (3) investigate the role of effective data pre-processing to improve detection accuracy; and (4) develop a probabilistic approach to detect fraudulent reviewers by learning a novel M-SMOTE model over a derived balanced dataset and feature distributions, which outperforms other ML models. Our study contributes to the literature on digital platforms and fraudulent review detection with significant managerial and theoretical implications through these novel findings. Collapse

Topics: online review electronic commerce website marketing management logistics management

Methods: feature engineering machine learning computational algorithm XGBoost product review

Collaborating with Virtual Assistants in Organizations: Analyzing Social Loafing Tendencies and Responsibility Attribution

2022 | Information Systems Frontiers | Citations: 3

Authors: Stieglitz, Stefan; Mirbabaie, Milad; Möllmann, Nicholas R. J.; Rzyski, Jannik

Abstract: Organizations increasingly introduce collaborative technologies in form of virtu ... Expand

Abstract: Organizations increasingly introduce collaborative technologies in form of virtual assistants (VAs) to save valuable resources, especially when employees are assisted with work-related tasks. However, the effect of VAs on virtual teams and collaboration remains uncertain, particularly whether employees show social loafing (SL) tendencies, i.e., applying less effort for collective tasks compared to working alone. While extant research indicates that VAs collaboratively working in teams exert greater results, less is known about SL in virtual collaboration and how responsibility attribution alters. An online experiment with N = 102 was conducted in which participants were assisted by a VA in solving a task. The results indicate SL tendencies in virtual collaboration with VAs and that participants tend to cede responsibility to the VA. This study makes a first foray and extends the information systems (IS) literature by analyzing SL and responsibility attribution thus updates our knowledge on virtual collaboration with VAs. Collapse

Topics: virtual teamwork brainstorming personality team productivity IT enabled teamwork

Methods: descriptive statistic experiment survey survey design statistical power analysis

An Exploratory Study on Fairness-Aware Design Decision-Making

2022 | HICSS | Citations: 0

Authors: Tanu, Sumaiya Sultana; Zhang, Lu; Gauri, Dinesh; Sha, Zhenghui

Abstract: With advances in machine learning (ML) and big data analytics, data-driven predi ... Expand

Abstract: With advances in machine learning (ML) and big data analytics, data-driven predictive models play an essential role in supporting a wide range of simple and complex decision-making processes. However, historical data embedded with unfairness may unintentionally reinforce discrimination towards minority groups when using data-driven decisionsupport technologies. In this paper, we quantify unfairness and analyze its impact in the context of datadriven engineering design using the Adult Income dataset. First, we introduce a fairness-aware design concept. Subsequently, we introduce standard definitions and statistical measures of fairness to the engineering design research. Then, we use the outcomes from two supervised ML models, Logistic Regression and CatBoost classifiers, to conduct the Disparate Impact and fair-test analyses to quantify any unfairness present in the data and decision outcomes. Based on the results, we highlight the importance of considering fairness in product design and marketing, and the consequences, if there is a loss of fairness. Collapse

Topics: shapley additive explanation marketing management decision making decision support system advertising management

Methods: binary classification case study design science logistic regression archival research

Redefining profit metrics for boosting student retention in higher education

2021 | Decision Support Systems | Citations: 2

Authors: Maldonado, Sebastián; Miranda, Jaime; Olaya, Diego; Vásquez, Jonathan; Verbeke, Wouter

Abstract: Student dropout is a major concern in higher education, as it leads to direct ec ... Expand

Abstract: Student dropout is a major concern in higher education, as it leads to direct economic losses and substantial social costs. Public and private institutions spend considerable resources to prevent student dropout. The effi­ ciency and effectiveness of these investments, however, may be improved by adopting a profit-driven perspec­ tive. In this paper, we propose a novel approach for implementing student dropout prediction using data-driven methods. Extending upon profit metrics as used in business analytics, we design a novel performance measure for evaluating predictive models that is tailored to the student dropout problem and that quantifies the net savings of a retention campaign. This metric supports the identification and selection of students to optimally allocate the limited resources for preventing student dropout and to maximize the resulting savings. Experiments were performed using data from three bachelor’s programs of a higher education institution containing information on dropouts and participation in a retention program, i.e., tutorials. The proposed metric allows for a better choice of prediction model and classification threshold than conventional approaches and, as a result, yields tangible savings for the institution. Finally, the presented approach and experimental results highlight pathways to design tailored student retention programs. Collapse

Topics: missing data communication service infrastructure decision making analytical information system

Methods: machine learning case study experiment descriptive statistic logistic regression

Sentiment aggregation of targeted features by capturing their dependencies: Making sense from customer reviews

2020 | International Journal of Information Management | Citations: 8

Authors: Mirtalaie, Monireh Alsadat; Hussain, Omar Khadeer

Abstract: Ideation is an important phase in the new product development process at which p ... Expand

Abstract: Ideation is an important phase in the new product development process at which product designers innovate and select novel ideas that can be added as features to an existing product. One way to find novel ideas is to transfer uncommon features of products of other domains and integrate them into the product to be improved. However, before incorporating such targeted features into the product, they need to be evaluated against the customers’ acceptance in social media using sentiment aggregation tools. Despite the many studies in sentiment analysis, mapping the customers’ opinions towards both high-level and technical features of a product extracted from social media to their best corresponding component in that product is still a challenge. Furthermore, none of the existing approaches ascertains the sentiment value of a targeted feature by capturing its dependencies on other features. In this paper, to address these drawbacks, we propose the sentiment aggregation framework for targeted features (SA-TF). SA-TF determines the sentiment of a targeted feature by assisting product designers in the tasks of mapping the features discussed in the reviews to the right product components, sentiment aggregation and considering feature dependencies to determine their polarity. The superiority of the different phases of SA-TF is demonstrated with experiments and comparing it with an existing approach. Collapse

Topics: database system knowledge representation social capital innovation management decision making

Methods: sentiment analysis computational algorithm literature study experiment ontological modelling

Social media in times of crisis: Learning from Hurricane Harvey for the coronavirus disease 2019 pandemic response

2020 | Journal of Information Technology | Citations: 39

Authors: Mirbabaie, Milad; Bunker, Deborah; Stieglitz, Stefan; Marx, Julian; Ehnis, Christian

Abstract: In recent times societal crises such as the coronavirus disease 2019 outbreak ha ... Expand

Abstract: In recent times societal crises such as the coronavirus disease 2019 outbreak have given rise to a tension between formal ‘command and control’ and informal social media activated self-organising information and communication systems that are utilised for crisis management decision-making. Social media distrust affects the dissemination of disaster information as it entails shifts in media perception and participation but also changes in the way individuals and organisations make sense of information in critical situations. So far, a little considered notion in this domain is the concept of sense-giving. Originating from organisational theory, it is used to explain the mechanisms behind intentional information provision that fosters collective meaning creation. In our study, we seek to understand the potential impact of sense-giving from Twitter crisis communication generated during the Hurricane Harvey disaster event. Social network and content analyses performed with a dataset of 9,414,463 tweets yielded insights into how sense-giving occurs during a large-scale disaster event. Theoretically, we specified (1) perpetual sense-giving, which relies primarily on topical authority and frequency; as well as (2) intermittent sense-giving, which occurs from high value of message content and leverage of popularity, that is, retweets. Our findings emphasise the importance of information-rich actors in communication networks and the leverage of their influence in crises such as coronavirus disease 2019 to reduce social media distrust and facilitate sense-making. Collapse

Topics: Twitter hurricane social media sensemaking pandemic

Methods: case study qualitative content analysis computational algorithm literature study social network analysis

Theories: graph theory

On the Variety and Veracity of Cyber Intrusion Alerts Synthesized by Generative Adversarial Networks

2020 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Sweet, Christopher; Moskal, Stephen; Yang, Shanchieh Jay

Abstract: Many cyber attack actions can be observed, but the observables often exhibit int ... Expand

Abstract: Many cyber attack actions can be observed, but the observables often exhibit intricate feature dependencies, non-homogeneity, and potentially rare yet critical samples. This work tests the ability to learn, model, and synthesize cyber intrusion alerts through Generative Adversarial Networks (GANs), which explore the feature space by reconciling between randomly generated samples and data that reflect a mixture of diverse attack behaviors without a priori knowledge. Through a comprehensive analysis using Jensen-Shannon Divergence, Conditional and Joint Entropy, and mode drops and additions, we show that the Wasserstein-GAN with Gradient Penalty and Mutual Information is more effective in learning to generate realistic alerts than models without Mutual Information constraints. We further show that the added Mutual Information constraint pushes the model to explore the feature space more thoroughly and increases the generation of low probability, yet critical, alert features. This research demonstrates the novel and promising application of unsupervised GANs to learn from limited yet diverse intrusion alerts to generate synthetic alerts that emulate critical dependencies, opening the door to proactive, data-driven cyber threat analyses. Collapse

Topics: IT security internet technology computer hardware IT security threat

Methods: descriptive statistic machine learning deep learning experiment artificial neural network

CHALLENGES IN THE DEPLOYMENT AND OPERATION OF MACHINE LEARNING IN PRACTICE

2019 | European Conference On Information Systems | Citations: 0

Authors: Baier, Lucas; Jã, Fabian

Abstract: Machine learning has recently emerged as a powerful technique to increase operat ... Expand

Abstract: Machine learning has recently emerged as a powerful technique to increase operational efficiency or to develop new value propositions. However, the translation of a prediction algorithm into an operationally usable machine learning model is a time-consuming and in various ways challenging task. In this work, we target to systematically elicit the challenges in deployment and operation to enable broader practical dissemination of machine learning applications. To this end, we first identify relevant challenges with a structured literature analysis. Subsequently, we conduct an interview study with machine learning practitioners across various industries, perform a qualitative content analysis, and identify challenges organized along three distinct categories as well as six overarching clusters. Eventually, results from both literature and interviews are evaluated with a comparative analysis. Key issues identified include automated strategies for data drift detection and handling, standardization of machine learning infrastructure, and appropriate communication and expectation management. Collapse

Topics: organizational value data quality digital service analytical information system database system

Methods: qualitative interview cross sectional research structured literature research literature study machine learning

Interaction-Aware Watching Duration Prediction on Live Streaming Platforms

2018 | Americas Conference on Information Systems | Citations: 0

Authors: Chen, Jiawei; Liu, Hongyan; He, Jun; Han, Sanpu

Abstract: Recently, live streaming, as a primary social media trend, has become more and m ... Expand

Abstract: Recently, live streaming, as a primary social media trend, has become more and more commonplace in businesses’ social media marketing. For live streaming platforms, how to keep viewers stay is always the central issue. To better predict viewer’s behaviors, we study a watching duration prediction problem in this paper. Different from prior literature, we take interactions between viewers and anchors into consideration and develop an integrated modeling framework for the prediction task. The proposed interaction-aware model combines probabilistic matrix factorization model with deep learning model to extract useful features from interactions for collaborative prediction. To the best of our knowledge, our study is the first one to analyze interactive behaviors for video watching prediction. Comprehensive experiments have been conducted on a real-world dataset to evaluate our predictive model. Experimental results demonstrate that our new model significantly outperforms baselines in watching duration prediction. Collapse

Topics: live streaming platform user behavior

Methods: experiment deep learning image processing convolutional neural network computational algorithm