What do you mean? A Review on Recovery Strategies to Overcome Conversational Breakdowns of Conversational Agents

2021 | International Conference on Information Systems | Citations: 27

Authors: Benner, Dennis; Elshan, Edona; Schöbel, Sofia; Janson, Andreas

Abstract: Since the emergence of conversational agents, this technology has seen continuo ... Expand

Abstract: Since the emergence of conversational agents, this technology has seen continuous development and research. Today, advanced conversational agents are virtually omnipresent in our everyday lives. Albeit the numerous improvements in their conversational capabilities, breakdowns are still a persistent issue. Such breakdowns can result in a very unpleasant experience for users and impair the future success of conversational agents. This issue has been acknowledged by many researchers recently. However, the research on strategies to overcome conversational breakdowns is still inconclusive, and further research is needed. Therefore, we conduct a systematic literature analysis to derive conceptual conversational breakdown recovery strategies from literature and highlight future research avenues to address potential gaps. Thus, we contribute to theory of human-agent interaction by deriving and assessing recovery strategies and suggesting leads for novel recovery strategies. Collapse

Topics: database system usability human computer interaction conversational agent robotic

Methods: literature study structured literature research literature sample theoretical contribution

Machine Learning-Based Android Malware Detection Using Manifest Permissions

2021 | HICSS | Citations: 0

Authors: Mcdonald, Jeffrey; Herron, Nathan; Glisson, William; Benton, Ryan

Abstract: The Android operating system is currently the most prevalent mobile device opera ... Expand

Abstract: The Android operating system is currently the most prevalent mobile device operating system holding roughly 54 percent of the total global market share. Due to Android’s substantial presence, it has gained the attention of those with malicious intent, namely, malware authors. As such, there exists a need for validating and improving current malware detection techniques. Automated detection methods such as anti-virus programs are critical in protecting the wide variety of Android-powered mobile devices on the market. This research investigates effectiveness of four different machine learning algorithms in conjunction with features selected from Android manifest file permissions to classify applications as malicious or benign. Case study results, on a test set consisting of 5,243 samples, produce accuracy, recall, and precision rates above 80%. Of the considered algorithms (Random Forest, Support Vector Machine, Gaussian Naïve Bayes, and K-Means), Random Forest performed the best with 82.5% precision and 81.5% accuracy. Collapse

Topics: mobile application malware Android Python mobile application market

Methods: computational algorithm machine learning support vector machine random forest classification naïve bayes

Tweeting in IIoT Ecosystems – Empirical Insights from Social Media Analytics About IIoT Platforms

2021 | International Conference on Business Informatics | Citations: 0

Authors: Petrik, Dimitri; Pantow, Katharina; Zschech, Patrick; Herzwurm, Georg

Abstract: The market for the Industrial Internet of Things (IIoT) platforms remains highly ... Expand

Abstract: The market for the Industrial Internet of Things (IIoT) platforms remains highly dynamic and is rapidly evolving regarding the growth of the platform-based ecosystems. However, digital platforms, used in the industrial business-to-business setting, differ significantly from the established platforms in the business-to-consumer domains and remain little researched. In this study, we apply a data-driven approach and conduct bottom-up and top-down content analysis, exploring social media data on the current state of IIoT platforms. For a top-down analysis, we draw on the theoretical concept of platform boundary resources. Specifically, we apply descriptive analytics and topic modeling on the Twitter data regarding the market-ready IIoT platforms Adamos, Cumulocity, Watson IoT, MindSphere, Leonardo, and ThingWorx, thus conducting an exploratory multiple case study. Our findings generate descriptive insights on the currently discussed topics in the area of IIoT platforms, contributing to the knowledge of the current state of digital platforms used in IIoT. Collapse

Topics: Twitter mobile system internet of things cloud computing application programming interface

Methods: latent dirichlet allocation qualitative content analysis topic model sentiment analysis design artifact

Boundary Resources for IIoT Platforms – a Complementor Satisfaction Study

2020 | International Conference on Information Systems | Citations: 0

Authors: Petrik, Dimitri; Herzwurm, Georg

Abstract: Platform providers can use Boundary Resources (BR) to enable complementors to ut ... Expand

Abstract: Platform providers can use Boundary Resources (BR) to enable complementors to utilize the platform to create value, simultaneously controlling the complementary output. Despite their significance, not much is currently known about the quality of BRs and their impact on the complementor satisfaction. This paper presents the results of the complementor satisfaction study in the Industrial Internet of Things (IIoT) domain through the application of the critical incident technique (CIT). Applying the Kano model, the first result sheds light on how the platform providers affect complementor satisfaction through various BRs. The second result discovers satisfaction-relevant quality dimensions (QD) for each evaluated BR. Our findings show which BRs are suitable to leverage the satisfaction-driven complementor engagement in platform-based IIoT ecosystems, establishing a link between the decisions on BR quality and the platformbased innovation dynamics, if satisfaction is incorporated in the design of BRs. Collapse

Topics: customer satisfaction application programming interface usability cloud computing devops

Methods: survey design principle case study single case study critical incident technique

Theories: two-factor theory

Prediction of Customer Movements in Large Tourism Industries by the Means of Process Mining

2018 | European Conference On Information Systems | Citations: 0

Authors: Brunk, Jens; Riehle, Dennis M; Delfmann, Patrick

Abstract: Customer movements in large tourism industries (such as public transport systems ... Expand

Abstract: Customer movements in large tourism industries (such as public transport systems, attraction parks or ski resorts) can be understood as business processes. Their processes describe the flow of persons through the networked systems, while Information Systems log the different steps. The prediction of how large numbers of customers will behave in the near future is a complex and yet unsolved challenge. However, the possible business benefits of predictive analytics in the tourism industry are manifold. We propose to approach this task with the yet unexploited application of predictive process mining. In a prototypical use case, we work together with two major European ski resorts. We implement a predictive process mining algorithm towards the goal of predicting near future lift arrivals of skiers within the ski resort in real-time. Furthermore, we present the results of our prototypical implementation and draw conclusions for future research in the area. Collapse

Topics: process mining business process management command line interface usability high-performance computing

Methods: computational algorithm event log design artifact business process modeling

Two CEGAR-based approaches for the safety verification of PLC-controlled plants

2016 | Information Systems Frontiers | Citations: 0

Authors: Nellen, Johanna; Driessen, Kai; Neuhäußer, Martin; Ábrahám, Erika; Wolters, Benedikt

Abstract: In this paper we address the safety analysis of chemical plants controlled by pr ... Expand

Abstract: In this paper we address the safety analysis of chemical plants controlled by programmable logic controllers (PLCs). We consider a specification of the control program of the PLCs, extended with the specification of the dynamic plant behavior. The resulting hybrid models can be transformed to hybrid automata, for which advanced techniques for reachability analysis exist. However, the hybrid automata models are often too large to be analyzed. We propose two counterexample-guided abstraction refinement (CEGAR) approaches to keep the size of the hybrid models moderate. Collapse

Topics: command line interface usability cyber-physical system

Methods: computational algorithm experiment design artifact cluster analysis case study

An Experimental Study of the Relationship BetweenSpatial Ability and the Learning of a Graphical User Interface

1995 | Americas Conference on Information Systems | Citations: 0

Authors: Leitheiser, Bob; Munro, David

Abstract: ... Expand

Abstract: Collapse

Topics: command line interface graphical user interface usability operating system

Methods: experiment ANOVA experimental group experimental task parametric test

Conceptual Versus Procedural Software Training for Graphical User Interfaces: A Longitudinal Field Experiment

1994 | Management Information Systems Quarterly | Citations: 10

Authors: Olfman, Lorne; Mandviwalla, Munir

Abstract: Graphical user interfaces (GUIs) are rapidly becoming ubiquitous in organizatio ... Expand

Abstract: Graphical user interfaces (GUIs) are rapidly becoming ubiquitous in organizations. Most of what we know about software training comes from studies of command-line interfaces. This paper compares concept-based versus procedure-based content of training materials. Concept-based materials define the nature and associations of the objects in the interface, while procedure-based materials define how specific tasks are carried out. This comparison was done using a field experiment. Eighty-two volunteers participated in a three-week Windows training program and completed a follow-up questionnaire seven months later. The results show that the amount learned in such sessions is a function of neither concept-based nor procedure-based training. GUI training should provide both kinds of information because trainees need to learn both. In addition, trainers should be aware of an apparent early plateau in learning the Windows GUI. Collapse

Topics: online learning system graphical user interface command line interface usability system support

Methods: survey analysis of covariance longitudinal research experiment field experiment