Using Isolation Forest and Alternative Data Products to Overcome Ground Truth Data Scarcity for Improved Deep Learning-based Agricultural Land Use Classification Models

2023 | HICSS | Citations: 0

Authors: García Pereira, Agustín; Porwol, Lukasz; Ojo, Adegboyega

Abstract: High-quality labelled datasets represent a cornerstone in the development of dee ... Expand

Abstract: High-quality labelled datasets represent a cornerstone in the development of deep learning models for land use classification. The high cost of data collection, the inherent errors introduced during data mapping efforts, the lack of local knowledge, and the spatial variability of the data hinder the development of accurate and spatially-transferable deep learning models in the context of agriculture. In this paper, we investigate the use of Isolation Forest (IF), an anomaly detection algorithm, to reduce noise in a large-scale, low-resolution alternative ground truth dataset used to train land use deep learning models. We use a modest-size, high-resolution and high-fidelity manually collected ground-truth dataset to calibrate Isolation Forest parameters and evaluate our approach, highlighting the relatively low cost of the methodology. Our data-centric methodology demonstrates the efficacy of deep learning methods coupled with IF to create mid-resolution land-use models and map products for agriculture using an alternative ground-truth dataset. Moreover, we compare our deep learning approach with a traditional algorithm used in remote sensing and evaluate the spatial transferability of the created models. Finally, we reflect upon the lessons learnt and future work. Collapse

Topics: cloud computing Python programming language open source geographic information system

Methods: experiment deep learning computational algorithm isolation forest random forest classification

Is personally identifiable information really more valuable? Evidence from consumers' willingness-to-accept valuation of their privacy information

2023 | Decision Support Systems | Citations: 0

Authors: Liu, Huan; Li, Kai; Chen, Yan; Luo, Xin (Robert)

Abstract: Information privacy is not yet a mature “product.” The amount of monetary reward ... Expand

Abstract: Information privacy is not yet a mature “product.” The amount of monetary reward that firms should pay consumers to obtain their data is unknown. This paper measures consumers’ valuation of two types of personal information—personally identifiable information (PII) and non-PII, with the willing-to-accept (WTA) payoffs using a multi-study mixed-methods approach. We conducted two realistic auction experiments with 150 and 415 participants, respectively, as well as one interview study with 31 participants and a meta-analysis study to explain international differences in WTA prices between China and other countries. We found that while con­ sumers claimed that PII was more valuable than non-PII in the interview study, they did not demand a higher WTA price when monetizing PII in the two experimental studies. However, consumers became more cautious and provided fewer data items when dealing with PII, compared to non-PII. Consumers may ask for a higher price for non-PII than PII when they need to disclose more information. They also strategically select information being disclosed, if possible, to reduce privacy risk. Context only matters in WTA price for certain types of data, which is medical PII data in our case. Specifically, the WTA price for PII is higher in the medical information context than in the shopping information context. The meta-analysis shows that individualism and uncertainty avoidance are two key cultural dimensions explaining international differences in WTA prices. Collapse

Topics: privacy healthcare data misinformation data breach mobile health

Methods: experiment qualitative interview meta analysis regression analysis method survey

Cashless Japan: Unlocking Influential Risk on Mobile Payment Service

2022 | Information Systems Frontiers | Citations: 0

Authors: Chang, Wei-Lun; Chen, Li-Ming; Hashimoto, Takako

Abstract: In Japan, cashless is not yet popular but government and companies are devoted t ... Expand

Abstract: In Japan, cashless is not yet popular but government and companies are devoted to the development of mobile payment methods. This research collected 241 Japanese users and applied decision trees algorithm. Six types of perceived risks (financial, privacy, performance, psychological, security, and time) were used and the categorized class is intention to use mobile payment (low, medium, and high). We also compared different competitive models to examine the performance, including decision trees, kNN, Naïve Bayes, SVM, and logistic regression and decision trees outperformed among all models. The findings indicated that privacy and performance risks are import to Japanese users. Safe, secured, reliable, and fast mobile payment environment are more important to low intention users (less concerns about financial risk). Financial loss, safe, secured, reliable, and fast mobile payment environment are more important to medium intention users (less concerns about time and security risk). Monetary loss, safe, reliable, and fast mobile payment environment are more important to high intention users (less concerns about security risk and psychological risk). The results can help Japanese companies unlock the perceived risk on mobile payment and furnish appropriate strategies to improve usage. Collapse

Topics: mobile payment mobile system usage intention privacy mobile phone

Methods: decision tree classification logistic regression support vector machine machine learning computational algorithm

Design and Evaluation of a Serious Game for the Training of Epilepsy Patients

2022 | European Conference On Information Systems | Citations: 0

Authors: Lange, Julia; Houta, Salima

Abstract: Epilepsy patients often have inadequate epilepsy knowledge with negative conseq ... Expand

Abstract: Epilepsy patients often have inadequate epilepsy knowledge with negative consequences. Current training programs are on-site and do not offer the advantages of digital interventions regarding independence of time and place. Moreover, research on serious games is in its infancy for epilepsy. This paper presents EpiTales, a serious game for training epilepsy knowledge. We conducted a survey and analyzed existing interventions to gain understanding about the target group and educational concepts. To design EpiTales we followed the Octalysis game design framework. The effect was investigated by means of knowledge transfer using the method of a randomized controlled experiment. Additionally, usability tests were performed. Our results demonstrated an average relative knowledge increase of 51% and a higher perception of joy among players of the game. Nevertheless, the workbook used by the control group remains more effective. Future development should consider strengths of the workbook, while keeping the positively noted aspects of EpiTales. Collapse

Topics: usability mobile application knowledge sharing mobile system digital distribution

Methods: survey experimental group usability testing experiment regression analysis method

Multi-sided platforms in competitive B2B networks with varying governmental influence – a taxonomy of Port and Cargo Community System business models

2022 | Electronic Markets | Citations: 0

Authors: Tessmann, Ruben; Elbert, Ralf

Abstract: Our knowledge on differences in business model characteristics of thriving and f ... Expand

Abstract: Our knowledge on differences in business model characteristics of thriving and failing Multi-Sided Platforms in competitive B2B networks (B2B-MSP) and potential influences of increasing governmental involvement remains fragmented. This study develops a taxonomy to classify special B2B-MSP with varying governmental influence in the supply chain and transportation context, viz. Port and Cargo Community Systems (CS). Based on the classification of 44 international CS, we identify four archetypes using cluster analysis. The taxonomy provides practitioners with a differentiated view on the configuration options of CS business models including the involvement of governmental institutions, while the presented archetypes contribute an aggregated view of CS business models. The statistical analysis of our results provides initial explanatory approaches on CS business model dimension interdependencies, thereby laying the basis for a deeper understanding of sectoral and geographic differences of B2B-MSP and their diffusion dynamics as well as facilitating a higher contextualization of future research. Collapse

Topics: business model business-to-business data governance analytical information system digital business model

Methods: cluster analysis data imputation literature study hierarchical clustering decision tree classification

A Comparison of False-Information Policies in Five Countries before and during the COVID-19 Pandemic

2022 | HICSS | Citations: 0

Authors: Zhu, Xiaohua; Yang, Shengnan; Allen, Summer

Abstract: This study analyzes five countries’ falseinformation policies before and during ... Expand

Abstract: This study analyzes five countries’ falseinformation policies before and during the COVID-19 pandemic. Building upon existing discussions of regulation models, this paper uses a qualitative, comparative case study method to unpack the characteristics of false-information policies in each country. The before-after comparisons show that each country has a unique evolving path of falseinformation regulation and that the state has enhanced or attempted to enhance its role in battling against the infodemic during the pandemic. The regulatory practices are a dynamic process and involve not only government and social media platforms but also multiple other actors, which is leading to more complex practices and blurring the boundary of existing models. We discuss the limitation of existing regulation models and suggest a relational perspective to understand the underlying relations between the state, platforms, and other stakeholders. Collapse

Topics: misinformation pandemic social media IT policy legal context

Methods: case study Google news literature study cross sectional research

Why do Chatbots fail? A Critical Success Factors Analysis

2021 | International Conference on Information Systems | Citations: 20

Authors: Janssen, Antje; Grützner, Lukas; Breitner, Michael H.

Abstract: Chatbots gain more and more attention, both in research and in practice, and en ... Expand

Abstract: Chatbots gain more and more attention, both in research and in practice, and enter several application areas. While much research addresses technical or human-centered aspects, development, and adoption, little is known about Critical Success Factors (CSFs) and failure reasons of chatbots in practice. Design Science Research (DSR) oriented, we first analyze 103 real-world chatbots to examine the discontinuation rate of chatbots in 15 months. With a literature review and 20 expert interviews, we derive 12 specific CSFs and identify failure reasons which are evaluated in a focus group discussion with chatbot experts, afterwards. We explain chatbots' failure in practice, improve chatbot knowledge in Information Systems (IS) and Human Computer Interaction (HCI), and finally deduce recommendations and further research opportunities. Collapse

Topics: usability human computer interaction customer service database system LinkedIn

Methods: chatbot qualitative interview literature study design process literature sample

Mining Social Networks to Detect Traffic Incidents

2021 | Information Systems Frontiers | Citations: 1

Authors: Vallejos, Sebastián; Alonso, Diego G.; Caimmi, Brian; Berdun, Luis; Armentano, Marcelo G.; Soria, Álvaro

Abstract: Social networks are usually used by citizens to report or complain about traffic ... Expand

Abstract: Social networks are usually used by citizens to report or complain about traffic incidents that affect their daily mobility. Automatically finding traffic-related reports and extracting useful information from them is not a trivial task, due to the informal language used in social networks, to the lack of geographic metadata, and to the large amount of non traffic-related publications. In this article, we address this problem by combining Machine Learning and Natural Language Processing techniques. Our approach (a) filters publications that report traffic incidents in social networks, (b) extracts geographic information from the textual content of the publications, and (c) provides a broadcasting service that clusters all the reports of the same incident. We compared the performance of our approach with state of the art approaches and with a popular traffic-specific social network, obtaining promising results. Collapse

Topics: Twitter social network application programming interface global navigation satellite system Wikipedia

Methods: experiment machine learning support vector machine natural language processing decision tree classification

ARE WE PROVIDING SERVICE QUALITY WITH IS? EMPIRICAL EVIDENCE FROM THE JUSTICE SYSTEM OF TWO DEVELOPING COUNTRIES

2018 | European Conference On Information Systems | Citations: 0

Authors: Arias, MarÃŁa Isabel

Abstract: Little is known about Information and Communication Technologies for Development ... Expand

Abstract: Little is known about Information and Communication Technologies for Development (ICT4D) impacts in Latin America justice system and few theoretical advances were done on this topic. This paper aims to propose a model grounded in Task-Technology Fit theory and explore its rationality in the justice system of two developing countries: Brazil and Argentina. Interviews with public managers and employees were conducted, and content analysis was applied to examine ICT4D impact on individual performance and public service quality. Our research makes several contributions by proposing a model on how ICT4D intervention can be assessed in an application area like the justice system. We examine the effectiveness of two national ICT4D endeavours, represented by the electronic lawsuit, thus showing how government can lead successful ICT4D implementations in developing countries. The practical value of this research rests on clarifying how ICT4D impacts public employees’ performance and public service quality. The results should help managers reduce gaps between policy and design of electronic lawsuits, thus guiding ICT4D endeavours by practitioners in other developing countries. Collapse

Topics: service quality information and communication technology for development IS impact individual characteristic task characteristic

Methods: qualitative interview qualitative content analysis survey theory development literature study

Theories: theory of task technology fit

Governing Open Data Platforms to Cultivate Innovation Ecosystems: The Case of the Government of Buenos Aires

2018 | International Conference on Information Systems | Citations: 7

Authors: Bonina, Carla; Eaton, Ben; Henningsson, Stefan

Abstract: Open Government Data (OGD) is increasingly an object of research. Whilst referre ... Expand

Abstract: Open Government Data (OGD) is increasingly an object of research. Whilst referred to as a platform problem, few studies examine the phenomenon using platform concepts. One challenge governments face is to establish thriving OGD ecosystems through appropriate platform governance. The governance of innovating complements on the demand side of platforms, such as services using OGD datasets by entrepreneurs for citizen users, is well studied in platform literature. However, understanding of the supply side and how third parties can be governed to help innovate platform core architecture, such a ministries sourcing quality datasets for OGD platforms, is lacking. In our preliminary study of emergent OGD platforms in Latin America, we construct a model extending concepts of boundary resources from the demand side to the supply side to expand our understanding of platform governance. In addition to contributing to platform governance theories, we improve our understanding of OGD platform ecosystem cultivation. Collapse

Topics: innovation management digital ecosystem platform governance open data blog

Methods: case study theory development archival research multiple case study longitudinal research

Theories: information systems theory