Ten years ago, we presented the DeLone and McLean Information Systems (IS) Success Model as a framework and model for measuring the complex-dependent variable in IS research. In this paper, we discuss many of the important IS success research contributions of the last decade, focusing especially on research efforts that apply, validate, challenge, and propose enhancements to our original model. Based on our evaluation of those contributions, we propose minor refinements to the model and propose an updated DeLone and McLean IS Success Model. We discuss the utility of the updated model for measuring e-commerce system success. Finally, we make a series of recommendations regarding current and future measurement of IS success.

/pdf/the-delone-and-mclean-model-of-information-systems-success-a-4qyq8geftq.pdf

The DeLone and McLean Model of Information Systems Success: A Ten-Year Update

Since DeLone and McLean (D&M) developed their model of IS success, there has been much research on the topic of success as well as extensions and tests of their model. Using the technique of a qualitative literature review, this research reviews 180 papers found in the academic literature for the period 1992–2007 dealing with some aspect of IS success. Using the six dimensions of the D&M model – system quality, information quality, service quality, use, user satisfaction, and net benefits – 90 empirical studies were examined and the results summarized. Measures for the six success constructs are described and 15 pairwise associations between the success constructs are analyzed. This work builds on the prior research related to IS success by summarizing the measures applied to the evaluation of IS success and by examining the relationships that comprise the D&M IS success model in both individual and organizational contexts.

https://link.springer.com/content/pdf/10.1057%2Fejis.2008.15.pdf

Measuring information systems success: models, dimensions, measures, and interrelationships

The purpose of the present study is to empirically and theoretically assess DeLone and McLean's (1992) and Seddon's (1997) models of information systems (IS) success in a quasi-voluntary IS use context. Structural modeling techniques were applied to data collected by questionnaire from 274 system users of an integrated student information system at a midwestern university. The Seddon structural model and the DeLone and McLean structural model each contained five variables (system quality, information quality, perceived usefulness, user satisfaction, and IS use). Both models exhibit reasonable fit with the collected data. The empirical findings are assessed in the broader theoretical context of the IS success literature, including the Technology Acceptance Model and the Theory of Planned Behavior. Our results support DeLone and McLean's focus on integrated IS success models and their observation that IS success models need to be carefully specified in a given context. The Seddon model conceptually elaborates and clarifies aspects of the DeLone and McLean model, thereby effectively integrating core theoretical relationships espoused in the IS success literature. Our study also supports Seddon's three construct categories (system and information quality, general perceptual measures aboutnetbene fts about IS use, and IS behavior), as defining IS success and its impact on nature of IS use.

Assessing the Validity of IS Success Models: An Empirical Testand Theoretical Analysis

Foundations of Behavioral Research 2nd ed

The impact of Web quality and playfulness on user acceptance of online retailing

Information Systems IS managers are under increasing pressure to justify the value and contribution of IS expenditures to the productivity, quality, and competitiveness of the organization. This paper examines the need for IS assessment and suggests a comprehensive IS assessment framework linked to organizational performance using existing IS assessment theory as a base and incorporating measurement concepts from other disciplines. The existing models of IS success are updated to include the emerging IS success dimensions of service quality and work group impact and provide a comprehensive method for organizing the various measures of IS success. In addition, many new measures from recent research are presented to supplement the lists supplied by previous research. Additional research is suggested to advance the IS assessment contingency theory. Such a theory has the potential to contribute to the quality and productivity of the IS function and the larger organization by providing feedback to manage and improve the IS function to better meet the needs of the organization.

A Comprehensive Model for Assessing the Quality and Productivity of the Information Systems Function: Toward a Theory for Information Systems Assessment

1.5 to 4 million hectares of land burns in wildfire across the United States each year, contributing to post-fire erosion, ecosystem degradation and loss of wildlife habitat. Unmanned Aircraft Systems (UAS) and sensor miniaturization offer a new paradigm, providing an affordable, safe, and responsive on-demand tool for monitoring fire effects at a much finer spatial resolution than is possible with current technology. Using spectroscopic analysis of a variety of live as well as combusted vegetation samples to identify the spectral separability of vegetation classes, an optimal set of spectra was selected to be utilized by machine learning classifiers. This approach allows high resolution mapping of wildland fire severity and extent.

/pdf/spectroscopic-analysis-for-mapping-wildland-fire-effects-2am0pmw34q.pdf

Spectroscopic Analysis for Mapping Wildland Fire Effects from Remotely Sensed Imagery.

The purpose of this research is to develop a comprehensive, IS assessment framework using existing IS assessment theory as a base and incorporating suggestions from other disciplines To validate the framework and to begin the investigation of current IS assessment practice, a survey instrument was developed A small group of subject matter experts evaluated and improved the instrument The instrument was further evaluated using a small sample of IS representatives Results of this research include a reexamination of the IS function measurement problem using new frameworks of analyses yielding (a) guidance for the IS manager or executive on which IS measures might best fit their organization, (b) a further verification of the important measures most widely used by IS executives, (c) a comprehensive, theoretically-derived, IS assessment framework, and by (d) the enhancement of IS assessment theory by incorporating ideas from actual practice The body of knowledge gains a comprehensive, IS assessment framework that can be further tested for usefulness and applicability Future research is recommended to substantiate and improve on these findings Chapter 2 is a complete survey of prior research, subdivided by relevant literature divisions, such as organizational effectiveness, quality management, and IS assessment Chapter 3 includes development of and support for the research questions, IS assessment framework, and the research model Chapter 4 describes how the research was conducted It includes a brief justification for the research approach, a description of how the framework was evaluated, a description of how the survey instrument was developed and evaluated, a description of the participants and how they were selected, a synopsis of the data collection procedures, a brief description of follow-up procedures, and a summary Chapter 5 presents the results of the research Chapter 6 is a summary and conclusion of the research Finally, included in the appendices are definitions of terms, and copies of the original and improved survey instruments

/pdf/information-systems-assessment-development-of-a-2zg49i8s78.pdf

Information systems assessment: development of a comprehensive framework and contingency theory to assess the effectiveness of the information systems function.

A variety of machine learning algorithms have been used to map wildland fire effects, but previous attempts to map post-fire effects have been conducted using relatively low-resolution satellite imagery. Small unmanned aircraft systems (sUAS) provide opportunities to acquire imagery with much higher spatial resolution than is possible with satellites or manned aircraft. This effort investigates improvements achievable in the accuracy of post-fire effects mapping with machine learning algorithms that use hyperspatial (sub-decimeter) drone imagery. Spatial context using a variety of texture metrics were also evaluated in order to determine the inclusion of spatial context as an additional input to the analytic tools along with the three-color bands. This analysis shows that the addition of texture as an additional fourth input increases classifier accuracy when mapping post-fire effects.

/pdf/evaluation-of-texture-as-an-input-of-spatial-context-for-1omrobq85d.pdf

Evaluation of Texture as an Input of Spatial Context for Machine Learning Mapping of Wildland Fire Effects

Support Vector Machines (SVM) and k-Nearest Neighbor (kNN) are two common machine learning algorithms. Used for classifying images, the kNN and SVM each have strengths and weaknesses. When classifying an image, the SVM creates a hyperplane, dividing the input space between classes and classifying based upon which side of the hyperplane an unclassified object lands when placed in the input space. The kNN uses a system of voting to determine which class an unclassified object belongs to, considering the class of the nearest neighbors in the decision space. The SVM is extremely fast, classifying 12 megapixel aerial images in roughly ten seconds as opposed to the kNN which takes anywhere from forty to fifty seconds to classify the same image. When classifying, the kNN will generally classify accurately; however, it generates several small misclassifications that interfere with final classified image that is outputted. In comparison, the SVM will occasionally misclassify a large object that rarely interferes with the final classified image. While both algorithms yield positive results regarding the accuracy in which they classify the images, the SVM provides significantly better classification accuracy and classification speed than the kNN.

https://www.fs.fed.us/rm/pubs_series/rmrs/proc/rmrs_p078/rmrs_p078_095_109.pdf

Barry Myers (Mentor)

Papers

A Comprehensive Model for Assessing the Quality and Productivity of the Information Systems Function: Toward a Theory for Information Systems Assessment

Spectroscopic Analysis for Mapping Wildland Fire Effects from Remotely Sensed Imagery.

Information systems assessment: development of a comprehensive framework and contingency theory to assess the effectiveness of the information systems function.

Evaluation of Texture as an Input of Spatial Context for Machine Learning Mapping of Wildland Fire Effects

KNN vs SVM: A Comparison of Algorithms