• Asia pacific journal of information systems
• /
• v.24 no.4
• /
• pp.611-635
• /
• 2014

Information systems (IS) have become ubiquitous and changed every aspect of how people live their lives. While some IS have been successfully adopted and widely used, others have failed to be adopted and crowded out in spite of remarkable progress in technologies. Both the technology acceptance model (TAM) and the IS Success Model (ISSM), among many others, have contributed to explain the reasons of success as well as failure in IS adoption and usage. While the TAM suggests that intention to use and perceived usefulness lead to actual IS usage, the ISSM indicates that information quality, system quality, and service quality affect IS usage and user satisfaction. Upon literature review, however, we found a significant void in theoretical development and its applications that employ either of the two models, and we raise research questions. First of all, in spite of the causal relationship between intention to use and actual usage, in most previous studies, only intention to use was employed as a dependent variable without overt explaining its relationship with actual usage. Moreover, even in a few studies that employed actual IS usage as a dependent variable, the degree of actual usage was measured based on users' perceptual responses to survey questionnaires. However, the measurement of actual usage based on survey responses might not be 'actual' usage in a strict sense that responders' perception may be distorted due to their selective perceptions or stereotypes. By the same token, the degree of system quality that IS users perceive might not be 'real' quality as well. This study seeks to fill this void by measuring the variables of actual usage and system quality using 'fact' data such as system logs and specifications of users' information and communications technology (ICT) devices. More specifically, we propose an integrated research model that bring together the TAM and the ISSM. The integrated model is composed of both the variables that are to be measured using fact as well as survey data. By employing the integrated model, we expect to reveal the difference between real and perceived degree of system quality, and to investigate the relationship between the perception-based measure of intention to use and the fact-based measure of actual usage. Furthermore, we also aim to add empirical findings on the general research question: what factors influence actual IS usage and how? In order to address the research question and to examine the research model, we selected a mobile campus application (MCA). We collected both fact data and survey data. For fact data, we retrieved them from the system logs such information as menu usage counts, user's device performance, display size, and operating system revision version number. At the same time, we conducted a survey among university students who use an MCA, and collected 180 valid responses. A partial least square (PLS) method was employed to validate our research model. Among nine hypotheses developed, we found five were supported while four were not. In detail, the relationships between (1) perceived system quality and perceived usefulness, (2) perceived system quality and perceived intention to use, (3) perceived usefulness and perceived intention to use, (4) quality of device platform and actual IS usage, and (5) perceived intention to use and actual IS usage were found to be significant. In comparison, the relationships between (1) quality of device platform and perceived system quality, (2) quality of device platform and perceived usefulness, (3) quality of device platform and perceived intention to use, and (4) perceived system quality and actual IS usage were not significant. The results of the study reveal notable differences from those of previous studies. First, although perceived intention to use shows a positive effect on actual IS usage, its explanatory power is very weak ($R^2$=0.064). Second, fact-based system quality (quality of user's device platform) shows a direct impact on actual IS usage without the mediating role of intention to use. Lastly, the relationships between perceived system quality (perception-based system quality) and other constructs show completely different results from those between quality of device platform (fact-based system quality) and other constructs. In the post-hoc analysis, IS users' past behavior was additionally included in the research model to further investigate the cause of such a low explanatory power of actual IS usage. The results show that past IS usage has a strong positive effect on current IS usage while intention to use does not have, implying that IS usage has already become a habitual behavior. This study provides the following several implications. First, we verify that fact-based data (i.e., system logs of real usage records) are more likely to reflect IS users' actual usage than perception-based data. In addition, by identifying the direct impact of quality of device platform on actual IS usage (without any mediating roles of attitude or intention), this study triggers further research on other potential factors that may directly influence actual IS usage. Furthermore, the results of the study provide practical strategic implications that organizations equipped with high-quality systems may directly expect high level of system usage.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.19-41
• /
• 2019

According to the rapidly increasing demand for text data analysis, research and investment in text mining are being actively conducted not only in academia but also in various industries. Text mining is generally conducted in two steps. In the first step, the text of the collected document is tokenized and structured to convert the original document into a computer-readable form. In the second step, tasks such as document classification, clustering, and topic modeling are conducted according to the purpose of analysis. Until recently, text mining-related studies have been focused on the application of the second steps, such as document classification, clustering, and topic modeling. However, with the discovery that the text structuring process substantially influences the quality of the analysis results, various embedding methods have actively been studied to improve the quality of analysis results by preserving the meaning of words and documents in the process of representing text data as vectors. Unlike structured data, which can be directly applied to a variety of operations and traditional analysis techniques, Unstructured text should be preceded by a structuring task that transforms the original document into a form that the computer can understand before analysis. It is called "Embedding" that arbitrary objects are mapped to a specific dimension space while maintaining algebraic properties for structuring the text data. Recently, attempts have been made to embed not only words but also sentences, paragraphs, and entire documents in various aspects. Particularly, with the demand for analysis of document embedding increases rapidly, many algorithms have been developed to support it. Among them, doc2Vec which extends word2Vec and embeds each document into one vector is most widely used. However, the traditional document embedding method represented by doc2Vec generates a vector for each document using the whole corpus included in the document. This causes a limit that the document vector is affected by not only core words but also miscellaneous words. Additionally, the traditional document embedding schemes usually map each document into a single corresponding vector. Therefore, it is difficult to represent a complex document with multiple subjects into a single vector accurately using the traditional approach. In this paper, we propose a new multi-vector document embedding method to overcome these limitations of the traditional document embedding methods. This study targets documents that explicitly separate body content and keywords. In the case of a document without keywords, this method can be applied after extract keywords through various analysis methods. However, since this is not the core subject of the proposed method, we introduce the process of applying the proposed method to documents that predefine keywords in the text. The proposed method consists of (1) Parsing, (2) Word Embedding, (3) Keyword Vector Extraction, (4) Keyword Clustering, and (5) Multiple-Vector Generation. The specific process is as follows. all text in a document is tokenized and each token is represented as a vector having N-dimensional real value through word embedding. After that, to overcome the limitations of the traditional document embedding method that is affected by not only the core word but also the miscellaneous words, vectors corresponding to the keywords of each document are extracted and make up sets of keyword vector for each document. Next, clustering is conducted on a set of keywords for each document to identify multiple subjects included in the document. Finally, a Multi-vector is generated from vectors of keywords constituting each cluster. The experiments for 3.147 academic papers revealed that the single vector-based traditional approach cannot properly map complex documents because of interference among subjects in each vector. With the proposed multi-vector based method, we ascertained that complex documents can be vectorized more accurately by eliminating the interference among subjects.