A Methodology for Investigating Public Opinion Using Multilevel Text Analysis

Recently, many users have begun to frequently share their opinions on diverse issues using various social media. Therefore, numerous governments have attempted to establish or improve national policies according to the public opinions captured from various social media. In this paper, we indicate several limitations of the traditional approaches to analyze public opinion on science and technology and provide an alternative methodology to overcome these limitations. First, we distinguish between the science and technology analysis phase and the social issue analysis phase to reflect the fact that public opinion can be formed only when a certain science and technology is applied to a specific social issue. Next, we successively apply a start list and a stop list to acquire clarified and interesting results. Finally, to identify the most appropriate documents that fit with a given subject, we develop a new logical filter concept that consists of not only mere keywords but also a logical relationship among the keywords. This study then analyzes the possibilities for the practical use of the proposed methodology thorough its application to discover core issues and public opinions from 1,700,886 documents comprising SNS, blogs, news, and discussions.

A Methodology for Automatic Diversification of Document Categories

Recently, numerous documents including large volumes of unstructured data and text have been created because of the rapid increase in the use of social media and the Internet. Usually, these documents are categorized for the convenience of users. Because the accuracy of manual categorization is not guaranteed, and such categorization requires a large amount of time and incurs huge costs. Many studies on automatic categorization have been conducted to help mitigate the limitations of manual categorization. Unfortunately, most of these methods cannot be applied to categorize complex documents with multiple topics because they work on the assumption that individual documents can be categorized into single categories only. Therefore, to overcome this limitation, some studies have attempted to categorize each document into multiple categories. However, the learning process employed in these studies involves training using a multi-categorized document set. These methods therefore cannot be applied to the multi-categorization of most documents unless multi-categorized training sets using traditional multi-categorization algorithms are provided. To overcome this limitation, in this study, we review our novel methodology for extending the category of a single-categorized document to multiple categorizes, and then introduce a survey-based verification scenario for estimating the accuracy of our automatic categorization methodology.

Investigating the Determinants of Purchase Intention in C2C E-Commerce

This study aims to examine the determinants of purchase intention in C2C e-commerce. Specifically the role of instant messaging in the C2C e-commerce contextis investigated. In addition to instant messaging, we brought in two antecedents of purchase intention - trust and customer satisfaction - to establish a theoretical research model. Structural equation modeling using LISREL was used to analyze the data.We discussed the research findings and suggested some implications for researchers and practitioners.

Exploring the Roles of Social Exchanges in Using Information Systems

Previous studies have indicated that one of the most critical failure reasons of enterprise systems is the lack of knowledge sharing and utilization across organizations. As a consequence, many information systems researchers have paid attention to examining the effect of absorptive capacity closely associated with knowledge sharing and transferring on IS usage performance. A lack of communications and interactions due to a lack of organizational citizenship behavior might lead to weak absorptive capacity and thus negatively influence knowledge sharing across organizations. In this study, a theoretical model which delves into the relationship between usage performance of enterprise systems and its determinants was established.

Investigating the Effects of Sociotechnical Changes

Cognizant of the fact that enterprise systems involve organizational change and their implementation is over shadowed by a high failure rate, it is argued that there is the need to focus attention on employees- perceptions of such organizational change when explaining adoption behavior of enterprise systems. For this purpose, the research incorporates a conceptual constructo fattitude toward change that captures views about the need for organizational change. Centered on this conceptual construct, the research model includes beliefs regarding the system and behavioral intention as its consequences, and the personal characteristics of organizational commitment and perceived personal competence as its antecedents. Structural equation analysis using LISREL provides significant support for the proposed relationships. Theoretical and practical implications are discussed along with limitations.