Jiho Kim, Youngjun Jang, Wongyeom Seo and Hongchul Lee
Information filtering systems serve as robust tools in the ongoing difficulties associated with overwhelming volumes of data. With constant generation and accumulation of reviews…
Abstract
Purpose
Information filtering systems serve as robust tools in the ongoing difficulties associated with overwhelming volumes of data. With constant generation and accumulation of reviews in online communities, the ability to distill and provide valuable insights to assist customers in their search for relevant information is of considerable significance. This study devised an effective review filtering system for a popular online physical experience review site.
Design/methodology/approach
This study entailed an investigation of a hybrid approach for a review filtering system augmented with various text mining-based operational variables to extract the linguistic signals of online reviews. Moreover, we devised three ensemble models based on multiple machine learning and deep learning algorithms to build a high-performance review filtering system.
Findings
The main findings confirm the effectiveness of using the derived operational variables when reviewing filtering systems. We found that the reviewer’s tendency and history macros, as well as the readability and sentiment of the reviews, contribute significantly to the filtering performance. Furthermore, the proposed three ensemble frameworks demonstrated good efficiency with an average accuracy of 89.39%.
Originality/value
This study provides a methodological blueprint for operationalizing variables in online reviews, covering both structured and unstructured datasets. Incorporating different variables enhances the efficiency of the algorithm and provides a more comprehensive understanding of user-generated content. Furthermore, the study affords a strategic perspective and integrated guidelines for developers seeking to create advanced review filtering systems.
Details
Keywords
Jiho Kim, Hanjun Lee and Hongchul Lee
This paper aims to find determinants that can predict the helpfulness of online customer reviews (OCRs) with a novel approach.
Abstract
Purpose
This paper aims to find determinants that can predict the helpfulness of online customer reviews (OCRs) with a novel approach.
Design/methodology/approach
The approach consists of feature engineering using various text mining techniques including BERT and machine learning models that can classify OCRs according to their potential helpfulness. Moreover, explainable artificial intelligence methodologies are used to identify the determinants for helpfulness.
Findings
The important result is that the boosting-based ensemble model showed the highest prediction performance. In addition, it was confirmed that the sentiment features of OCRs and the reputation of reviewers are important determinants that augment the review helpfulness.
Research limitations/implications
Each online community has different purposes, fields and characteristics. Thus, the results of this study cannot be generalized. However, it is expected that this novel approach can be integrated with any platform where online reviews are used.
Originality/value
This paper incorporates feature engineering methodologies for online reviews, including the latest methodology. It also includes novel techniques to contribute to ongoing research on mining the determinants of review helpfulness.
Details
Keywords
Sang T. Choe and Kelly D. Huff
North Korea is moving in the direction of an open market as China did a generation ago. With a substantial population of 22 million, the country has abundant natural resources and…
Abstract
North Korea is moving in the direction of an open market as China did a generation ago. With a substantial population of 22 million, the country has abundant natural resources and an affordable labor force that are attractive to contract manufacturers, importers of retail goods, and contractors of large turnkey projects. North Korea's strategic location in the Far East offers enormous savings in transportation cost for multinational firms wishing to ship goods to Southeast Asia and Europe. Five reasons to do business with North Korea are analyzed in the report.
Abstract
Details
Keywords
Sungwon Oh, Min Jae Park, Tae You Kim and Jiho Shin
This study aimed to present the methodology of the text data analysis to establish marketing strategies for fintech companies in a practical way. Specifically, the methodology was…
Abstract
Purpose
This study aimed to present the methodology of the text data analysis to establish marketing strategies for fintech companies in a practical way. Specifically, the methodology was presented to convert customers' review data, which consisted of the text data (unstructured data), to the numerical data (structured data) by using a text mining algorithm “Global Vectors for Word Representation,” abbreviated as “GloVe”; additionally, the authors presented the methodology to deploy the numerical data for marketing strategies with eliminate-reduce-raise-create (ERRC) value factor analytics.
Design/methodology/approach
First, the authors defined the background, features and contents of fintech services based on a review of related literature review. Additionally, they examined business strategies, the importance of social media for fintech services and fintech technology trends based on the literature review. Next, they analyzed the similarity between fintech-related keywords, which represent the trends in fintech services, and the text data related to fintech corporations and their services posted on Facebook and Twitter, which are two of the most popular social media globally, during the period 2017–2019. The similarity was then quantified and categorized in terms of the representative global fintech companies and the status of each fintech service sector. Furthermore, the similarity was visualized, and value elements were rebuilt using ERRC strategy analytics.
Findings
This study is meaningful in that it quantifies the degree of similarity between customers' responses, experiences and expectations regarding the rapidly growing global fintech firms' services and trends in fintech services.
Originality/value
This study suggests a practical way to apply in business by providing a method for transforming unstructured text data into structured numerical data it is measurable. It is expected that this study can be used as the basis for exploring sustainable development strategies for the fintech industry.
Details
Keywords
JiHo Hwang, YoungJun Kim, Soekho Son and Jongmin Han
Accurate and timely foresight of future trends and changes in science and technology (S&T) is a key to national competitiveness. The purpose of this paper is to describe recent…
Abstract
Purpose
Accurate and timely foresight of future trends and changes in science and technology (S&T) is a key to national competitiveness. The purpose of this paper is to describe recent technological foresight conducted by the Technology Foresight Center at the Korea Institute of Science and Technology Evaluation and Planning. The authors also address current issues and problems encountered in the process of technology foresight (TF) in Korea.
Design/methodology/approach
The authors used TF methodologies which included bibliometrics, expert panels, SWOT analysis, and conferences/seminars.
Findings
The authors derived 20 future issues and 40 future needs in S&T from the five areas of global mega trends; then 200 future technologies were suggested with a time horizon of 40 years, from 2010 to 2050, for solving those future issues and needs. Finally, the authors suggested outlooks for technological development in the years 2020 and 2050.
Research limitations/implications
It is time to evaluate Korean TF exercises which were started 15 years ago. The evaluation of TF will help guide TF and inform policy and decision makers.
Practical implications
The findings can help policy makers shape future governmental S&T policy in Korea. The final result of this work was applied to the second S&T Framework Plan in Korea, in which 90 technologies were identified as national key technologies for the next five years, from 2008 to 2012.
Originality/value
To the best of the authors' knowledge, there are no studies suggesting not only future technologies based on solving future issues and needs but also outlooks for technology development in the years 2020 and 2050.
Details
Keywords
Magnus Osahon Igbinovia and Bolanle Clifford Ishola
Technological expansion and adoption in university libraries have precipitated cybercrimes and the need to equip library personnel with the required knowledge to combat this…
Abstract
Purpose
Technological expansion and adoption in university libraries have precipitated cybercrimes and the need to equip library personnel with the required knowledge to combat this menace. Consequently, this study aims to examine cyber security in university libraries and its implication for Library and Information Science education.
Design/methodology/approach
The study adopted descriptive research design, while questionnaire and interview were used to elicit data from library personnel and heads of library schools, respectively. A total of 134 responses were elicited through structured questionnaire (administered online due to the closure of universities) while six heads of library schools were interviewed, one from each of the six geopolitical zones in Nigeria.
Findings
The data from the questionnaire which were descriptively analysed revealed that the perceived knowledge of cyber security among the librarians was moderately low. Also, the university libraries were exposed to various cyber threats, with cyber security/guideline been one of the critical measures to combat cybercrime. Also, the result showed that librarians displayed high level of adherence to cyber ethics. However, the disposition of library management towards cyber security issues was revealed to be the main challenge to the deployment of cyber security in university libraries, follow by poor password management. Majority of the librarians possess basic knowledge of cyber security, though with serious interest to learn more about it. They were not taught cyber security in library school and they indicated enthusiasm to learn about it. The result of the interview with heads of library schools showed majority of these schools do not offer cyber security course due to dearth in skilled manpower.
Originality/value
The study presents cybercrime as a menace, if not tackled, would affect the university libraries’ sustainability as information institution, compromising their ability to deliver quality services.
Details
Keywords
Joon‐heon Song and Kyoung‐joo Lee
This paper aims to deepen understanding of the interrelated questions: how Japanese antidumping policies have been formulated and transformed; what the reasons are for such…
Abstract
Purpose
This paper aims to deepen understanding of the interrelated questions: how Japanese antidumping policies have been formulated and transformed; what the reasons are for such caution in adopting antidumping measures; and what patterns can be observed of recent changes in antidumping policy and legal systems.
Design/methodology/approach
To explain the changes in antidumping policy and rules in Japan, this paper examines not only political competition among bureaucratic organizations but also policy learning by bureaucratic organizations and their effects on change in policy preferences and advancements in the legal system.
Findings
The effects of bureaucratic politics and policy learning not only complexly interact but also are highly complicated to initiate policy changes in accordance with the maturity of antidumping legal system. In this case study, the policy learning has led the rival bureaucrats to a consensus to change antidumping policy and legal system, but the agreement could be a temporal truce that may easily collapse by political contingencies.
Originality/value
Along with the influences of large‐scale economic and political dynamisms, this paper focuses on two aspects of the policy subsystem to explain those changes: one is political competition among bureaucratic organizations claiming jurisdiction of antidumping policy; the other is the effect of policy learning among bureaucratic organizations on changes in policy preferences and on advancements in antidumping rules.
Details
Keywords
The purpose of this study is to explore the relationships among information‐seeking behavior, interpersonal communication, perceived procedural justice, and the reduction of…
Abstract
Purpose
The purpose of this study is to explore the relationships among information‐seeking behavior, interpersonal communication, perceived procedural justice, and the reduction of job‐related uncertainty.
Design/methodology/approach
The sample consisted of 323 Japanese white‐collar workers who completed the questionnaires, with a usable sample of 295.
Findings
The results of covariance structure analysis (SEM) revealed that: there were not any direct relationships between information‐seeking behavior and the reduction of work‐related uncertainty; information‐seeking behavior induced a change of voice, explanation, and rational interpersonal communication from decision makers; the provision of voice, explanation, and social sensitivity from decision makers caused outcome recipients’ perception of procedural justice; and their perception of procedural justice caused the reduction of job‐related uncertainty.
Research limitations/implications
There are some limitations of the present study that can be addressed in future research. First, the concept of uncertainty might have been used too broadly to have been applied to the concept of job‐related uncertainty. Second, the respondents in the present research were highly educated white‐collar workers and were selected to attend business school by their companies.
Practical implications
The results of the present study have some practical implications. Under a newly introduced managerial system of performance‐based personnel practices, Japanese companies need to establish a system by which workers can form judgements of fairness.
Originality/value
The paper suggests that one must exercise caution when generalizing the findings of the present study without taking into account the characteristics of the respondents.