Search results
1 – 10 of over 13000Ririn Diar Astanti, Ivana Carissa Sutanto and The Jin Ai
This paper aims to propose a framework on complaint management system for quality management by applying the text mining method and potential failure identification that can…
Abstract
Purpose
This paper aims to propose a framework on complaint management system for quality management by applying the text mining method and potential failure identification that can support organization learning (OL). Customer complaints in the form of email text is the input of the framework, while the most frequent complaints are visualized using a Pareto diagram. The company can learn from this Pareto diagram and take action to improve their process.
Design/methodology/approach
The first main part of the framework is creating a defect database from potential failure identification, which is the initial part of the failure mode and effect analysis technique. The second main part is the text mining of customer email complaints. The last part of the framework is matching the result of text mining with the defect database and presenting in the form of a Pareto diagram. After the framework is proposed, a case study is conducted to illustrate the applicability of the proposed method.
Findings
By using the defect database, the framework can interpret the customer email complaints into the list of most defect complained by customer using a Pareto diagram. The results of the Pareto diagram, based on the results of text mining of consumer complaints via email, can be used by a company to learn from complaint and to analyze the potential failure mode. This analysis helps company to take anticipatory action for avoiding potential failure mode happening in the future.
Originality/value
The framework on complaint management system for quality management by applying the text mining method and potential failure identification is proposed for the first time in this paper.
Details
Keywords
Ahmet Yucel, Musa Caglar, Hamidreza Ahady Dolatsara, Benjamin George and Ali Dag
Machine learning algorithms are useful to effectively analyse, and therefore automatically classify online reviews. The purpose of this paper is to demonstrate a novel text-mining…
Abstract
Purpose
Machine learning algorithms are useful to effectively analyse, and therefore automatically classify online reviews. The purpose of this paper is to demonstrate a novel text-mining framework and its potential for use in the classification of unstructured hotel reviews.
Design/methodology/approach
Well-known data mining methods (i.e. boosted decision trees (BDT), classification and regression trees (C&RT) and random forests (RF)) in conjunction with incorporating five-fold cross-validation are used to predict the star rating of the hotel reviews. To achieve this goal, extracted features are used to create a composite variable (CV) to deploy into machine learning algorithms as the main feature (variable) during the learning process.
Findings
BDT outperformed the other alternatives in the exact accuracy rate (EAR) and multi-class accuracy rate (MCAR) by reaching the accuracy rates of 0.66 and 0.899, respectively. Moreover, phrases such as “clean”, “friendly”, “nice”, “perfect” and “love” are shown to be associated with four and five stars, whereas, phrases such as “horrible”, “never”, “terrible” and “worst” are shown to be associated with one and two-star hotels, as it would be the intuitive expectation.
Originality/value
To the best of the knowledge, there is no study in the existent literature, which synthesizes the knowledge obtained from individual features and uses them to create a single composite variable that is powerful enough to predict the star rates of the user-generated reviews. This study believes that the proposed method also provides policymakers with a unique window in the thoughts and opinions of individual users, which may be used to augment the current decision-making process.
Details
Keywords
Abstract
Details
Keywords
Arun Malik, Shamneesh Sharma, Isha Batra, Chetan Sharma, Mahender Singh Kaswan and Jose Arturo Garza-Reyes
Environmental sustainability is quickly becoming one of the most critical issues in industry development. This study aims to conduct a systematic literature review through which…
Abstract
Purpose
Environmental sustainability is quickly becoming one of the most critical issues in industry development. This study aims to conduct a systematic literature review through which the author can provide various research areas to work on for future researchers and provide insight into Industry 4.0 and environmental sustainability.
Design/methodology/approach
This study accomplishes this by performing a backward analysis using text mining on the Scopus database. Latent semantic analysis (LSA) was used to analyze the corpus of 4,364 articles published between 2013 and 2023. The authors generated ten clusters using keywords in the industrial revolution and environmental sustainability domain, highlighting ten research avenues for further exploration.
Findings
In this study, three research questions discuss the role of environmental sustainability with Industry 4.0. The author predicted ten clusters treated as recent trends on which more insight is required from future researchers. The authors provided year-wise analysis, top authors, top countries, top sources and network analysis related to the topic. Finally, the study provided industrialization’s effect on environmental sustainability and the future aspect of automation.
Research limitations/implications
The reliability of the current study may be compromised, notwithstanding the size of the sample used. Poor retrieval of the literature corpus can be attributed to the limitations imposed by the search words, synonyms, string construction and variety of search engines used, as well as to the accurate exclusion of results for which the search string is insufficient.
Originality/value
This research is the first-ever study in which a natural language processing technique is implemented to predict future research areas based on the keywords–document relationship.
Details
Keywords
Lu An, Chuanming Yu, Xia Lin, Tingyao Du, Liqin Zhou and Gang Li
The purpose of this paper is to identify salient topic categories and outline their evolution patterns and temporal trends in microblogs on a public health emergency across…
Abstract
Purpose
The purpose of this paper is to identify salient topic categories and outline their evolution patterns and temporal trends in microblogs on a public health emergency across different stages. Comparisons were also examined to reveal the similarities and differences between those patterns and trends on microblog platforms of different languages and from different nations.
Design/methodology/approach
A total of 459,266 microblog entries about the Ebola outbreak in West Africa in 2014 on Twitter and Weibo were collected for nine months after the inception of the outbreak. Topics were detected by the latent Dirichlet allocation model and classified into several categories. The daily tweets were analyzed with the self-organizing map technique and labeled with the most salient topics. The investigated time span was divided into three stages, and the most salient topic categories were identified for each stage.
Findings
In total, 14 salient topic categories were identified in microblogs about the Ebola outbreak and were summarized as increasing, decreasing, fluctuating or ephemeral types. The topical evolution patterns of microblogs and temporal trends for topic categories vary on different microblog platforms. Twitter users were keen on the dynamics of the Ebola outbreak, such as status description, secondary events and so forth, while Weibo users focused on background knowledge of Ebola and precautions.
Originality/value
This study revealed evolution patterns and temporal trends of microblog topics on a public health emergency. The findings can help administrators of public health emergencies and microblog communities work together to better satisfy information needs and physical demands by the public when public health emergencies are in progress.
Details
Keywords
Bernard Rothenburger and Daniel Galarreta
The aim of this paper is to provide a conceptual and methodological framework in order to prevent knowledge loss in a long duration space project.
Abstract
Purpose
The aim of this paper is to provide a conceptual and methodological framework in order to prevent knowledge loss in a long duration space project.
Design/methodology/approach
Starting from risk management, the paper considers existing factors that contribute to the success of the mission, such as dependability and safety, and then argues, using a multi‐viewpoint approach, that risk analysis produces knowledge (not simply information or data). Then, the paper describes how the filtering of risky components of a technical documentation is performed. It is based on the confrontation of the vocabulary of the different documents to an ontology of “criticality” built by the authors. The paper also describes how the knowledge evolutions are detected and how the interpretation of these evolutions is carried out.
Findings
On a conceptual side, a general model of the design process is presented based on a multi‐viewpoints approach and characterised by a value system. On the practical side, an ontology of risk, used as a reference system in order to compare knowledge at different stages of a project, is described.
Research limitations/implications
Some difficulty arises when a very huge documentation is addressed. Among all evolution clues a lot of them could be well‐known by everybody or could be of little importance.
Practical implications
The paper intends to have a preventive strategy for knowledge loss in a long duration project. Reaching the ultimate stage of a mission, project management should be able to identify the main knowledge differences between technical culture of new incomers and the one of the early designer that can be found in the project documents.
Originality/value
The paper carries a multi‐discipline approach, putting together different domains: space activity, statistic specialist, knowledge managements, and linguistics.
Details
Keywords
Lu An, Yan Shen, Yanfang Tao, Gang Li and Chuanming Yu
This study aims to profile the government microbloggers and evaluate their roles. The results can help improve the governments' response capability to public emergencies.
Abstract
Purpose
This study aims to profile the government microbloggers and evaluate their roles. The results can help improve the governments' response capability to public emergencies.
Design/methodology/approach
This study proposes the user profiling and role evaluation model of government microbloggers in the context of public emergencies. The indicators are designed from the four dimensions of time, content, scale and influence, and the feature labels are identified. Three different public emergencies were investigated, including the West Africa Ebola outbreak, the Middle East respiratory syndrome outbreak and the Shandong vaccine case in China.
Findings
The results found that most government microbloggers were follower responders, short-term participants, originators, occasional participants and low influencers. The role distribution of government microbloggers was highly concentrated. However, in terms of individual profiles, the role of a government microblogger varied with events.
Social implications
The findings can provide a reference for the performance assessment of the government microbloggers in the context of public emergencies and help them improve their ability to communicate with the public and respond to public emergencies.
Originality/value
By analyzing the performance of government microbloggers from the four dimensions of time, content, scale and influence, this paper fills the gap in existing literature on designing the user profiling and role evaluation model of government microbloggers in the context of public emergencies.
Details
Keywords
Soohyung Joo and Gisela M. Schmidt
This study aims to investigate the perceptions of academic librarians regarding research data services (RDS) in academic library environments. This study also examines a range of…
Abstract
Purpose
This study aims to investigate the perceptions of academic librarians regarding research data services (RDS) in academic library environments. This study also examines a range of challenges in RDS from the perspectives of academic librarians.
Design/methodology/approach
A nationwide online survey was administered to academic librarians engaged in data services at research universities around the USA. The collected survey responses were analyzed quantitatively using descriptive statistics, hierarchical clustering and multidimensional scaling.
Findings
Academic librarians perceived that consultation services would be more valuable to users than technical services in offering RDS. Accordingly, skills associated with consultation services such as instructional skills and data management planning were perceived by participants to be more important. The results revealed that academic libraries would need to seek collaboration opportunities with other units on campus to develop and offer RDS, especially technical services.
Originality/value
This study contributes to the existing body of research on the topic of data services in research universities. The study investigated various types of specific professional competencies and used clustering analysis to identify closely associated groups of service types. In addition, this study comprehensively examined both relevant resources for and barriers to RDS.
Details
Keywords
Malika Neifar, Amira Ghorbel and Kawthar Bouaziz
This study attempts to come in help for Morocco by investigating rigorously the linkage between environmental degradation, measured by ecological footprint (EF), and the gross…
Abstract
Purpose
This study attempts to come in help for Morocco by investigating rigorously the linkage between environmental degradation, measured by ecological footprint (EF), and the gross domestic product growth (EG), the human capital (HC) index and the natural resources (NR) depletion over the period of 1980:Q1 to 2021:Q1. The paper examines the validity of environmental Kuznets curve (EKC) hypothesis in the Moroccan context.
Design/methodology/approach
Unlike previous studies, which are based only on the autoregressif dynamic linear (ARDL) model, this paper investigates two recent models: the novel DYNARDL simulation approach and the Kernel-based regularized least squares (KRLS) technics and uses in addition the frequency domain causality (FDC) test.
Findings
Models output say a significant and negative association between HC and the EF and a significant and positive interplay between economic growth and environmental quality in the long term. In the short term, findings reveal a significant and negative association between NR and the EF. Based on the FDC test, results conclude about a unidirectional causality from NR to the EF in short-, medium-, and long-term. Moreover, results validate the EKC hypothesis for the Moroccan environment sustainability.
Originality/value
In this study, the researchers use the “ecological footprint” as dependent variable to obtain more accurate and comprehensive assessment of environmental deterioration. Based on time series data investigations, this study is the first paper, which validates the EKC hypothesis and develops important policy implications for Morocco context to achieve sustainable development targets.
Details
Keywords
Geeta Rana and Vikas Arya
This study sought to determine the role of green human resource management (GHRM) in fostering employees' environmental performance (ENVP). This study aims to advance knowledge…
Abstract
Purpose
This study sought to determine the role of green human resource management (GHRM) in fostering employees' environmental performance (ENVP). This study aims to advance knowledge related to the role of firms’ GHRM activities in cultivating eco-responsible behaviors among employees, considering green innovation (GI) as a mediator.
Design/methodology/approach
For this study, data of 579 respondents were collected from employees working in the manufacturing industry in India. In all, 579 employees from the manufacturing sector in India participated in the study. The proposed model was tested using SMART PLS 3.3.
Findings
The findings of this study stated that GHRM was found significantly to predict ENVP in the Indian manufacturing industry, and GI exhibited partial mediation. This study emphasizes that GHRM activities carried out by firms encourage employees to engage in innovation to develop green products and find novel green operation processes to improve firms’ ENVP.
Research limitations/implications
As this study is limited to manufacturing organizations in India, the results of this study cannot be generalized; future studies may examine the proposed model in different contexts to generalize findings.
Originality/value
This study encourages policymakers to devise laws to enable organizations to implement GHRM practices. This study contributes to the existing literature on the environmental aspects of corporate social responsibility and environmental management. This study is one of the few attempts that seek to assess the relationship between GHRM, ENVP and GI in the Indian manufacturing industry. The contribution of this paper is significant to limit GHRM literature, as it empirically investigates the association between GHRM and ENVP.
Details