scholarly journals Applying Text Mining Technique on Innovation-Development Relationship: A Joint Research Agenda

Author(s):  
CICEA CLAUDIU ◽  
LEFTERIS TSOULFIDIS ◽  
MARINESCU CORINA ◽  
POPA STEFAN CATALIN ◽  
ALBU CATALINA FLORENTINA
2019 ◽  
Vol 9 (1) ◽  
pp. 65-93 ◽  
Author(s):  
Alberto Arenal ◽  
Claudio Feijoo ◽  
Ana Moreno ◽  
Cristina Armuña ◽  
Sergio Ramos

Purpose Academic research into entrepreneurship policy is particularly interesting due to the increasing relevance of the topic and since knowledge about the evolution of themes in this field is still rather limited. The purpose of this paper is to analyse the key concepts, topics, trends and shifts that have shaped the entrepreneurship policy research agenda during the period 1990–2016. Design/methodology/approach This paper uses text mining techniques, cluster analysis and complementary bibliographic data to examine the evolution of a corpus of 1,048 academic papers focused on entrepreneurship-related policies and published during the period 1990–2016 in ten relevant journals. In particular, the paper follows a standard text mining workflow: first, as text is unstructured, content requires a set of pre-processing tasks and then a stemming process. Then, the paper examines the most repeated concepts within the corpus, considering the whole period 1990–2016 and also in five-year terms. Finally, the paper conducts a k-means clustering to divide the collection of documents into coherent groups with similar content. The analyses in the paper also include geographical particularities considering three regional sub-corpora, distinguishing those articles authored in the European Union (EU), the USA and South and Eastern Asia, respectively. Findings Results of the analysis show that inclusion, employment and regulation-related papers have largely dominated the research in the field, evolving from an initial classical approach to the relationship between entrepreneurship and employment to a wider, multidisciplinary perspective, including the relevance of management, geographies and narrower topics such as agglomeration economics or internationalisation instead of the previous generic sectorial approaches. The text mining analysis also reveals how entrepreneurship policy research has gained increasing attention and has become both more open, with a growing cooperation among researchers from different affiliations, and more sophisticated, with concepts and themes that moved the research agenda forward, closer to the priorities of policy implementation. Research limitations/implications The paper identifies main trends and research gaps in the field of entrepreneurship policy providing actionable knowledge by presenting the spectrum of both over-explored and understudied research themes in the field. In practical terms the results of the text mining analysis can be interpreted as a compass to navigate the entrepreneurship policy research agenda. Practical implications The paper presents the heterogeneity of topics under research in the field, reinforcing the concept of entrepreneurship as a multidisciplinary and dynamic domain. Therefore, the definition and adoption of a certain policy agenda in entrepreneurship should consider multiple aspects (needs, objectives, stakeholders, expected outputs, etc.) to be comprehensive and aligned with its complexity. In addition, the paper shows how text mining techniques could be used to map the research activity in a particular field, contributing to the challenge of linking research and policy. Originality/value The exploratory nature of text mining allows us to obtain new knowledge and reveals hidden patterns from large quantities of documents/text data, representing an opportunity to complement other qualitative reviews. In this sense, the main value of this paper is not to advise on the future configuration of entrepreneurship policy as a research topic, but to unwrap the past by unveiling how key themes of the entrepreneurship policy research agenda have emerged, evolved and/or declined over time as a foundation on which to build further developments.


2021 ◽  
Author(s):  
Takumi Miura ◽  
Takumi Furukawa ◽  
Junko Harada ◽  
Yudai Hirano ◽  
Takako Hashimoto
Keyword(s):  

2015 ◽  
Vol 3 (2) ◽  
pp. 1-12
Author(s):  
Carl Lee

In this article, the authors conduct a case study using text mining technique to analyze the patterns of the president's State of the Union Address in USA, and investigate the effects of these speech patterns on their performance rating in the following year. The speeches analyzed include the recent four USA presidents, Bush (1989 – 1992), Clinton (1993 - 2000), G.W. Bush (2001 – 2008), and Obama (2009 – 2011). The patterns found are further integrated and merged with over 4000 surveys on the presidents' performance ratings from 1989 to 2010. Two text mining methodology are applied to study the text patterns. Two predictive modeling techniques are applied to study the effects of these found patterns to their presidential approval ratings. The results indicate that the speech patterns found are highly associated with their approval rates.


2019 ◽  
Vol 62 (2) ◽  
pp. 195-215
Author(s):  
Frederik Situmeang ◽  
Nelleke de Boer ◽  
Austin Zhang

The purpose of this study is to contribute to the marketing literature and practice by describing a research methodology to identify latent dimensions of customer satisfaction in product reviews, and examining the relationship between these attributes and customer satisfaction. Previous research in product reviews has largely relied only on quantitative ratings, either stars or review score. Advanced techniques for text mining provide the opportunity to extract meaning from customer online reviews. By analyzing 51,110 online reviews for 1,610 restaurants via latent Dirichlet allocation, this study uncovers 30 latent dimensions that are determinants of customer satisfaction. Furthermore, this study developed measurements of sentiment and innovativeness as moderators of the effect of these latent attributes to satisfaction.


2018 ◽  
Vol 22 (7) ◽  
pp. 1471-1488 ◽  
Author(s):  
Antonio Usai ◽  
Marco Pironti ◽  
Monika Mital ◽  
Chiraz Aouina Mejri

Purpose The aim of this work is to increase awareness of the potential of the technique of text mining to discover knowledge and further promote research collaboration between knowledge management and the information technology communities. Since its emergence, text mining has involved multidisciplinary studies, focused primarily on database technology, Web-based collaborative writing, text analysis, machine learning and knowledge discovery. However, owing to the large amount of research in this field, it is becoming increasingly difficult to identify existing studies and therefore suggest new topics. Design/methodology/approach This article offers a systematic review of 85 academic outputs (articles and books) focused on knowledge discovery derived from the text mining technique. The systematic review is conducted by applying “text mining at the term level, in which knowledge discovery takes place on a more focused collection of words and phrases that are extracted from and label each document” (Feldman et al., 1998, p. 1). Findings The results revealed that the keywords extracted to be associated with the main labels, id est, knowledge discovery and text mining, can be categorized in two periods: from 1998 to 2009, the term knowledge and text were always used. From 2010 to 2017 in addition to these terms, sentiment analysis, review manipulation, microblogging data and knowledgeable users were the other terms frequently used. Besides this, it is possible to notice the technical, engineering nature of each term present in the first decade. Whereas, a diverse range of fields such as business, marketing and finance emerged from 2010 to 2017 owing to a greater interest in the online environment. Originality/value This is a first comprehensive systematic review on knowledge discovery and text mining through the use of a text mining technique at term level, which offers to reduce redundant research and to avoid the possibility of missing relevant publications.


Sign in / Sign up

Export Citation Format

Share Document