Educational data mining: a systematic review of research and emerging trends

2020 ◽  
Vol 48 (4) ◽  
pp. 225-236
Author(s):  
Xu Du ◽  
Juan Yang ◽  
Jui-Long Hung ◽  
Brett Shelton

Purpose Educational data mining (EDM) and learning analytics, which are highly related subjects but have different definitions and focuses, have enabled instructors to obtain a holistic view of student progress and trigger corresponding decision-making. Furthermore, the automation part of EDM is closer to the concept of artificial intelligence. Due to the wide applications of artificial intelligence in assorted fields, the authors are curious about the state-of-art of related applications in Education. Design/methodology/approach This study focused on systematically reviewing 1,219 EDM studies that were searched from five digital databases based on a strict search procedure. Although 33 reviews were attempted to synthesize research literature, several research gaps were identified. A comprehensive and systematic review report is needed to show us: what research trends can be revealed and what major research topics and open issues are existed in EDM research. Findings Results show that the EDM research has moved toward the early majority stage; EDM publications are mainly contributed by “actual analysis” category; machine learning or even deep learning algorithms have been widely adopted, but collecting actual larger data sets for EDM research is rare, especially in K-12. Four major research topics, including prediction of performance, decision support for teachers and learners, detection of behaviors and learner modeling and comparison or optimization of algorithms, have been identified. Some open issues and future research directions in EDM field are also put forward. Research limitations/implications Limitations for this search method include the likelihood of missing EDM research that was not captured through these portals. Originality/value This systematic review has not only reported the research trends of EDM but also discussed open issues to direct future research. Finally, it is concluded that the state-of-art of EDM research is far from the ideal of artificial intelligence and the automatic support part for teaching and learning in EDM may need improvement in the future work.

2017 ◽  
Vol 28 (3) ◽  
pp. 295-321 ◽  
Author(s):  
Junjun Cheng ◽  
Yimin Huang ◽  
Yong Su

Purpose The purpose of this paper is to systematically review and analyze the important, yet under-researched, topic of relationality in negotiations and propose new directions for future negotiation research. Design/methodology/approach This paper conducts a systematic review of negotiation literature related to relationality from multiple disciplines. Thirty-nine leading and topical academic journals are selected and 574 papers on negotiation are reviewed from 1990 to 2014. Based on the systematic review, propositions regarding the rationales for relationality in negotiations are developed and future research avenues in this area are discussed. Findings Of 574 papers on negotiations published in 39 peer-reviewed journals between 1990 and 2014, only 18 papers have studied and discussed relationality in negotiations. This suggests that relationality as a theoretical theme has long been under-researched in negotiation research. For future research, this paper proposes to incorporate the dynamic, cultural and mechanism perspectives, and to use a qualitative approach to study relationality in negotiations. Originality/value This paper presents the first systematic review of the negotiation literature on relationality, and identifies new research topics on relationality in negotiations. In so doing, this research opens new avenues for future negotiation research on relationality.


Energies ◽  
2019 ◽  
Vol 12 (8) ◽  
pp. 1443 ◽  
Author(s):  
Zhang ◽  
Yuan

The increasing demand for applying energy performance contracting (EPC) for urban energy conservation has resulted in a significant amount of publications over the past decade. This study tries to identify future research trends in the subject of EPC through analyzing 127 journal papers published from 2008 to 2018. Based on the analysis and discussion of the EPC research, several main research trends were identified. The research results reveal an increasing research interest in EPC over the period. The findings imply that case study is the major research method and descriptive analysis and statistical analysis are primarily used for data analysis. In addition, EPC research in the past decade focused on five major research topics, which are ‘implementation of EPC projects’, ‘EPC mechanism and business models’, ‘decision-making in EPC projects’, ‘Energy Service Companies (ESCOs) in EPC projects’, and ‘risk management in EPC projects’. Based on the five research topics, future research trends and directions in EPC were identified as well. The findings of this study can be informative and valuable for guiding future research in EPC, and are particularly helpful for researchers who are keen to open a new window of investigating EPC issues worldwide.


Mathematics ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 584 ◽  
Author(s):  
Gwo-Jen Hwang ◽  
Yun-Fang Tu

Learning mathematics has been considered as a great challenge for many students. The advancement of computer technologies, in particular, artificial intelligence (AI), provides an opportunity to cope with this problem by diagnosing individual students’ learning problems and providing personalized supports to maximize their learning performances in mathematics courses. However, there is a lack of reviews from diverse perspectives to help researchers, especially novices, gain a whole picture of the research of AI in mathematics education. To this end, this research aims to conduct a bibliometric mapping analysis and systematic review to explore the role and research trends of AI in mathematics education by searching for the relevant articles published in the quality journals indexed by the Social Sciences Citation Index (SSCI) from the Web of Science (WOS) database. Moreover, by referring to the technology-based learning model, several dimensions of AI in mathematics education research, such as the application domains, participants, research methods, adopted technologies, research issues and the roles of AI as well as the citation and co-citation relationships, are taken into account. Accordingly, the advancements of AI in mathematics education research are reported, and potential research topics for future research are recommended.


2020 ◽  
Author(s):  
Kashif Ahmad ◽  
Junaid Qadir ◽  
Ala Al-Fuqaha ◽  
Waleed Iqbal ◽  
Ammar El-Hassan ◽  
...  

Motivated by the importance of education in an individual's and a society's development, researchers have been exploring the use of Artificial Intelligence (AI) in the domain and have come up with myriad potential applications. This paper pays particular attention to this issue by highlighting the future scope and market opportunities for AI in education, the existing tools and applications deployed in several applications of AI in education, research trends, current limitations and pitfalls of AI in education. In particular, the paper reviews the various applications of AI in education including student grading and evaluations, students' retention and drop out prediction, sentiment analysis, intelligent tutoring, classrooms' monitoring and recommendation systems. The paper also provides a detailed bibliometric analysis to highlight the research trends in the domain over six years (2014--2019). For this study, we analyze research publications in various related sub-domains such as learning analytics, educational data mining (EDM), and big data in education. The paper analyzes educational applications from different perspectives. On the one hand, it provides a detailed description of the tools and platforms developed as the outcome of the research work achieved in these applications. On the other side, it identifies the potential challenges, current limitations and hints for further improvement. We also provide important insights into the use and pitfalls of AI in education. We believe such rigorous analysis will provide a baseline for future research in the domain.


2015 ◽  
Vol 27 (7) ◽  
pp. 1556-1572 ◽  
Author(s):  
Xi Yu Leung ◽  
Lan Xue ◽  
Billy Bai

Purpose – The purpose of this study is to provide a progress review of published Internet marketing research within the top eight hospitality and tourism journals and to provide suggestions on future research directions. Design/methodology/approach – The study collected 331 Internet marketing-related articles published in the top eight hospitality and tourism journals during the period of 1996-2013. Using content analysis, the study analyzed and discussed research topics, research methods and industry sectors of selected articles. The study period was broken into three sub-periods and used correspondence analysis (CA) to examine the significant changes of topical areas over time. A follow-up CA was conducted to compare the topical and methodological preferences of the selected eight journals. Findings – In all, 5-category and 27-subcategory classifications of research topics were identified in the study. The two-dimensional perceptual map indicates that Internet marketing research in the hospitality and tourism fields experienced introduction, growth and maturity stages. The research focus changed from business perspective to customer perspective and then to both business and customer perspectives. The eight top hospitality and tourism journals were grouped into four journal sets that share similar article characteristics and preferences. Research limitations/implications – Due to the sample size, the classifications and trends generated in this study may not be generalized to all Internet marketing research in hospitality and tourism disciplines. The process of identifying topic and method categories might be biased, especially in identifying new topics. Future research may apply CA method in literature review studies on other research topics. Practical implications – The study analyzed published research in Internet marketing in the hospitality and tourism fields and provided topical and methodological recommendations to academia for future research. This study may also give hospitality managers new insights into Internet marketing applications in the industry. Originality/value – This study is one of the few attempts to provide a comprehensive review of Internet marketing research in the hospitality and tourism fields. This study uses CA in literature review study, opening up a new way to easily analyze and visually display the literature trends. This study also creatively compared the publication preferences among eight top-tier hospitality and tourism journals using correspondence analysis.


Author(s):  
Lucy T.B. Rattrie ◽  
Markus G. Kittler

Purpose – The purpose of this paper is to provide a synthesis and evaluation of literature surrounding the job demands-resources (JD-R) model (Demerouti et al., 2001) in the first decade since its inception, with particular emphasis on establishing an evidence-based universal application towards different national and international work contexts. Design/methodology/approach – The study uses a systematic review approach following the stages suggested by Tranfield et al. (2003). Based on empirical data from 62 studies, the authors systematically analyse the application of the JD-R model and queries whether it is applicable outside merely domestic work contexts. Findings – The authors find convincing support for the JD-R model in different national contexts. However, the authors also found an absence of studies employing the JD-R model in cross-national settings. None of the empirical studies in the sample had explicitly considered the international context of today’s work environment or had clearly associated JD-R research with the IHRM literature. Research limitations/implications – Based on the wide acceptance of the JD-R model in domestic work contexts and the increased interest in work-related outcomes such as burnout and engagement in the IHRM literature, the study identifies a gap and suggests future research applying the JD-R model to international work and global mobility contexts. Originality/value – This study is the first to systematically assess the application of the JD-R model in domestic and international work contexts based on a systematic review of empirical literature in the first decade since the inception of the model. The study identifies a lack of internationally focussed JD-R studies and invites further empirical research and theoretical extensions.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Md Aynul Hoque ◽  
Rajah Rasiah ◽  
Fumitaka Furuoka ◽  
Sameer Kumar

Purpose This paper aims to identify key theoretical cornerstones and research trends in the apparel industry. It also compares theoretical bases with those of the general research domain in technology adoption literature and, thus, provides future policy guidelines for practitioners and research gaps for further studies. Design/methodology/approach Documents were collected from the Web of Science (core collection) database using systematic methods. The bibliometric coupling and co-citation analyses were conducted using VOSviewer software to construct theoretical cornerstones and research trends in the apparel industry. Findings Literature in the apparel industry focuses mainly on the diffusion of innovation and the theory of reasoned action. Hence, the literature lacks investigations of technology–organization–environment and institutional theories for technology adoption in the apparel industry. This study also traces six clusters of prevalent research trends: radiofrequency identification, virtual-try on technology for e-commerce, computer-aided design, Industry 4.0 technologies, virtual-try on technology in design and information technology. Originality/value Little research is done on theoretical cornerstones on technology adoption in the apparel industry. This study looks into the theoretical bases for technology adoption, research trends in the apparel supply chain and calls for future research necessities.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ankita Bhatia ◽  
Arti Chandani ◽  
Rizwana Atiq ◽  
Mita Mehta ◽  
Rajiv Divekar

Purpose The purpose of this study is to gauge the awareness and perception of Indian individual investors about a new fintech innovation known as robo-advisors in the wealth management scenario. Robo-advisors are comprehensive automated online advisory platforms that help investors in managing wealth by recommending portfolio allocations, which are based on certain algorithms. Design/methodology/approach This is a phenomenological qualitative study that used five focussed group discussions to gather the stipulated information. Purposive sampling was used and the sample comprised investors who actively invest in the Indian stock market. A semi-structured questionnaire and homogeneous discussions were used for this study. Discussion time for all the groups was 203 min. One of the authors moderated the discussions and translated the audio recordings verbatim. Subsequently, content analysis was carried out by using the NVIVO 12 software (QSR International) to derive different themes. Findings Factors such as cost-effectiveness, trust, data security, behavioural biases and sentiments of the investors were observed as crucial points which significantly impacted the perception of the investors. Furthermore, several suggestions on different ways to enhance the awareness levels of investors were brought up by the participants during the discussions. It was observed that some investors perceive robo-advisors as only an alternative for fund/wealth managers/brokers for quantitative analysis. Also, they strongly believe that human intervention is necessary to gauge the emotions of the investors. Hence, at present, robo-advisors for the Indian stock market, act only as a supplementary service rather than a substitute for financial advisors. Research limitations/implications Due to the explorative nature of the study and limited participants, the findings of the study cannot be generalised to the overall population. Future research is imperative to study the dynamic nature of artificial intelligence (AI) theories and investigate whether they are able to capture the sentiments of individual investors and human sentiments impacting the market. Practical implications This study gives an insight into the awareness, perception and opinion of the investors about robo-advisory services. From a managerial perspective, the findings suggest that additional attention needs to be devoted to the adoption and inculcation of AI and machine learning theories while building algorithms or logic to come up with effective models. Many investors expressed discontent with the current design of risk profiles of the investors. This helps to provide feedback for developers and designers of robo-advisors to include advanced and detailed programming to be able to do risk profiling in a more comprehensive and precise manner. Social implications In the future, robo-advisors will change the wealth management scenario. It is well-established that data is the new oil for all businesses in the present times. Technologies such as robo-advisor, need to evolve further in terms of predicting unstructured data, improvising qualitative analysis techniques to include the ability to gauge emotions of investors and markets in real-time. Additionally, the behavioural biases of both the programmers and the investors need to be taken care of simultaneously while designing these automated decision support systems. Originality/value This study fulfils an identified gap in the literature regarding the investors’ perception of new fintech innovation, that is, robo-advisors. It also clarifies the confusion about the awareness level of robo-advisors amongst Indian individual investors by examining their attitudes and by suggesting innovations for future research. To the best of the authors’ knowledge, this study is the first to investigate the awareness, perception and attitudes of individual investors towards robo-advisors.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Victor Saha ◽  
Praveen Goyal ◽  
Charles Jebarajakirthy

Purpose The purpose of this paper is to present a systematic review of the available literature on value co-creation (VCC) and provide insightful future directions for research in this domain. Design/methodology/approach The extant literature on VCC has been reviewed by collecting relevant research papers based on certain specified delimiting criteria. A total of 110 research papers have been analysed to gain useful insights into VCC literature. Findings The study analyses the literature on VCC and provides a clear distinction between VCC and its closely related constructs in the literature. The study also draws significant insights from the VCC literature based on some specific parameters. Some frequently used theoretical perspectives have been discussed in the study, thus pointing towards a few alternative theories that can be used for future research. Finally, specific trends emerging from the literature have been discussed that provide a comprehensive understanding of the research inclinations of this concept, along with future scopes of research in the VCC domain. Research limitations/implications The papers were selected for this study based on some delimiting criteria. Thus, the findings cannot be generalised for the entire research on VCC. Originality/value This paper fulfils the need for a systematic review of the extant literature on VCC. The study synthesises literature and bibliography on VCC from 2004 to 2019 to benefit both academics and practitioners and gives some directions to advance this domain of literature.


Sign in / Sign up

Export Citation Format

Share Document