Introduction: Online Learning and Big Data in Horticulture: New Insights and Directions

in HortTechnology

It is well documented that the scientific community is dealing with the “big data” challenge, where researchers are grappling with massive data sets and developing protocols for storing, exchanging, and publishing research data (Marx, 2013; Schadt et al., 2010; Swedlow et al., 2011). As horticultural researchers gain access to increasingly affordable high-throughput instruments, even small research laboratories can become big data generators. This means that horticultural researchers have to become familiar with the tools used in the storage, analysis, and sharing of large data sets. Big data concepts and analytics can also be applied to online learning applications, including monitoring and evaluation of learner performance (Picciano, 2012). Within this context, “big data” is a generic term that assumes that the database system used as the main storage facility is capable of storing large quantities of data longitudinally and down to specific transactions (Picciano, 2012). Analytics is defined as the use of data to determine courses of action especially where there is a high volume of transactions (Picciano, 2012). Thus, for horticulture teachers and educators, the era of big data brings unique opportunities to improve the online learning experience. A prerequisite for the application of big data concepts and analytics to current online learning systems is the development of a well-planned online learning platform. In particular, asynchronous learning platforms can require significant time and resources during the development stages.

This workshop has two main objectives. First, provide an overview of new computing tools and approaches for improving data management in horticulture. Second, share practical experiences and insights in the development of an asynchronous online extension platform. The first paper aims to introduce valuable concepts and techniques to improve familiarity with advanced computing tools and increase efficiency of data management using the publicly available software package R (R Core Team, 2013). The paper addressed the following specific learning objectives: data structures and workflow, installing additional packages, and how to import, subset, and export data.

The remainder of the session will be devoted to the presentation of two related papers by a multidisciplinary team representing different institutions. This team has the unique and valuable experience of developing and making available an asynchronous online extension platform. The first paper will provide an overview of platform development from conceptualization to content development as well as initial and recurring costs. This presentation underscores the fact that the development of an online learning platform requires that all members of the development team must have clearly defined roles and responsibilities that are mapped to a project timetable. The second paper compares the asynchronous online extension platform with a traditional face-to-face program for delivering course content. Although the online platform will potentially reach a wider audience due to scheduling flexibility and elimination of travel relative to traditional delivery methods, asynchronous programs can require significant time and resources during the initial development stage. The advantages and disadvantages of each type of program delivery will be covered along with other considerations like cost of development, administration, and ability to respond to emerging issues.

The papers from this workshop provide an overview of the opportunities and constraints confronting horticulture professionals in the era of big data. It is hoped that the papers provide guidance for others who are planning to leverage big data concepts to promote horticulture research, teaching, and extension.

Literature cited

  • MarxV.2013Biology: The big challenges of big dataNature498255260

  • PiccianoA.G.2012The evolution of big data and learning analytics in American higher educationJ. Asynchronous Learn. Netw.16920

  • R Core Team2013R: A language and environment for statistical computing. R Foundation for Statistical Computing Vienna Austria

  • SchadtE.E.LindermanM.D.SorensonJ.LeeL.NolanG.P.2010Computational solutions to large-scale data management and analysisNat. Rev. Genet.11647657

    • Search Google Scholar
    • Export Citation
  • SwedlowJ.R.ZanettiG.BestC.2011Channeling the data delugeNat. Methods8463465

If the inline PDF is not rendering correctly, you can download the PDF file here.

Contributor Notes

This paper was part of the workshop “Online Learning and Big Data in Horticulture: New Insights and Directions” held on 4 Aug. 2015 at the ASHS Annual Conference in New Orleans, LA, and sponsored by the Computer Applications in Horticulture (COMP) Working Group.Mention of trademark, proprietary product or method, and vendor does not imply endorsement by the Louisiana State University Agricultural Center nor its approval to the exclusion of other suitable products or vendors.

Corresponding author. E-mail: avillordon@agcenter.lsu.edu.

  • MarxV.2013Biology: The big challenges of big dataNature498255260

  • PiccianoA.G.2012The evolution of big data and learning analytics in American higher educationJ. Asynchronous Learn. Netw.16920

  • R Core Team2013R: A language and environment for statistical computing. R Foundation for Statistical Computing Vienna Austria

  • SchadtE.E.LindermanM.D.SorensonJ.LeeL.NolanG.P.2010Computational solutions to large-scale data management and analysisNat. Rev. Genet.11647657

    • Search Google Scholar
    • Export Citation
  • SwedlowJ.R.ZanettiG.BestC.2011Channeling the data delugeNat. Methods8463465

All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 126 122 3
PDF Downloads 27 24 1