Show simple item record

dc.contributor.authorOrwig, Richard Eldon.
dc.creatorOrwig, Richard Eldon.en_US
dc.date.accessioned2011-10-31T18:34:27Z
dc.date.available2011-10-31T18:34:27Z
dc.date.issued1995en_US
dc.identifier.urihttp://hdl.handle.net/10150/187257
dc.description.abstractThis dissertation describes research in the application and evaluation of a Kohonen Self-Organizing Map (SOM) to the problem of classification of Electronic Brainstorming output. Electronic Brainstorming is one of the most productive tools in the Electronic Meeting System called GroupSystems. A major step in group problem solving involves the classification of Electronic Brainstorming output into a manageable list of concepts, topics, or issues that can be further evaluated by the group. This step is problematic due to the information overload and cognitive load of the large quantity of data. This research builds upon previous work in automating the classification process using a Hopfield Neural Network. Evaluation of the Kohonen output in comparison with the Hopfield and human expert output over the same set of data found that the Kohonen SOM performed as well as a human expert in the recollection of associated term pairs and outperformed the Hopfield Neural Network algorithm. Using information retrieval measures, recall of concepts using the Kohonen algorithm was equivalent to the human expert. However, precision was poor. The graphical representation of textual data produced by the Kohonen SOM suggests many opportunities for improving information management of textual electronic information. Increasing uses of electronic mail, computer-based bulletin board systems, and world-wide web textual data suggest an overwhelming amount of textual information to manage. This research suggests that the Kohonen SOM may be used to automatically create "a picture that can represent a thousand (or more) words."
dc.language.isoenen_US
dc.publisherThe University of Arizona.en_US
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en_US
dc.subjectSoftware architecture.en_US
dc.subjectComputer software -- Human factors.en_US
dc.subjectGraphical user interfaces (Computer systems)en_US
dc.titleA graphical, self-organizing approach to classifying electronic meeting output.en_US
dc.typetexten_US
dc.typeDissertation-Reproduction (electronic)en_US
dc.contributor.chairChen, Hsinchunen_US
dc.identifier.oclc706711414en_US
thesis.degree.grantorUniversity of Arizonaen_US
thesis.degree.leveldoctoralen_US
dc.contributor.committeememberNunamaker, Jay F. Jr.en_US
dc.contributor.committeememberVogel, Douglasen_US
dc.identifier.proquest9603707en_US
thesis.degree.disciplineBusiness Administrationen_US
thesis.degree.disciplineGraduate Collegeen_US
thesis.degree.namePh.D.en_US
dc.description.noteThis item was digitized from a paper original and/or a microfilm copy. If you need higher-resolution images for any content in this item, please contact us at repository@u.library.arizona.edu.
dc.description.admin-noteOriginal file replaced with corrected file April 2023.
refterms.dateFOA2018-04-25T14:52:44Z
html.description.abstractThis dissertation describes research in the application and evaluation of a Kohonen Self-Organizing Map (SOM) to the problem of classification of Electronic Brainstorming output. Electronic Brainstorming is one of the most productive tools in the Electronic Meeting System called GroupSystems. A major step in group problem solving involves the classification of Electronic Brainstorming output into a manageable list of concepts, topics, or issues that can be further evaluated by the group. This step is problematic due to the information overload and cognitive load of the large quantity of data. This research builds upon previous work in automating the classification process using a Hopfield Neural Network. Evaluation of the Kohonen output in comparison with the Hopfield and human expert output over the same set of data found that the Kohonen SOM performed as well as a human expert in the recollection of associated term pairs and outperformed the Hopfield Neural Network algorithm. Using information retrieval measures, recall of concepts using the Kohonen algorithm was equivalent to the human expert. However, precision was poor. The graphical representation of textual data produced by the Kohonen SOM suggests many opportunities for improving information management of textual electronic information. Increasing uses of electronic mail, computer-based bulletin board systems, and world-wide web textual data suggest an overwhelming amount of textual information to manage. This research suggests that the Kohonen SOM may be used to automatically create "a picture that can represent a thousand (or more) words."


Files in this item

Thumbnail
Name:
azu_td_9603707_sip1_c.pdf
Size:
9.134Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record