CCE Theses and Dissertations
Author-Statement Citation Analysis Applied as a Recommender System to Support Non-Domain-Expert Academic Research
Date of Award
2007
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Computing Technology in Education (DCTE)
Department
Graduate School of Computer and Information Sciences
Advisor
William Hafner
Committee Member
Sumitra Mukherjee
Committee Member
Timothy Ellis
Abstract
This study will investigate the use of citation indexing to provide expert recommendations to domain-novice researchers. Prioritizing the result-set returned from an electronic academic library query is both an essential task and a significant start-up burden for a domain-novice researcher. Current literature reveals many attempts to provide recommender systems in support of research. However, these systems rely on some form of relevance feedback from the user. The domain-novice researcher is unable to satisfy this expectation. Additional research demonstrates that a network of expert recommendations is available in each collection of academic documents. A power distribution, Lotka's law, has been found to be an attribute of the citation network found in large collections of academic domain documents.
The issue under study is whether the network of recommendations found in a relatively small collection of academic documents reveals a citation density that conforms to the distribution pattern of large collections. This study will use a descriptive, comparative methodology to answer this question. The study will use Lotka's law to form a predicted density and distribution for comprehensive domain collections. Next, the study will calculate an actual concentration and distribution from a sample population. The sample population will be a result-set returned from a general query to an academic collection.
The two indexes and distributions will be statistically compared to ascertain whether the actual density is equivalent to the predicted. If the sample set does not conform to normative Lotkian density, it will demonstrate an unnatural bias and therefore not qualify as an appropriate set of recommendations for guiding domain novice research.
The null hypothesis is that the actual density will be statistically equal to the predicted index. If this expectation is met, the result will be a set of expert recommendations that is user-independent for providing domain-relevant expert prioritization. A recommender system based on such recommendations would significantly improve the early research tasks of a domain novice by overcoming the identified start-up problem. It would remove the burden of expertise required when a domain novice seeks to effectively use the result set from a novice query. This experiment will test an alternative hypothesis by isolating smaller subsets of the sample and testing the citation density of each using a factorial orthogonal design. This experiment will attempt to determine the minimal population size valid for the predicted density index. It is anticipated that a sample size below the lower bound for distribution validity will be non-ambiguously identified by actual indexes significantly below that of the standard
NSUWorks Citation
Rick Blazek. 2007. Author-Statement Citation Analysis Applied as a Recommender System to Support Non-Domain-Expert Academic Research. Doctoral dissertation. Nova Southeastern University. Retrieved from NSUWorks, Graduate School of Computer and Information Sciences. (416)
https://nsuworks.nova.edu/gscis_etd/416.