Knowledge exploration with concept association techniques
| Pages | 786-805 |
| Published date | 28 September 2010 |
| DOI | https://doi.org/10.1108/14684521011084627 |
| Date | 28 September 2010 |
| Author | Chen‐Chung Liu,Shih‐Hsun Fan Chiang,Chih‐Yueh Chou,Sherry Y. Chen |
| Subject Matter | Information & knowledge management,Library & information science |
Knowledge exploration with
concept association techniques
Chen-Chung Liu and Shih-Hsun Fan Chiang
Graduate Institute of Network Learning Technology,
National Central University, Jhongli City, Taiwan, Republic of China
Chih-Yueh Chou
Department of Computer Science and Engineering, Yuan-Ze University,
Jhongli City, Taiwan, Republic of China, and
Sherry Y. Chen
Graduate Institute of Network Learning Technology,
National Central University, Jhongli City, Taiwan, Republic of China
Abstract
Purpose – Exploratory learning is regarded as an important ability for developing knowledge from
open environments. During the exploration, learners not only need to acquire new information based
on their current interests, but also they need to form new perspectives by incorporating new
knowledge into their previous knowledge. This paper seeks to address these issues.
Design/methodology/approach – To this end, this paper proposes an approach that includes a
concept association bank to recommend related concepts in a domain based on the goal of an exploration.
By doing so, learners’ knowledge can be expanded beyond their current understanding. An experiment
was conducted to investigate how the proposed approach facilitated the learners’ exploration.
Findings – The results indicated that the concept association bank is a useful mechanism to help
learners gain new understanding, including providing exploration directions, reducing complexity and
cognitive load, facilitating data- and goal-driven exploration strategies, and commenting on new
understanding. The implications of these results are discussed.
Originality/value – Current recommendation systems emphasise a data-driven strategy, which
seeks isolated pieces of information, instead of suggesting directions related to their exploration goal.
The problem with such an approach is that learners’ exploration will be limited by their existing
knowledge. Thus, this paper presents an approach to support both data- and goal-driven strategies.
Keywords Worldwide web, Learning, Knowledge mining
Paper type Research paper
Introduction
Exploratory learning ( Jonassen and Mandl, 1990; Rieman, 1996) is regarded as an
important ability for developing knowledge from open environments, such as the web
and internet databases, since they contain valuable and comprehensive information for
learners. Learners need to uncover interrelated concepts and topics to explore a domain
in an exploratory learning environment. More specifically, this is a self-initiated
and goal-oriented process, during which learners independently explore information
in databases and gradually acquire new knowledge to extend their understanding
The current issue and full text archive of this journal is available at
www.emeraldinsight.com/1468-4527.htm
The authors appreciate the work of their anonymous reviewers in suggesting revisions for this
paper. This research was partially funded by the National Science Foundation under
98-2511-S-008-004-MY3, 98-2631-S-008-001, and 96-2524-S-008-002.
OIR
34,5
786
Refereed article received
30 September 2009
Approved for publication
31 January 2010
Online Information Review
Vol. 34 No. 5, 2010
pp. 786-805
qEmerald Group Publishing Limited
1468-4527
DOI 10.1108/14684521011084627
(Hohl et al., 1996). However, learners may easily experience disorientation and find the
cognitive load too heavy (Conklin, 1989; Madrid et al., 2009) due to the huge amount of
information. Therefore, facilitating information extraction and assisting learners to
explore the environments become critical issues to support exploratory learning. In
other words, there is a need to develop a mechanism that can help students to investigate
the domain.
To address this issue, a number of recommendation mechanisms have been devised,
such as content-based filtering (Mooney and Roy, 2000) and collaborative filtering
(Good et al., 1999). Many of these mechanisms recommend information in order to
inform the users about new items such as books, etc. However, learners not only need to
acquire new information based on their current interests; they also need to form new
perspectives by incorporating new knowledge into their previous knowledge (Siemens,
2005). While new knowledge is built on previous knowledge, the development of new
knowledge usually consists of associations that had not been thought of before
(Shneiderman, 2000). Therefore, it is necessary to provide learners with
recommendations for further expanding their current understanding. However, the
informationobjectsrecommendedbycurrent recommendation systems are
“overspecialised” (Adomavicius et al., 2005) and thus learners’ exploration of the
recommendation will be limited by their existing knowledge. This is due to the fact that
the current recommendation systems emphasise a data-driven strategy, which seeks
isolated pieces of information based on their current interests, instead of suggesting new
directions which would help learners to expand their current understanding.
Expanding current understanding of a domain can be achieved by associations,
which indicate correlations between learning objects (Ouyang and Zhu, 2008). In order to
facilitate learners’ associations this paper developed a mind map tool equipped with
association support to provide learners with concepts related to their current
understanding. The mind map tool provides a kind of association support that
recommends concept keywords as new directions for exploration. The association
support facilitates learners to explore a domain using the work of experts in a particular
community. The concept associations were not provided by teachers or stakeholders;
instead they were obtained by mining academic articles contributed by a majority of
experts in a professional community. Recently, online academic collective databases
have become an important channel for accumulating the work of experts in a
community. It is hoped that the concept associations obtained from online academic
collective databases will help to stimulate divergent exploration directions and deepen
the exploration of a domain. However, the strategies that learners apply to explore a
domain may vary (Hill and Hannafin, 1997). Therefore, it is necessary to analyse their
exploration strategies when they are provided with the mind map tool. To this end,
we conducted an empirical study to examine how the concept association approach
affects exploratory learning. The ultimate goal of the empirical study was to develop a
framework based on the answers to the following research questions:
RQ1. How can the concept association support help learners to identify exploratory
directions?
RQ2. How can the concept association support reduce the learners’ cognitive load?
RQ3. How can the concept association support affect learners’ information seeking
strategies?
Concept
association
techniques
787
To continue reading
Request your trial