Mining for Reengineering: An Application to Semantic Wikis Using Formal and Relational Concept Analysis

Abstract

Semantic wikis enable collaboration between human agents for creating knowledge systems. In this way, data embedded in semantic wikis can be mined and the resulting knowledge patterns can be reused to extend and improve the structure of wikis. This paper proposes a method for guiding the reengineering and improving the structure of a semantic wiki. This method suggests the creation of categories and relations between categories using Formal Concept Analysis (FCA) and Relational Concept Analysis (RCA). FCA allows the design of a concept lattice while RCA provides relational attributes completing the content of formal concepts. The originality of the approach is to consider the wiki content from FCA and RCA points of view and to extract knowledge units from this content allowing a factorization and a reengineering of the wiki structure. This method is general and does not depend on any domain and can be generalized to every kind of semantic wiki. Examples are studied throughout the paper and experiments show the substantial results.

Towards the Extraction of Variability Information to Assist Variability Modelling of Complex Product Lines

“…Relational Concept Analysis: RCA was first used to build class model abstractions [AFHN06]. It has been applied for restructuring ontologies [STNB11,RHVN11], refactoring design defects [MHVG08] or extracting tranformation rules from model transformation examples [SDH + 12].…”

RCA-Seq: An original approach for enhancing the analysis of sequential data based on hierarchies of multilevel closed partially-ordered patterns

“…This algorithm is applicable to temporal concepts (in this case ipb 1 is replaced with ipb 2 ) as well. Lines [2][3][4][5][6][7][8]: delete all concepts in C next that are upper covers for other concepts in C next , i.e. delete concepts that are not the most specific ones in C next .…”

“…Second, in Algorithm 1, Lines are executed m times. Lines [5,7] have the complexity O(p) since C next contains p concepts pointed by Y m temporal relational attributes. Lines [8][9][10][11][12][13][14][15][16][17][18][19][20][21] are executed p times since each temporal concept of L Kt is visited only once and the complexity of these lines is O(p(q + p)).…”

“…It has been used with success in various domain, e.g. the fuzzy semantic annotation of web resources [3], the analysis and re-engineering of software models [4], or semantic wikis [5], or the extraction of rules from large datasets [6]. Nevertheless, RCA, as FCA, has some major challenges, one of them being the complexity of its result, since the number of concepts grows exponentially with the size of the dataset.…”

Generalization effect of quantifiers in a classification based on relational concept analysis

“…RCA has been applied to multi-relational datasets from various domains, e.g. for analyzing the quality of watercourses [4], for the fuzzy semantic annotation of web resources [5], or for the analysis and reengineering of software models [6] or semantic wikis [7].…”