Difference between revisions of "Wcaminer: a Novel Knowledge Discovery System for Mining Concept Associations Using Wikipedia"
(Int.links) |
(infobox) |
||
| Line 1: | Line 1: | ||
| + | {{Infobox work | ||
| + | | title = Wcaminer: a Novel Knowledge Discovery System for Mining Concept Associations Using Wikipedia | ||
| + | | date = 2014 | ||
| + | | authors = [[Peng Yan]]<br />[[Wei Jin]] | ||
| + | | link = | ||
| + | }} | ||
'''Wcaminer: a Novel Knowledge Discovery System for Mining Concept Associations Using Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2014, written by [[Peng Yan]] and [[Wei Jin]]. | '''Wcaminer: a Novel Knowledge Discovery System for Mining Concept Associations Using Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2014, written by [[Peng Yan]] and [[Wei Jin]]. | ||
== Overview == | == Overview == | ||
This paper presents WCAMiner, a system focusing on detecting how concepts are associated by incorporating [[Wikipedia]] knowledge. Authors propose to combine content analysis and link analysis techniques over Wikipedia resources, and define various association mining models to interpret such queries. Specifically, algorithm can automatically build a Concept Association Graph (CAG) from Wikipedia for two given topics of interest, and generate a ranked list of concept chains as potential associations between the two given topics. In comparison to traditional cross-document mining models where documents are usually domain-specific, the system proposed here is capable of handling different query scenarios across domains without being limited to the given documents. Authors highlight the importance of this problem in various domains, present experiments on different datasets and compare the mining results with two competitive baseline models to demonstrate the improved performance of system. | This paper presents WCAMiner, a system focusing on detecting how concepts are associated by incorporating [[Wikipedia]] knowledge. Authors propose to combine content analysis and link analysis techniques over Wikipedia resources, and define various association mining models to interpret such queries. Specifically, algorithm can automatically build a Concept Association Graph (CAG) from Wikipedia for two given topics of interest, and generate a ranked list of concept chains as potential associations between the two given topics. In comparison to traditional cross-document mining models where documents are usually domain-specific, the system proposed here is capable of handling different query scenarios across domains without being limited to the given documents. Authors highlight the importance of this problem in various domains, present experiments on different datasets and compare the mining results with two competitive baseline models to demonstrate the improved performance of system. | ||
Revision as of 14:10, 23 November 2019
Authors | Peng Yan Wei Jin |
|---|---|
Publication date | 2014 |
Links |
Wcaminer: a Novel Knowledge Discovery System for Mining Concept Associations Using Wikipedia - scientific work related to Wikipedia quality published in 2014, written by Peng Yan and Wei Jin.
Overview
This paper presents WCAMiner, a system focusing on detecting how concepts are associated by incorporating Wikipedia knowledge. Authors propose to combine content analysis and link analysis techniques over Wikipedia resources, and define various association mining models to interpret such queries. Specifically, algorithm can automatically build a Concept Association Graph (CAG) from Wikipedia for two given topics of interest, and generate a ranked list of concept chains as potential associations between the two given topics. In comparison to traditional cross-document mining models where documents are usually domain-specific, the system proposed here is capable of handling different query scenarios across domains without being limited to the given documents. Authors highlight the importance of this problem in various domains, present experiments on different datasets and compare the mining results with two competitive baseline models to demonstrate the improved performance of system.
