Method for monitoring online communities

Provided is a method for efficiently monitoring anomalies generated in an online community using a lexical semantic pattern (LSP). The method for monitoring an online community includes the steps of: (a) previously constructing LSP knowledge by defining concept, meaning qualities and the LSP for mon...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	GO, JUN HO, JANG, JUNG HOON, WON, JONG KYU
Format:	Patent
Sprache:	eng ; kor
Schlagworte:	CALCULATING COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Provided is a method for efficiently monitoring anomalies generated in an online community using a lexical semantic pattern (LSP). The method for monitoring an online community includes the steps of: (a) previously constructing LSP knowledge by defining concept, meaning qualities and the LSP for monitoring harmful contents; (b) extracting a web document from a web page of an online community; (c) analyzing the morphemes of the sentences constituting the web document and detecting the LSP matched with each sentence from the LSP knowledge; and (d) calculating a web document risk degree of the web document based on the LSP weight sum using the weight of each LSP and the number of the LSPs matched with the web document and an LSP matching ratio which is a ratio occupied by the matched LSP in the web document. 어휘의미패턴(LSP)을 이용하여 온라인 커뮤니티에서 발생하는 이상징후를 효율적으로 모니티링할 수 있는 방법이 제공된다. 이 온라인 커뮤니티 모니터링 방법은, (a) 유해내용의 모니터링에 대하여 컨셉, 의미자질 및 LSP를 정의하여 LSP 지식을 사전에 구축하는 단계와, (b) 온라인 커뮤니티의 웹 페이지로부터 웹문서를 추출하는 단계와, (c) 웹문서를 구성하는 문장들의 형태소를 분석하여 각 문장에 매칭하는 LSP를 LSP 지식으로부터 검출하는 단계와, (d) 웹문서에 매칭된 LSP의 개수와 각 LSP의 가중치를 이용한 LSP 가중치 합과, 웹문서에서 매칭된 LSP가 차지하는 비율인 LSP매칭비율을 기준으로 웹문서에 대한 웹문서위험도를 산출하는 단계를 포함한다.