Efficient mining of correlated sequential patterns based on null hypothesis

Abstract

Frequent pattern mining has been a widely studied topic in the research area of data mining for more than a decade. However, pattern mining with real data sets is complicated -a huge number of co-occurrence patterns are usually generated, a majority of which are either redundant or uninformative. The true correlation relationships among data objects are buried deep among a large pile of useless information. To overcome this difficulty, mining correlations has been recognized as an important data mining task for its many advantages over mining frequent patterns.In this paper, we formally propose and define the task of mining frequent correlated sequential patterns from a sequential database. With this aim in mind, we re-examine various interestingness measures to select the appropriate one(s), which can disclose succinct relationships of sequential patterns. We then propose PSBSpan, an efficient mining algorithm based on the framework of the pattern-growth methodology which mines frequent correlated sequential patterns. Our experimental study on real datasets shows that our algorithm has outstanding performance in terms of both efficiency and effectiveness.

Extracting user behavior-related words and phrases using temporal patterns of sequential pattern evaluation indices

“…sequential item set [8] and an evaluation index group that considers the items in a sequential pattern [9]. We consider a sequence α to be the term term i and each item to be word…”

Proceedings of ACL-IJCNLP 2015 System Demonstrations

“…• The limited coverage of a Knowledge Base (KB) is another challenge facing NED for tweets. According to (Lin et al, 2012), 5 million out of 15 million mentions on the Web cannot be linked to Wikipedia. This means that relying only on a KB for NED leads to around 33% loss in the disambiguated entities.…”