Matches in ScholarlyData for { <https://w3id.org/scholarlydata/inproceedings/www2012/poster/256> ?p ?o. }
Showing items 1 to 15 of
15
with 100 items per page.
- 256 creator cheng-te-li.
- 256 creator hsun-ping-hsieh.
- 256 creator shou-de-lin.
- 256 type InProceedings.
- 256 label "Frequent Temporal Social Behavior Search in Information Networks".
- 256 sameAs 256.
- 256 abstract "In current social networking service (SNS) like Facebook, there are increasing and changing social interactions among diverse entity types. Users in SNS may be interested in tracking an individual’s frequent and representative temporal behaviors. This inspires us to propose a new problem of frequent temporal social behavior search. Given a structural query with associated temporal labels, how to find the instances with matched structure and temporal clues in a heterogeneous network? In this paper, we propose a Temporal Social Behavior Search (TSBS) to achieve such query search. In our TSBS, a query can be (a) a simple structure, (b) a structure with partially assigned individuals, or (c) a structure with assigned individuals and temporal label sequence. Our TSBS consists of two parts: offline mining, and online matching. For the offline part, we propose a novel pattern mining algorithm to retrieve significant social interaction patterns, termed Temporal Subgraph Patterns. For the online part, based on the given query, we perform the structural matching with the mined patterns and return the top-k resulting subgraphs. We conduct the experiments on academic real datasets to demonstrate the effectiveness of our TSBS and show the results of different structural queries in case studies.".
- 256 hasAuthorList authorList.
- 256 isPartOf proceedings.
- 256 isPartOf proceedings.
- 256 keyword "Heterogeneous networks".
- 256 keyword "Social search".
- 256 keyword "Structural matching".
- 256 keyword "Temporal subgraph pattern mining".
- 256 title "Frequent Temporal Social Behavior Search in Information Networks".