|
| << vorige | volgende >> |
Tijdschrift beschrijving
Alle jaargangen van het bijbehorende tijdschrift
Alle afleveringen van het bijbehorende jaargang
Alle artikelen van de bijbehorende aflevering
Details van artikel 17 van 43 gevonden artikelen
| Titel: |
Clustering Posts in Online Discussion Forum Threads |
| Auteur: |
Dina Said Nayer Wanas |
| Verschenen in: |
International journal of computer science and information technology |
| Paginering: | Jaargang 3 (2011) nr. 2 pagina's 1-14 |
| Jaar: |
2011 |
| Inhoud: |
Online discussion forums are considered a challenging repository for data mining tasks. Forums usuallycontain hundreds of threads which in turn consist of hundreds, or even thousands, of posts. Clusteringposts can be used to discover outlier and off-topic posts and would provide better visualization andexploration of online threads.In this paper, we propose the Leader-based Post Clustering (LPC), amodification to the Leader algorithm to be applied to the domain of clustering posts in threads ofdiscussion boards. We also suggest using asymmetric pair-wise distances to measure the dissimilaritybetween posts. We further investigate the effect of indirect distance between posts, and how to calibrate itwith the direct distance. In order to evaluate the proposed methods, we conduct experiments usingartificial and real threads extracted from Slashdot and Ciao discussion forums. Experimental resultsdemonstrate the effectiveness of the LPC algorithm when using the linear combination of direct andindirect distances, as well as using an averaging approach to evaluate a representative indirect distance.Furthermore, the results show the potential of the LPC algorithm for detecting off-topic or outlier postscompared with two state-of-the-art methods for off-topic post detection. |
| Uitgever: |
Academy & Industry Research Collaboration Center (AIRCC) (provided by DOAJ) |
| Bronbestand: |
Elektronische Wetenschappelijke Tijdschriften |
Details van artikel 17 van 43 gevonden artikelen
| << vorige | volgende >> |