文章基本信息

标题：Clustering Hashtags Based on New Hybrid Method and Power Links
本地全文：下载
作者：Mahmoud Rokaya ; Hamza Turabieh ; Sanaa Al Azwari 等
期刊名称：IAENG International Journal of Computer Science
印刷版ISSN：1819-656X
电子版ISSN：1819-9224
出版年度：2021
卷号：48
期号：3
语种：English
出版社：IAENG - International Association of Engineers
摘要：It is very important for various apps to cluster hashtags accurately. Some clustering methods depend on text properties. Since in social media there is complete freedom for users, there much spelling and grammar errors that might make dependence on lexical properties is useless. On the other hand, depending on the metadata of wordnet also affected by the users spelling and grammar errors. Hybrid methods might improve the accuracy of clustering for some extent. In this work, an un-supervised method for clustering hashtags based on text properties, semantic metadata, and power links is presented. The semantic method and lexical method will be combined in a strictly different way to produce a new hybrid method. The proposed hybrid method is supported through Power links to refine the clusters. The experiments proved that the proposed method outperforms each method individually and, also, outperform past hybrid methods. In all results, it is never happened that previous method achieved better results than the proposed method.
关键词：Hashtag;Power Link;Semantic methods;Lexical methods;clustering;hybrid approach;wordnet;Social media