For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Method of Classifying Relationships between Hashtags Using Co-occurrence and Latent Topics
Tasuku KIMURA Hisashi MIYAMORI
D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)
Publication Date: 2015/08/01
Online ISSN: 1881-0225
Type of Manuscript: PAPER
Twitter, hashtag, folksonomy, structuring, information recommend,
Full Text(in Japanese): PDF(1.1MB)
>>Buy this Article
In Twitter, using hashtags can obtain users useful information by searching and sharing tweets that indicate topic. Unfortunately, However, hashtags to be recommended in existing approaches may not necessarily be familiar users. Therefore, we considered it would help users utilize such unfamiliar hashtags, to full extent, to present relationships between popular hashtags and unfamiliar ones. In this paper, we propose a new method for classifying relationships hashtags into four categories. To confirm the efficacy of our method, we performed evaluation experiment about estimating accuracy of relationship between hashtags.