@inproceedings{3f287e62c4d048b790aa1e4379f20b41,
title = "Exploiting the Wisdom of the Crowds for Characterizingand Connecting Heterogeneous Resources",
abstract = "Heterogeneous content is an inherent problem for cross-system search, recommendation and personalization. In this paper we investigate differences in topic coverage and the impact of topics in different kinds of Web services. We use entity extraction and categorization to create fingerprints that allow for meaningful comparison. As a basis taxonomy, we use the 23 main categories of Wikipedia Category Graph, which has been assembled over the years by the wisdom of the crowds. Following a proof of concept of our approach, we analyze differences in topic coverage and topic impact. The results show many differences between Web services like Twitter, Flickr and Delicious, which reflect users' behavior and the usage of each system. The paper concludes with a user study that demonstrates the benefits of fingerprints over traditional textual methods for recommendations of heterogeneous resources.",
keywords = "classification, comparison, domain independent, fingerprints, twikime, wikipedia",
author = "Ricardo Kawase and Patrick Siehndel and \{Pereira Nunes\}, Bernardo and Eelco Herder and Wolfgang Nejdl",
year = "2014",
month = sep,
day = "1",
doi = "10.1145/2631775.2631797",
language = "English",
isbn = "9781450329545",
series = "HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media",
publisher = "Association for Computing Machinery (ACM)",
pages = "56--65",
booktitle = "HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media",
address = "United States",
note = "25th ACM Conference on Hypertext and Social Media, HT 2014 ; Conference date: 01-09-2014 Through 04-09-2014",
}