Detecting research topics via the correlation between graphs and texts

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{DBLP:conf/kdd/JoLG07,

• author = "Yookyung Jo and Carl Lagoze and C. Lee Giles",
• title = "Detecting research topics via the correlation between graphs and texts",
• booktitle = "Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining KDD-2007",
• year = "2007",
• editor = "Pavel Berkhin and Rich Caruana and Xindong Wu",
• pages = "370--379",
• address = "San Jose, California, USA",
• month = aug # " 12-15",
• publisher = "ACM",
• keywords = "genetic algorithms, genetic programming, Algorithms, Languages, Measurement, topic detection, graph mining, probabilistic measure, citation graphs, correlation of text and links",
• isbn13 = "978-1-59593-609-7",
• bibsource = "DBLP, http://dblp.uni-trier.de",
• DOI = "doi:10.1145/1281192.1281234",
• size = "10 pages",
• abstract = "In this paper we address the problem of detecting topics in large-scale linked document collections. Recently, topic detection has become a very active area of research due to its utility for information navigation, trend analysis, and high-level description of data. We present a unique approach that uses the correlation between the distribution of a term that represents a topic and the link distribution in the citation graph where the nodes are limited to the documents containing the term. This tight coupling between term and graph analysis is distinguished from other approaches such as those that focus on language models. We develop a topic score measure for each term, using the likelihood ratio of binary hypotheses based on a probabilistic description of graph connectivity. Our approach is based on the intuition that if a term is relevant to a topic, the documents containing the term have denser connectivity than a random selection of documents. We extend our algorithm to detect a topic represented by a set of terms, using the intuition that if the co-occurrence of terms represents a new topic, the citation pattern should exhibit the synergistic effect. We test our algorithm on two electronic research literature collections, arXiv and Citeseer. Our evaluation shows that the approach is effective and reveals some novel aspects of topic detection.",
• notes = "GP literature used as one example",

}

Genetic Programming entries for Yookyung Jo Carl Lagoze C Lee Giles

Citations