Deyi Li

From WikiPapers
Jump to: navigation, search

Deyi Li is an author.

Publications

Only those publications related to wikis are shown here.
Title Keyword(s) Published in Language DateThis property is a special property in this wiki. Abstract R C
Survey on statics of Wikipedia Collective intelligence
Statistics
Wiki
Wikipedia
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University Chinese 2012 This paper mainly focuses on the Wikipedia, a collaborative editing pattern in Web 2. 0. The articles, editors and the editing relationships between the two ones are three important components in Wikipedia statistical analysis. We collected different kinds of statistical tools, methods and results, and further analyzed the problems in the current statistics researches and discussed the possible resolutions. 0 0
A Research for the Centrality of Article Edit Collective in Wikipedia Wikipedia
Article edit interaction network
Centrality
Networked data mining
Collective intelligence
ICM English 2011 0 0
Quality of articles in Wikipedia Collective intelligence
Quality of article evaluation
Wiki
Wikipedia
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University Chinese 2011 The recent research of wikipediais is firs briefly analyzed, especially on the statistics of quality of articles in Wikipedia. Then the automatic evaluating methods of article quality are discussed. The methods mainly include two kinds: the correlation-based analysis and cooperation modeling. Furthermore, we present the open problems of automatic quality evaluation and the possiblepromotions of collective intelligence. 0 0
There exist correlations between editing behaviors and hyperlinks structure in Wikipedia Human behavior dynamics
Social network analysis
Wikipedia
Proceedings - 2011 IEEE International Conference on Granular Computing, GrC 2011 English 2011 The co-editing in Wikipedia is a typical and complex collective behavior with lots of voluntary editors' participation, while the relationship between the edit behaviors and the hyperlink structure of articles remains unknown until now. In this paper, we try to explore the correlation between them via a novel two-layer network. In this two-layer network, we model the articles in Wikipedia as nodes, and model the edits and hyperlinks as the edges of two layers respectively. Here, the correlation is suggested to be measured by a structure similarity metric. By analyzing the structure similarity of two layers via a method named partially ordered ranking, we find that there exist significant and stable correlations: in our sample dataset composed of four Wikipedia categories, the structure similarity is around 0.6, which is two times than that of a theoretical random network. Furthermore, if turn back to the initial stage of categories, i.e., take the evolution into consideration, the correlation is evolving too. Usually the evolution undergoes a sharp decline stage from the initial high value, and at last it tends to the stable value around 0.6. 0 0
Visualizing revisions and building semantic network in Wikipedia Semantic Network
Visualisation
Wikipedia
Proceedings - 2011 International Conference on Cloud and Service Computing, CSC 2011 English 2011 Wikipedia, one of the largest online encyclopedias, is competent to Britannica. Articles are subject to day to day changes by authors, and each such change is recorded as a new revision. In this paper, we visualize the article's revisions and build the semantic network between articles. First, we analyze the revisions difference of article and using color to show the revisions change. Second, through the article's classified information, we constructed a semantic network of articles' relationship. 0 0
A semi-supervised key phrase extraction approach: Learning from title phrases through a document semantic network ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference English 2010 It is a fundamental and important task to extract key phrases from documents. Generally, phrases in a document are not independent in delivering the content of the document. In order to capture and make better use of their relationships in key phrase extraction, we suggest exploring the Wikipedia knowledge to model a document as a semantic network, where both n-ary and binary relationships among phrases are formulated. Based on a commonly accepted assumption that the title of a document is always elaborated to reflect the content of a document and consequently key phrases tend to have close semantics to the title, we propose a novel semi-supervised key phrase extraction approach in this paper by computing the phrase importance in the semantic network, through which the influence of title phrases is propagated to the other phrases iteratively. Experimental results demonstrate the remarkable performance of this approach. 0 0
Efficient Wikipedia-based semantic interpreter by exploiting top-k processing Concept
Semantic interpretation
Wikipedia
International Conference on Information and Knowledge Management, Proceedings English 2010 Proper representation of the meaning of texts is crucial to enhancing many data mining and information retrieval tasks, including clustering, computing semantic relatedness between texts, and searching. Representing of texts in the concept-space derived from Wikipedia has received growing attention recently, due to its comprehensiveness and expertise. This concept-based representation is capable of extracting semantic relatedness between texts that cannot be deduced with the bag of words model. A key obstacle, however, for using Wikipedia as a semantic interpreter is that the sheer size of the concepts derived from Wikipedia makes it hard to efficiently map texts into concept-space. In this paper, we develop an efficient algorithm which is able to represent the meaning of a text by using the concepts that best match it. In particular, our approach first computes the approximate top-k concepts that are most relevant to the given text. We then leverage these concepts for representing the meaning of the given text. The experimental results show that the proposed technique provides significant gains in execution time over current solutions to the problem. 0 0