Focused Citation Count: A Combined Measure of Relevancy and Quality
Focused Citation Count: A Combined Measure of Relevancy and Quality
复制标题
重点引用计数：相关性和质量的综合衡量标准
DOI：
10.1109/iiai-aai.2015.282
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
S. Hirokawa
中科院分区：
文献类型：
--
作者：
T. Nakatoh;H. Nakanishi;K. Baba;S. Hirokawa
科技论文的文献调查取决于所获得的列表的相关性和质量。相关性可以由适当的搜索查询和搜索结果的相关性排名来控制。引文计数（CC）被广泛使用，并作为一个简单的措施来评估文章的质量有用。然而，具有高引用计数的文章可能覆盖广泛的区域，而它们可能与查询的相关性较低。此外，相关性和引文数是两个独立的衡量标准，我们不能同时选择。本文提出了“聚焦引文计数”（FCC）方法，该方法仅关注相关论文的引文计数。通过对引用目标文章的文章进行限制，实现了相关性和质量的统一。采用P@N方法对10,186篇“文献计量学”文献进行了实证评价。它被证实，通过所提出的方法FCC的排名获得了超过0.8，并优于传统的排名CC的得分低于0.6。
Literature survey of scientific articles depends on the relevancy and the quality of the obtained list. Relevancy might be controlled by an appropriate search query and the relevancy ranking of the search result. Citation count (CC) is widely used and useful as an easy measure to evaluate the quality of articles. However, articles with high citation count might cover a wide area, while they might have the low relation to a query. Moreover, relevancy and citation count are two independent measures that we cannot choose at the same time. The present paper proposes "Focused Citation Count(FCC)", a novel measure that focuses only on the relevant articles to count the citation. We realize the integration of relevancy and quality by restricting the articles that cite the target article. Empirical evaluation was conducted with 10,186 articles on "bibliometrics" by P@N measure, the average precision at top N search result. It is confirmed that the ranking by the proposed method FCC gained over 0.8 and outperformed the conventional ranking by CC whose score was below 0.6.